diff --git a/spaces/1acneusushi/gradio-2dmoleculeeditor/data/ABBYY FineReader 12.0.101.264 Professional cRACk-Pafnutiy761 full version Review and Comparison.md b/spaces/1acneusushi/gradio-2dmoleculeeditor/data/ABBYY FineReader 12.0.101.264 Professional cRACk-Pafnutiy761 full version Review and Comparison.md deleted file mode 100644 index 90eba056613f6b717485e5612149ff301ca003eb..0000000000000000000000000000000000000000 --- a/spaces/1acneusushi/gradio-2dmoleculeeditor/data/ABBYY FineReader 12.0.101.264 Professional cRACk-Pafnutiy761 full version Review and Comparison.md +++ /dev/null @@ -1,104 +0,0 @@ - -

Readiris Pro 11: A Powerful OCR Solution for Windows

-

If you are looking for a way to convert your paper documents into digital formats, edit and annotate your PDF files, recognize text in multiple languages, and export your files to various applications and cloud services, then you might be interested in Readiris Pro 11. Readiris Pro 11 is an optical character recognition (OCR) software that can scan, recognize, and convert any type of document into editable text, image, or PDF formats. In this article, we will tell you what Readiris Pro 11 can do, how to download and install it for free using a crack, what are the risks and drawbacks of using a cracked version, and what are some alternatives to Readiris Pro 11 crack.

-

What is Readiris Pro 11 and what can it do?

-

Readiris Pro 11 is an OCR software developed by I.R.I.S., a Belgian company that specializes in document management and recognition solutions. Readiris Pro 11 was released in 2006 as the eleventh version of the Readiris software series. It is compatible with Windows XP, Vista, 7, 8, and 10 operating systems. It can scan and recognize text from any type of document, such as paper documents, books, magazines, invoices, receipts, business cards, photos, etc. It can also convert scanned documents into editable text formats, such as Word, Excel, PowerPoint, HTML, TXT, RTF, etc. It can also create searchable PDF files with annotations and bookmarks. It can recognize text in more than 120 languages, including Asian languages and Arabic. It can export the converted files to various applications and cloud services, such as Microsoft Office, Google Drive, Dropbox, Evernote, etc.

-

readiris pro 11 free download crack for gta


DOWNLOAD >> https://byltly.com/2uKvbL



-

Features and benefits of Readiris Pro 11

-

Readiris Pro 11 has many features and benefits that make it a powerful OCR solution for Windows users. Here are some of them:

-

Convert paper documents to digital formats

-

Readiris Pro 11 can scan any type of paper document using a scanner or a digital camera. It can then recognize the text and layout of the document and convert it into an editable text format. You can choose from various output formats depending on your needs and preferences. For example, you can convert your paper documents into Word files if you want to edit them later. You can also convert them into Excel files if you want to work with numbers and data. You can also convert them into PowerPoint files if you want to create presentations. You can also convert them into HTML files if you want to publish them on the web.

-

Edit and annotate PDF files

-

Readiris Pro 11 can also create searchable PDF files from your scanned documents. You can then edit and annotate your PDF files using the built-in PDF editor. You can add comments, highlights, stamps, signatures, etc. to your PDF files. You can also create bookmarks and hyperlinks to navigate through your PDF files. You can also merge or split PDF files as you wish.

-

Recognize text in multiple languages

-

Readiris Pro 11 can recognize text in more than 120 languages, including Asian languages and Arabic. You can select the language of your document before scanning it or let Readiris Pro 11 detect it automatically. You can also scan documents that contain multiple languages and let Readiris Pro 11 recognize them separately. You can also use the spell checker and the dictionary to correct any errors or typos in your recognized text.

-

Export to various applications and cloud services

-

Readiris Pro 11 can export your converted files to various applications and cloud services that you use regularly. For example, you can export your files to Microsoft Office applications such as Word, Excel, PowerPoint, etc. You can also export your files to Google Drive, Dropbox, Evernote, etc. where you can store them online or access them from any device. You can also export your files to email clients such as Outlook or Gmail where you can send them as attachments.

-

How to download and install Readiris Pro 11 for free

-

If you want to use Readiris Pro 11 without paying for it

How to download and install Readiris Pro 11 for free

-

If you want to use Readiris Pro 11 without paying for it, you might be tempted to download and install a cracked version of the software. A crack is a program that modifies the original software to bypass its security features and allow unauthorized use. However, downloading and installing a crack is not as easy or safe as it sounds. Here are the steps you need to follow to get Readiris Pro 11 for free using a crack:

-

Find a reliable source of Readiris Pro 11 crack

-

The first step is to find a website that offers Readiris Pro 11 crack for download. You can use a search engine like Google or Bing to look for keywords like "readiris pro 11 free download crack" or "readiris pro 11 keygen". However, you need to be careful about the websites you visit and the files you download. Many websites that offer cracks are full of ads, pop-ups, malware, viruses, and other threats that can harm your computer and your data. You also need to check the comments and reviews of other users who have downloaded the crack to see if it works or not.

-

readiris pro 11 full version free download with crack
-how to install readiris pro 11 cracked on windows 10
-readiris pro 11 activation code generator for gta v
-download readiris pro 11 patch for gta san andreas
-readiris pro 11 serial key free download no survey
-readiris pro 11 crack only download for gta iv
-readiris pro 11 license key crack for gta vice city
-readiris pro 11 torrent download with crack for gta 3
-readiris pro 11 keygen download for gta 5
-readiris pro 11 portable free download with crack for gta online
-readiris pro 11 mac crack download for gta sa
-readiris pro 11 windows 7 crack download for gta vc
-readiris pro 11 rar password crack for gta iv
-readiris pro 11 zip file free download with crack for gta lcs
-readiris pro 11 mega download link with crack for gta vcs
-readiris pro 11 mediafire download with crack for gta cw
-readiris pro 11 google drive download with crack for gta ct
-readiris pro 11 dropbox download with crack for gta advance
-readiris pro 11 zippyshare download with crack for gta london
-readiris pro 11 direct download link with crack for gta berlin
-readiris pro 11 latest version free download with crack for gta rio
-readiris pro 11 update download with crack for gta tokyo
-readiris pro 11 offline installer free download with crack for gta moscow
-readiris pro 11 setup.exe free download with crack for gta new york
-readiris pro 11 iso file free download with crack for gta paris
-readiris pro 11 dmg file free download with crack for gta sydney
-readiris pro 11 ocr software free download with crack for gta dubai
-readiris pro 11 pdf converter free download with crack for gta london
-readiris pro 11 scanner software free download with crack for gta berlin
-readiris pro 11 document management software free download with crack for gta rio
-readiris pro 11 image to text converter free download with crack for gta tokyo
-readiris pro 11 text to speech software free download with crack for gta moscow
-readiris pro 11 speech to text software free download with crack for gta new york
-readiris pro 11 barcode reader software free download with crack for gta paris
-readiris pro 11 qr code scanner software free download with crack for gta sydney
-readiris pro 11 business card scanner software free download with crack for gta dubai
-readiris pro 11 invoice scanner software free download with crack for gta london
-readiris pro 11 receipt scanner software free download with crack for gta berlin
-readiris pro 11 form scanner software free download with crack for gta rio
-readiris pro 11 signature scanner software free download with crack for gta tokyo
-readiris pro 11 handwriting recognition software free download with crack for gta moscow
-readiris pro 11 arabic ocr software free download with crack for gta new york
-readiris pro 11 chinese ocr software free download with crack for gta paris
-readiris pro 11 japanese ocr software free download with crack for gta sydney
-readiris pro 11 korean ocr software free download with crack for gta dubai
-readiris pro 11 hindi ocr software free download with crack for gta london
-readiris pro 11 urdu ocr software free download with crack for gta berlin
-readiris pro 11 persian ocr software free download with crack for gta rio
-readiris pro 11 hebrew ocr software free download with crack for gta tokyo
-readiris pro 11 thai ocr software free download with crack for gta moscow

-

Follow the instructions to install and activate the software

-

The second step is to follow the instructions provided by the website or the crack file to install and activate Readiris Pro 11. Usually, you need to download a zip or rar file that contains the crack and the setup file of Readiris Pro 11. You need to extract the files using a program like WinRAR or 7-Zip. Then, you need to run the setup file of Readiris Pro 11 and follow the installation wizard. After that, you need to copy and paste the crack file into the installation folder of Readiris Pro 11. Sometimes, you also need to run the crack file as an administrator or enter a serial number or a license key that is provided by the crack.

-

Scan your system for viruses and malware

-

The third step is to scan your system for viruses and malware using a reliable antivirus or anti-malware program. This is because cracks often contain malicious code that can infect your system and compromise its security. You might not notice it at first, but cracks can steal your personal information, damage your files, slow down your performance, display unwanted ads, or even lock your system until you pay a ransom. Therefore, it is important to scan your system regularly and remove any threats that are detected.

-

Risks and drawbacks of using Readiris Pro 11 crack

-

While using Readiris Pro 11 crack might seem like a good idea at first, it actually comes with many risks and drawbacks that outweigh its benefits. Here are some of them:

-

Legal issues and penalties

-

Using Readiris Pro 11 crack is illegal and unethical. It violates the intellectual property rights of I.R.I.S., the developer of Readiris Pro 11. It also breaches the terms and conditions of the software license agreement that you agree to when you install Readiris Pro 11. If you are caught using Readiris Pro 11 crack, you could face legal consequences such as fines, lawsuits, or even jail time. You could also lose your reputation and credibility as a professional or a student.

-

Software errors and malfunctions

-

Using Readiris Pro 11 crack is unreliable and unstable. It can cause software errors and malfunctions that affect its performance and functionality. For example, Readiris Pro 11 crack might not recognize some documents correctly or convert them accurately. It might also crash or freeze frequently or fail to export your files properly. It might also conflict with other programs on your system or cause compatibility issues with your scanner or camera.

-

Security threats and data loss

-

Using Readiris Pro 11 crack is risky and dangerous. It can expose your system and your data to security threats such as viruses, malware, spyware, ransomware, etc. These threats can infect your system and compromise its security. They can also steal your personal information, damage your files, slow down your performance, display unwanted ads, or even lock your system until you pay a ransom. You could also lose your data if Readiris Pro 11 crack corrupts or deletes your files during conversion or export.

-

Alternatives to Readiris Pro 11 crack

-

If you want to use an OCR software like Readiris Pro 11 without breaking the law or risking your system and data, you have some alternatives that are better than using a crack. Here are some of them:

-

Buy the official version of Readiris Pro 11

-

The best alternative to using Readiris Pro 11 crack is to buy the official version of Readiris Pro 11 from I.R.I.S.'s website or an authorized reseller. By buying the official version of Readiris Pro 11

, you will get the full features and benefits of the software without any limitations or risks. You will also get free updates and technical support from I.R.I.S. The official price of Readiris Pro 11 is $129.99, but you can find some discounts and offers online. For example, if you are a registered user of Readiris OCR software, you can get an exclusive $70 discount for Readiris Pro 11 for Windows or Mac OS X. You can also buy Readiris Pro 11 Corporate Edition with more advanced features for $299.99 instead of $399.00.

-

Use a free online OCR service

-

If you don't want to buy Readiris Pro 11, but you still need to convert some documents occasionally, you can use a free online OCR service. There are many websites that offer free OCR services that can scan and recognize your documents and convert them into various formats. You just need to upload your document to the website and choose the output format and language. Some of the popular free online OCR services are OnlineOCR.net, FreeOCR.net, i2OCR.com, etc. However, you need to be aware of some limitations and drawbacks of using free online OCR services. For example, they might have a file size limit, a page limit, a language limit, or a quality limit. They might also not support some features such as PDF editing, table recognition, handprint recognition, etc. They might also not guarantee the privacy and security of your documents.

-

Try a different OCR software

-

If you are not satisfied with Readiris Pro 11 or its alternatives, you can also try a different OCR software that suits your needs and preferences. There are many OCR software available in the market with different features and prices. Some of them are free, some of them are paid, some of them are online, some of them are offline. You can compare and contrast different OCR software based on their reviews, ratings, testimonials, demos, etc. Some of the popular OCR software are ABBYY FineReader, Adobe Acrobat Pro DC, OmniPage Ultimate, etc.

-

Conclusion

-

In conclusion, Readiris Pro 11 is a powerful OCR software that can scan and convert any type of document into editable text, image, or PDF formats. It has many features and benefits that make it a useful tool for personal and professional use. However, using Readiris Pro 11 crack is illegal and risky. It can cause legal issues and penalties, software errors and malfunctions, security threats and data loss. Therefore, it is better to avoid using Readiris Pro 11 crack and use one of its alternatives instead. You can buy the official version of Readiris Pro 11 from I.R.I.S.'s website or an authorized reseller. You can also use a free online OCR service or try a different OCR software.

-

FAQs

- -

0a6ba089eb
-
-
\ No newline at end of file diff --git a/spaces/1acneusushi/gradio-2dmoleculeeditor/data/Cracku Number System The Ultimate Guide to Ace Any Competitive Exam.md b/spaces/1acneusushi/gradio-2dmoleculeeditor/data/Cracku Number System The Ultimate Guide to Ace Any Competitive Exam.md deleted file mode 100644 index f083d131067c4ed5b77e36a355682cde3ae59997..0000000000000000000000000000000000000000 --- a/spaces/1acneusushi/gradio-2dmoleculeeditor/data/Cracku Number System The Ultimate Guide to Ace Any Competitive Exam.md +++ /dev/null @@ -1,45 +0,0 @@ -
-

How to Master the Cracku Number System for Competitive Exams

-

If you are preparing for competitive exams like CAT, GMAT, GRE, or Bank PO, you might have heard of the Cracku Number System. This is a unique and effective way of solving number-related problems in less time and with more accuracy. But what is the Cracku Number System and how can you learn it?

-

The Cracku Number System is based on the concept of divisibility rules and remainder theorem. It helps you to find out whether a number is divisible by another number, what is the remainder when a number is divided by another number, and how to simplify complex calculations involving large numbers. By using the Cracku Number System, you can avoid lengthy and tedious calculations and save time in the exam.

-

cracku number system


Download Zip ❤ https://byltly.com/2uKxcC



-

Here are some benefits of using the Cracku Number System:

- -

So how can you master the Cracku Number System? Here are some tips:

-
    -
  1. Learn the basic divisibility rules and remainder theorem. You can find them on the Cracku website or in any standard book on quantitative aptitude.
    2. -
  2. Practice solving problems using the Cracku Number System. You can find plenty of practice questions and mock tests on the Cracku website or app. Try to solve them without using a calculator or pen and paper.
    3. -
  3. Analyze your mistakes and learn from them. If you get stuck or make a mistake, check the solution and explanation provided by Cracku. Understand where you went wrong and how to avoid it in the future.
    4. -
  4. Revise and review regularly. The more you practice, the more you will get familiar with the Cracku Number System and its applications. Make sure to revise the concepts and formulas periodically and review your progress.
    5. -
-

The Cracku Number System is a powerful tool that can help you ace any competitive exam that involves numbers. All you need is to learn it, practice it, and apply it. So what are you waiting for? Start your preparation today with Cracku and achieve your dream score!

- -

Some Examples of Using the Cracku Number System

-

To give you a better idea of how the Cracku Number System works, let us look at some examples of problems that can be solved using it. These are taken from various competitive exams and are typical of the kind of questions you might encounter.

-

Example 1: What is the remainder when 7^2021 is divided by 9?

-

Solution: Using the Cracku Number System, we can find the remainder of any power of 7 when divided by 9 by using the following pattern:

-

- - - - - - - - - -
Power of 7Remainder when divided by 9
7^17
7^24
7^31
7^47
7^54
7^61
......
-

We can see that the remainder repeats after every 3 powers of 7. So we can divide the exponent by 3 and find the remainder. In this case, 2021 divided by 3 gives a remainder of 2. So we look at the second row of the table and see that the remainder is 4. Hence, the answer is 4.

-

Example 2: How many positive integers less than 1000 are divisible by both 3 and 5?

-

Solution: Using the Cracku Number System, we can find the number of positive integers less than 1000 that are divisible by both 3 and 5 by using the following formula:

-

N = (Last term - First term) / Common difference + 1

-

The first term is the smallest positive integer that is divisible by both 3 and 5, which is 15. The last term is the largest positive integer that is divisible by both 3 and 5 and less than 1000, which is 990. The common difference is the difference between any two consecutive terms, which is 15. So we plug in these values into the formula and get:

-

N = (990 - 15) / 15 + 1 = (975) / 15 + 1 = 65 + 1 = 66

-

Hence, the answer is 66.

ddb901b051
-
-
\ No newline at end of file diff --git a/spaces/1acneusushi/gradio-2dmoleculeeditor/data/Dont Fall for Revo Uninstaller Pro Crack Reddit Heres How to Get a Legit and Free Uninstaller.md b/spaces/1acneusushi/gradio-2dmoleculeeditor/data/Dont Fall for Revo Uninstaller Pro Crack Reddit Heres How to Get a Legit and Free Uninstaller.md deleted file mode 100644 index 6ac25caff4ee2675540d465cf2925896948e3adb..0000000000000000000000000000000000000000 --- a/spaces/1acneusushi/gradio-2dmoleculeeditor/data/Dont Fall for Revo Uninstaller Pro Crack Reddit Heres How to Get a Legit and Free Uninstaller.md +++ /dev/null @@ -1,29 +0,0 @@ - -# How to Get Revo Uninstaller Pro Crack Reddit for Free - -Revo Uninstaller Pro is a powerful software that helps you uninstall unwanted programs and clean up your system. It has many features such as advanced scanning, forced uninstall, quick/multiple uninstall, and more. However, Revo Uninstaller Pro is not a free software and you need to purchase a license to use it. - -If you are looking for a way to get Revo Uninstaller Pro crack Reddit for free, you might be tempted to download it from some shady websites or torrent sites. However, this is not a good idea as you might end up with malware, viruses, or other problems on your computer. Moreover, using a cracked software is illegal and unethical as it violates the terms and conditions of the software developer. - -So, what is the best way to get Revo Uninstaller Pro crack Reddit for free? The answer is simple: you don't. Instead, you should use a legitimate and safe alternative that can do the same job as Revo Uninstaller Pro without costing you anything. Here are some of the best free alternatives to Revo Uninstaller Pro that you can try: - -- IObit Uninstaller: This is a popular and reliable uninstaller that can remove stubborn programs, browser extensions, Windows apps, and more. It also has a file shredder, a software updater, and a toolbar cleaner. -- Geek Uninstaller: This is a lightweight and portable uninstaller that can scan and remove all traces of programs from your system. It also supports batch uninstallation, force removal, and export to HTML. -- Wise Program Uninstaller: This is a user-friendly and effective uninstaller that can remove programs completely and safely. It also has a repair function that can fix corrupted installations and a rating system that shows how other users rate the programs. - -These are some of the best free alternatives to Revo Uninstaller Pro that you can use to uninstall unwanted programs and optimize your system. They are easy to use, fast, and secure. So, don't waste your time and money on Revo Uninstaller Pro crack Reddit and try these free alternatives instead. - -# How to Use IObit Uninstaller to Remove Programs - -One of the best free alternatives to Revo Uninstaller Pro is IObit Uninstaller. It is a powerful and easy-to-use software that can help you uninstall unwanted programs and clean up your system. Here are the steps to use IObit Uninstaller to remove programs: - -- Step 1: Download and install IObit Uninstaller from here. -- Step 2: Launch IObit Uninstaller and select the programs that you want to uninstall from the list. You can also use the search box or the filter options to find the programs quickly. -- Step 3: Click on the "Uninstall" button and follow the instructions to remove the programs. You can also choose to create a restore point before uninstalling in case you need to restore your system later. -- Step 4: After uninstalling, IObit Uninstaller will scan your system for any leftover files, folders, or registry entries that the programs might have left behind. You can review the results and click on the "Delete" button to remove them completely. -- Step 5: You can also use the other tools in IObit Uninstaller to manage your browser extensions, Windows apps, software updates, and more. - -That's it! You have successfully used IObit Uninstaller to remove unwanted programs and optimize your system. You can enjoy a faster and cleaner PC with IObit Uninstaller.

-

revo uninstaller pro crack reddit


Download File >>> https://byltly.com/2uKvAF



ddb901b051
-
-
\ No newline at end of file diff --git a/spaces/1gistliPinn/ChatGPT4/Examples/Chicken Invaders 4 Multiplayer Patch Download.md b/spaces/1gistliPinn/ChatGPT4/Examples/Chicken Invaders 4 Multiplayer Patch Download.md deleted file mode 100644 index 11ab3d331459886123d4cceee6e493257a3c9c86..0000000000000000000000000000000000000000 --- a/spaces/1gistliPinn/ChatGPT4/Examples/Chicken Invaders 4 Multiplayer Patch Download.md +++ /dev/null @@ -1,7 +0,0 @@ - -

Your review for Chicken Invaders. Your review for Chicken Invaders Thank you for rating! Leave a review. This is embarrassing Try this instead. Some waves have you destroying the chicken invaders who are organized in different formations throughout , while others have you dodging deadly asteroids heading straight for you.

-

Chicken Invaders 4 Multiplayer Patch Download


Download File ……… https://imgfil.com/2uy1vA



-

Disclosures: This game was obtained via paid digital download and reviewed on the PC. Approximately 80 hours of play was devoted to multiplayer modes, and there is no offline option available.

-

I remember the day of the invasion well. The memories still burn deeply, like spicy chicken wings.

They came without warning, squawking menacingly, their ruffled feathers darkening the sun. Invading intergalactic chickens, out to punish humanity for our oppression of their earthly brethren.

I instantly knew what had to be done. I dropped my half-eaten chicken burger and jumped in my cockpit. With a greasy finger I set my lasers to "extra crispy" and blasted off to intercept the fowl invaders.

It wasn't easy. Squawks, feathers flying, the smell of charred chicken everywhere. Three times they invaded, each time with increasingly devious plans. Three times I managed to push them back whence they came, and secure humanity a few more years as the dominant species of this planet.

After their last retreat, I headed for my local Space Burger to bask in the glow of my recent victory. Breathing a sigh of relief, I sat down to enjoy a double chicken-burger with crispy chicken wings on the side.

Little did I know that my greatest adventure was yet to come...

aaccfb2cb3
-
-
\ No newline at end of file diff --git a/spaces/1gistliPinn/ChatGPT4/Examples/Desamuduru Telugu Movie Dialogues Download Movies.md b/spaces/1gistliPinn/ChatGPT4/Examples/Desamuduru Telugu Movie Dialogues Download Movies.md deleted file mode 100644 index b7affb57df53ba1e87b4c024f5967ee6a3f3979a..0000000000000000000000000000000000000000 --- a/spaces/1gistliPinn/ChatGPT4/Examples/Desamuduru Telugu Movie Dialogues Download Movies.md +++ /dev/null @@ -1,34 +0,0 @@ - -

Desamuduru: A Romantic Action Entertainer in Telugu

- -

If you are looking for a Telugu movie that has a perfect blend of romance, action, comedy and drama, then you should watch Desamuduru. Desamuduru is a 2007 Telugu movie directed by Puri Jagannadh and starring Allu Arjun and Hansika Motwani in the lead roles. The movie was a blockbuster hit and received positive reviews from critics and audiences alike.

-

desamuduru telugu movie dialogues download movies


Download ->->->-> https://imgfil.com/2uxZ1z



- -

Desamuduru tells the story of Bala Govind (Allu Arjun), a program director in MAA TV, who is known for his fights for justice. He saves a person from goons and gets into trouble with Tambi Durai (Pradeep Rawat), a notorious arrack smuggler. To escape from his wrath, Bala is sent to Kulu Manali to shoot a travel episode, where he meets Vaishali (Hansika Motwani), a sanyasin. He falls in love with her at first sight, but she is reluctant to reciprocate his feelings. However, with the help of Ramaprabha (Ramaprabha), the head sanyasin of the ashram, they get united.

- -

But their happiness is short-lived, as Bala finds out that Vaishali is the daughter of Narayana Patwari, who was killed by Tambi Durai along with his wife. Tambi Durai also forced Vaishali to marry his son Murugan (Subbaraju) before their dead bodies. Vaishali managed to escape and reach Kulu Manali. Bala decides to save Vaishali from Tambi Durai's clutches and bring him to justice.

- -

Desamuduru is a movie that has everything for everyone. It has romance, action, comedy, drama, music and dance. The movie showcases the chemistry between Allu Arjun and Hansika Motwani, who look adorable together. Allu Arjun delivers a power-packed performance as Bala Govind, who is fearless, witty and charming. Hansika Motwani looks beautiful and innocent as Vaishali, who is brave and loyal. Pradeep Rawat plays the role of Tambi Durai with menace and intensity. The supporting cast of Ali, Kovai Sarala, Srinivas Reddy and others provide comic relief and entertainment.

-

- -

The movie also has some memorable dialogues that are catchy and impactful. Some of them are:

- - - -

The movie also has some amazing songs composed by Chakri that are melodious and catchy. Some of them are:

- - - -

Desamuduru is a movie that you can watch with your family and friends and enjoy the entertainment quotient. It is a movie that will make you laugh, cry, cheer and clap. It is a movie that will make you

d5da3c52bf
-
-
\ No newline at end of file diff --git a/spaces/1pelhydcardo/ChatGPT-prompt-generator/assets/Alias The Game - A Run and Gun Game with a Twist - Download Here.md b/spaces/1pelhydcardo/ChatGPT-prompt-generator/assets/Alias The Game - A Run and Gun Game with a Twist - Download Here.md deleted file mode 100644 index 4d1ad3e4381db1959842c391ec24c3580c6b7fc9..0000000000000000000000000000000000000000 --- a/spaces/1pelhydcardo/ChatGPT-prompt-generator/assets/Alias The Game - A Run and Gun Game with a Twist - Download Here.md +++ /dev/null @@ -1,144 +0,0 @@ -
-

Alias: The Game - A Stealth Action Adventure Based on the Hit TV Series

-

If you are a fan of Alias, the popular spy thriller TV series that ran from 2001 to 2006, you might be interested in playing Alias: The Game, a video game adaptation that was released in 2004 for PC, PlayStation 2, and Xbox. In this article, we will review Alias: The Game and tell you everything you need to know about it, from its story and characters, to its gameplay and graphics, to its reception and legacy. Whether you want to relive the adventures of Sydney Bristow, or discover a new stealth action game, read on to find out more.

-

Introduction

-

What is Alias: The Game?

-

Alias: The Game is a 3D third-person stealth action game developed by Acclaim Studios Cheltenham and published by Acclaim Entertainment. It is based on the TV series Alias, created by J.J. Abrams and starring Jennifer Garner as Sydney Bristow, a CIA agent who works undercover for a secret division called SD-6, which she later discovers is actually an enemy organization. The game follows Sydney as she travels around the world, infiltrates enemy bases, fights against various villains, and uncovers the mysteries of a mysterious device called the Rambaldi artifact.

-

alias the game download


Download File ✦✦✦ https://urlin.us/2uSVtG



-

Who are the main characters and enemies?

-

The game features many of the main characters from the TV series, both as allies and enemies. You play as Sydney Bristow, voiced by Jennifer Garner, who is assisted by her father Jack Bristow (Victor Garber), her handler Michael Vaughn (Michael Vartan), and her tech support Marshall Flinkman (Kevin Weisman). You also encounter other characters from the show, such as Dixon (Carl Lumbly), Kendall (Terry O'Quinn), Weiss (Greg Grunberg), Francie (Merrin Dungey), Will (Bradley Cooper), and Sark (David Anders).

-

The game also features some of the most notorious villains from the TV series, such as Arvin Sloane (Ron Rifkin), the leader of SD-6 and Sydney's former mentor; Anna Espinosa (Gina Torres), Sydney's rival agent who works for K-Directorate; and Julian Sark (David Anders), a mercenary who works for various factions. You will have to face them in various missions, as well as other enemies such as guards, snipers, hackers, and bosses.

-

What is the plot of the game?

-

The plot of the game is set between episodes 19 and 20 of season 2 of the TV series. It revolves around Sydney's quest to find and retrieve a Rambaldi artifact, a mysterious device that was created by a 15th-century prophet and inventor named Milo Rambaldi. The artifact is believed to have immense power and secrets, and is sought after by various factions, such as SD-6, K-Directorate, The Covenant, and The Alliance. Sydney has to travel to different locations around the world, such as Monte Carlo, Saudi Arabia, Romania, Hong Kong, Rio de Janeiro, and Russia, to find clues and pieces of the artifact, while also dealing with her personal life and relationships.

- Gameplay -

How does the game work?

-

The game is divided into 10 missions, each with a different objective and location. The missions are linear and follow the plot of the game, but you can also explore the environments and find hidden items and secrets. You can also replay the missions to improve your score and unlock bonus features, such as concept art, videos, and cheats.

-

The game is mainly focused on stealth, as you have to avoid detection by enemies and cameras, use disguises and gadgets, and perform silent takedowns. You can also use various weapons, such as pistols, rifles, grenades, and crossbows, but you have limited ammo and using them will alert the enemies. You can also engage in hand-to-hand combat, using punches, kicks, and combos, but you have to be careful not to get overwhelmed by multiple enemies.

-

The game also has some puzzle and hacking elements, as you have to solve riddles, crack codes, bypass security systems, and use your computer skills. You can also use your phone to contact your allies and get information and tips. The game has a simple interface that shows your health, ammo, gadgets, objectives, and map.

-

alias pc game free download
-alias flash game online
-alias board game app
-alias game download full version
-alias run and gun game
-alias game official website
-alias game for android
-alias game tactics
-alias game language options
-alias game cybernetic soldier
-alias game internet archive
-alias game new words
-alias game finland
-alias game 1989
-alias game robots
-alias game video game
-alias game fun and polished
-alias game simple plot
-alias game cdrom
-alias game english version
-alias game mobile game
-alias game partnership with dictionary
-alias game sold in 40 countries
-alias pc eng full version
-alias 1 free online games
-official alias board games
-free download borrow and streaming
-internet archive html5 uploader
-make sure for full version old pc game
-cybernetic soldier who has to fight a bunch of robots
-the fun starts the minute you open the box
-download a free app check out this awesome alias one-player mobile game
-new words annually new words keep alias games fresh local and up to date
-developed and made in finland by tactic games entry to market in 1989
-a.l.i.a.s. is a run and gun game where you play as a cybernetic soldier
-the plot is obviously simple what set this game apart from other flash games was how polished and fun it was
-it was one of the few flash games that felt close to playing a real video game
-korea superconducting tokamak advanced research experiment korea institute of fusion energy
-scientists in south korea have managed to sustain a nuclear fusion reaction running at temperatures in excess of 100 million°C for 30 seconds for the first time
-it's being refered to as the ‘holy grail’ fusion experiment to create a mini sun as it achieved temperatures nearly seven times hotter than the core of the sun

-

What are the main features and mechanics of the game?

-

The game has several features and mechanics that make it unique and fun to play. Some of them are:

- -

How does the game compare to other stealth action games?

-

The game is similar to other stealth action games such as Metal Gear Solid, Splinter Cell, Hitman, and Thief. It has the same elements of sneaking around, using gadgets and weapons, avoiding or neutralizing enemies, and completing objectives. However, it also has some differences that make it stand out from the crowd. Some of them are:

- -

Graphics and Sound

-

How does the game look and sound?

-

The game has decent graphics and sound for its time and platform. The game uses the RenderWare engine, which allows for realistic lighting, shadows, textures, and animations. The game also has a cinematic camera that follows the action and creates a dynamic and immersive experience. The game also has a lot of detail and variety in its environments and characters, which makes the game more appealing and believable.

-

The game also has a great sound design that enhances the gameplay and atmosphere. The game has a catchy and suspenseful soundtrack that matches the mood and tone of the game. The game also has realistic sound effects that make the game more immersive and exciting. The game also has excellent voice acting that brings the characters to life and adds personality and emotion to the game.

-

What are the strengths and weaknesses of the game's presentation?

-

The game's presentation has some strengths and weaknesses that affect the overall quality and enjoyment of the game. Some of them are:

- -

How does the game use the voice talents of the show's cast?

-

The game uses the voice talents of most of the show's main cast members, such as Jennifer Garner, Victor Garber, Michael Vartan, Kevin Weisman, Ron Rifkin, David Anders, Gina Torres, Carl Lumbly, and Terry O'Quinn. They reprise their roles and deliver their lines with the same quality and emotion as they do in the show. They also add some extra dialogue and banter that are not in the show, which makes the game more original and humorous. The game also uses some of the show's guest stars, such as Quentin Tarantino, Vivica A. Fox, and Ricky Gervais, who play minor roles or cameo appearances in the game. The game also has some new voice actors who play some of the new characters or enemies in the game, such as Sydney's new partner Kelly Peyton (Rachel Nichols), or the Russian mobster Yuri Komarov (Andrei Zayats).

-

The game uses the voice talents of the show's cast very well, as they enhance the authenticity and appeal of the game. They make the game feel like an extension of the show, and they make the characters more relatable and memorable. They also add some humor and personality to the game, which makes the game more enjoyable and entertaining.

-

Reception and Legacy

-

How did the game perform commercially and critically?

-

The game did not perform very well commercially or critically, as it was overshadowed by other more popular and successful games in the genre or based on TV shows. The game sold poorly, as it only sold about 100,000 copies worldwide, according to VGChartz. The game also received mixed reviews from critics and players, as it had an average score of 60% on Metacritic and 6.1 on IGN. The game was praised for its faithful adaptation of the show's style and story, its female protagonist, its variety and creativity, and its voice acting. However, it was criticized for its technical issues and glitches, its outdated and low-quality graphics and sound, its inconsistent and unrealistic presentation, and its linear and repetitive gameplay.

-

What are the pros and cons of the game according to reviewers and players?

-

The game has some pros and cons that affect the overall satisfaction and enjoyment of the game. Some of them are:

- -

How did the game influence other games in the genre or based on TV shows?

-

The game did not have much influence on other games in the genre or based on TV shows, as it was not very popular or successful. However, it did have some positive aspects that could inspire other games to improve or innovate. For example, the game showed that it is possible to create a faithful and satisfying adaptation of a TV show's style and story, with the involvement of the show's cast and crew. The game also showed that it is possible to create a female protagonist who is strong, smart, brave, and beautiful, without being sexualized or objectified. The game also showed that it is possible to create a lot of variety and creativity in the gameplay, environments, and challenges, with the use of disguises, gadgets, mini-games, and multiplayer mode.

-

Conclusion

-

Summary of the main points

-

In conclusion, Alias: The Game is a stealth action game based on the TV series Alias, starring Jennifer Garner as Sydney Bristow. The game follows Sydney as she travels around the world, infiltrates enemy bases, fights against various villains, and uncovers the mysteries of a Rambaldi artifact. The game has some strengths and weaknesses in its presentation and gameplay. The game is praised for its faithful adaptation of the show's style and story, its female protagonist, its variety and creativity, and its voice acting. However, the game is criticized for its technical issues and glitches, its outdated and low-quality graphics and sound, its inconsistent and unrealistic presentation, and its linear and repetitive gameplay. The game did not perform well commercially or critically, and it did not have much influence on other games in the genre or based on TV shows. However, it did have some positive aspects that could inspire other games to improve or innovate.

-

Recommendation and rating of the game

-

We would recommend Alias: The Game to fans of the TV series, as they would enjoy the game's faithful adaptation of the show's style and story, and the involvement of the show's cast and crew. We would also recommend the game to female gamers, as they would appreciate the game's female protagonist, who is strong, smart, brave, and beautiful, without being sexualized or objectified. We would also recommend the game to gamers who like stealth action games, as they would find the game's variety and creativity in its gameplay, environments, and challenges, with the use of disguises, gadgets, mini-games, and multiplayer mode.

-

We would not recommend Alias: The Game to gamers who are looking for a high-quality and polished game, as they would be disappointed by the game's technical issues and glitches, its outdated and low-quality graphics and sound, its inconsistent and unrealistic presentation, and its linear and repetitive gameplay. We would also not recommend the game to gamers who are not familiar with or interested in the TV series, as they would not understand or appreciate the game's story and characters.

-

We would rate Alias: The Game 3 out of 5 stars, as it is a decent but flawed game that has some strengths and weaknesses. It is a good game for fans of the TV series, but a mediocre game for everyone else.

-

FAQs

-

197e85843d
-
-
\ No newline at end of file diff --git a/spaces/1pelhydcardo/ChatGPT-prompt-generator/assets/Download AetherSX2 Hack and Enjoy PS2 Emulation with Enhanced Graphics and Performance.md b/spaces/1pelhydcardo/ChatGPT-prompt-generator/assets/Download AetherSX2 Hack and Enjoy PS2 Emulation with Enhanced Graphics and Performance.md deleted file mode 100644 index 5cb60bb302910ddf37123162c75a46da6617a148..0000000000000000000000000000000000000000 --- a/spaces/1pelhydcardo/ChatGPT-prompt-generator/assets/Download AetherSX2 Hack and Enjoy PS2 Emulation with Enhanced Graphics and Performance.md +++ /dev/null @@ -1,107 +0,0 @@ - -

How to Download AetherSX2 Hack: A Guide for PS2 Emulation on Android

-

Do you miss playing your favorite PS2 games on your Android device? Do you want to enjoy them with better graphics, faster speed, and more options? If so, you need to try AetherSX2, the best PS2 emulator for Android. And if you want to take your gaming experience to the next level, you need to download AetherSX2 hack, a modded version of the emulator that allows you to use cheats, 60fps patches, and more. In this article, we will show you how to download and install AetherSX2 hack, and how to use it to enhance your PS2 emulation on Android.

-

What is AetherSX2 and why do you need a hack?

-

AetherSX2 is a free and open-source PS2 emulator for Android that is based on the PCSX2 emulator for PC. It can run most PS2 games at full speed, with custom resolutions, save states, multiple control schemes, and more. It is easily the best PS2 emulator on the platform, as it offers better performance and compatibility than other alternatives.

-

download aethersx2 hack


Download > https://urlin.us/2uSS4Y



-

However, AetherSX2 is not perfect. Some games may have glitches, slowdowns, or compatibility issues. Some features may not work as expected, such as widescreen mode or internal resolution scaling. And some users may not like the ads that were added in March 2023. That's why you may want to download AetherSX2 hack, a modded version of the emulator that removes the ads, enables cheats, 60fps patches, and more. With AetherSX2 hack, you can enjoy your PS2 games with more options and flexibility.

-

How to download and install AetherSX2 hack

-

To download and install AetherSX2 hack, you will need a few things:

-

How to use cheats in AetherSX2 PS2 emulator on Android
-AetherSX2 PS2 emulator Action Replay MAX codes
-AetherSX2 PS2 emulator Code Breaker codes
-AetherSX2 PS2 emulator 60fps patches
-AetherSX2 PS2 emulator performance hacks
-AetherSX2 PS2 emulator disable bloom and motion blur
-AetherSX2 PS2 emulator god hand cheats
-AetherSX2 PS2 emulator god hand unlimited gameplay
-AetherSX2 PS2 emulator texture download link
-AetherSX2 PS2 emulator patch code link
-AetherSX2 PS2 emulator burnout 3 cheats
-AetherSX2 PS2 emulator burnout 3 100% speed
-AetherSX2 PS2 emulator burnout 3 3x resolution
-AetherSX2 PS2 emulator YouTube tutorial
-AetherSX2 PS2 emulator Reddit discussion
-AetherSX2 PS2 emulator best settings
-AetherSX2 PS2 emulator compatible games list
-AetherSX2 PS2 emulator latest version download
-AetherSX2 PS2 emulator APK download
-AetherSX2 PS2 emulator modded APK download
-AetherSX2 PS2 emulator premium APK download
-AetherSX2 PS2 emulator cracked APK download
-AetherSX2 PS2 emulator no ads APK download
-AetherSX2 PS2 emulator free download for Android
-AetherSX2 PS2 emulator free download for PC
-AetherSX2 PS2 emulator free download for iOS
-AetherSX2 PS2 emulator free download for Mac
-AetherSX2 PS2 emulator free download for Linux
-AetherSX2 PS2 emulator free download for Windows 10
-AetherSX2 PS2 emulator free download for Windows 7
-AetherSX2 PS2 emulator free download for Windows XP
-AetherSX2 PS2 emulator free download for Chromebook
-AetherSX2 PS2 emulator free download for Firestick
-AetherSX2 PS2 emulator free download for Smart TV
-AetherSX2 PS2 emulator free download for Raspberry Pi
-AetherSX2 PS2 emulator online play
-AetherSX2 PS2 emulator multiplayer mode
-AetherSX2 PS2 emulator LAN play
-AetherSX2 PS2 emulator Bluetooth controller support
-AetherSX2 PS2 emulator touch screen controller support
-AetherSX2 PS2 emulator save state feature
-AetherSX

- -

Here are the steps to follow:

-
    -
  1. Download the latest version of AetherSX2 hack from this link: . This is an ad-free version of the emulator that has been modified by fans.
    2. -
  2. Install the APK file on your device. You may need to enable unknown sources in your settings.
    3. -
  3. Copy the BIOS file from your PS2 console to your device's storage. You can use a tool like BIOS Dumper to extract it from your console.
    4. -
  4. Launch AetherSX2 hack and select BIOS from the menu. Locate and select the BIOS file you copied.
    5. -
  5. Copy your PS2 games in ISO format to your device's storage. You can use a tool like ImgBurn to rip them from your discs.
    6. -
  6. Launch AetherSX2 hack and select Games from the menu. Locate and select the game you want to play.
    7. -
  7. To apply the hack, you will need either a patch code or a cheat file for the game. You can find patch codes for various games here. You can find cheat files for various games here or here[^6 ^]^].
    8. -
  8. If you have a patch code, you will need to convert it to a cheat file using a tool like OmniConvert. You can follow this guide to learn how to do it.
    9. -
  9. Copy the cheat file to your device's storage, in the folder named cheats_ws under the AetherSX2 folder.
    10. -
  10. Launch AetherSX2 hack and select Settings from the menu. Enable cheats and widescreen patches under System.
    11. -
  11. Launch the game and enjoy the hack. You can also access the cheat menu by pressing the back button on your device.
    12. -
-

How to use AetherSX2 hack to enhance your gaming experience

-

Now that you have downloaded and installed AetherSX2 hack, you can use it to enhance your gaming experience on Android. Here are some tips and tricks to optimize the performance and compatibility of the emulator, and some examples of games that work well with the hack and how to use them.

-

Tips and tricks to optimize the performance and compatibility of AetherSX2 hack

- -

Examples of games that work well with AetherSX2 hack and how to use them

- - - - - - - -
GameHackEffect
God of War IICheat file with 60fps patchDoubles the frame rate from 30fps to 60fps, making the game smoother and more responsive
Shadow of the ColossusCheat file with 60fps patchDoubles the frame rate from 30fps to 60fps, making the game smoother and more responsive
Final Fantasy XIICheat file with widescreen patchExpands the aspect ratio from 4:3 to 16:9, making the game fill the screen without stretching or cropping
Metal Gear Solid 3: Snake EaterCheat file with pressure-sensitive buttonsEnables pressure-sensitive buttons for actions such as aiming, shooting, or choking, making the game more immersive and realistic
Kingdom Hearts II Final MixCheat file with English patchTranslates the game from Japanese to English, making it accessible for non-Japanese speakers
-

Conclusion

-

AetherSX2 is a great PS2 emulator for Android that lets you play your favorite PS2 games on your device. But if you want to make it even better, you should download AetherSX2 hack, a modded version of the emulator that removes ads, enables cheats, 60fps patches, and more. With AetherSX2 hack, you can enjoy your PS2 games with more options and flexibility. Just follow our guide on how to download and install AetherSX2 hack, and how to use it to enhance your gaming experience. Happy gaming!

-

FAQs

-

Q: Is AetherSX2 hack safe and legal?

-

A: AetherSX2 hack is safe as long as you download it from a trusted source. It does not contain any malware or viruses. However, AetherSX2 hack may not be legal in some regions or countries, as it may violate the terms of service of AetherSX2 or infringe on the rights of PS2 game developers or publishers. Use it at your own risk. -

Q: How can I update AetherSX2 hack?

-

A: AetherSX2 hack is updated regularly by the modders who created it. You can check their website or social media for the latest version. You can also use the built-in updater in the emulator to download and install the updates automatically.

-

Q: How can I support AetherSX2 and AetherSX2 hack?

-

A: AetherSX2 is a free and open-source project that relies on donations and contributions from the community. You can support AetherSX2 by donating to their Patreon or PayPal, or by contributing to their GitHub or Discord. You can also support AetherSX2 hack by following and thanking the modders who created it, or by sharing it with your friends.

-

Q: What are some alternatives to AetherSX2 hack?

-

A: If you are looking for other PS2 emulators for Android, you can try DamonPS2, Play!, or PTWOE. However, none of them are as good as AetherSX2 in terms of performance and compatibility. If you are looking for other ways to hack your PS2 games, you can try using a PS2 cheat device such as CodeBreaker, Action Replay, or GameShark. However, you will need a real PS2 console and a compatible disc to use them.

-

Q: Where can I find more information about AetherSX2 hack?

-

A: You can find more information about AetherSX2 hack on their website, their YouTube channel, their Reddit community, or their Telegram group. You can also ask questions, report bugs, request features, or share your feedback on these platforms.

197e85843d
-
-
\ No newline at end of file diff --git a/spaces/1phancelerku/anime-remove-background/Barbie Dreamhouse Adventures APK OBB A Game for Girls Who Love Fashion Cooking and More.md b/spaces/1phancelerku/anime-remove-background/Barbie Dreamhouse Adventures APK OBB A Game for Girls Who Love Fashion Cooking and More.md deleted file mode 100644 index 524aca17de76399cf2ca4791297a65c97818c7ed..0000000000000000000000000000000000000000 --- a/spaces/1phancelerku/anime-remove-background/Barbie Dreamhouse Adventures APK OBB A Game for Girls Who Love Fashion Cooking and More.md +++ /dev/null @@ -1,108 +0,0 @@ -
- - -
-

Barbie Dreamhouse Adventures APK OBB: A Fun Game for Girls

-

If you love Barbie and her friends, you will love Barbie Dreamhouse Adventures APK OBB. This is a fun game for girls that lets you create your own Barbie DreamHouse experience. You can join Barbie and her friends in various activities, such as baking, cooking, dancing, makeovers, home design, fashion, nail salon, hair salon, mini games, pool parties, beach fun, and more. You can also explore Malibu with Barbie's pink convertible or dress up in fashion-forward looks. Plus, you can follow Barbie and her friends on exciting adventures in different scenarios, such as becoming a princess, a mermaid, or going camping.

-

Barbie Dreamhouse Adventures APK OBB is a game that you can download and install on your Android device. It is an XAPK file that contains both APK (application) and OBB (data) files. You will need a special app to install it properly. In this article, we will show you how to download and install Barbie Dreamhouse Adventures APK OBB on your Android device. We will also tell you what you can do in the game and why you should play it. So, let's get started!

-

barbie dreamhouse adventures apk obb


DOWNLOAD ✏ ✏ ✏ https://jinyurl.com/2uNNd1



-

How to Download and Install Barbie Dreamhouse Adventures APK OBB

-

To download and install Barbie Dreamhouse Adventures APK OBB, you will need to follow these steps:

-
    -
  1. Download the XAPK file from APKCombo or other trusted sources. The file size is about 1.1 GB, so make sure you have enough space on your device.
    2. -
  2. Install APKCombo Installer app on your Android device. This app will help you install XAPK files easily and safely. You can download it from Google Play Store or APKCombo website.
    3. -
  3. Open the APKCombo Installer app and tap Install.
    4. -
  4. Select Barbie Dreamhouse Adventures.xapk and tap OK.
    5. -
  5. Follow the steps on screen to complete the installation. The app will extract the APK and OBB files and install them on your device.
    6. -
  6. Once the installation is done, you can launch the game and enjoy it.
    7. -
-

Note: If you have any problems with the installation, you can contact APKCombo support team for help.

-

What Can You Do in Barbie Dreamhouse Adventures APK OBB?

-

Barbie Dreamhouse Adventures APK OBB is a game that lets you create your own Barbie DreamHouse experience. You can join Barbie and her friends in various activities and mini games, such as:

-

Home Design and Makeovers

-

You can design every room in your DreamHouse with wallpapers, furniture, decorations, and more. You can also give your DreamHouse a makeover with new themes, such as tropical, glam, or cozy. You can even change the exterior of your DreamHouse with different colors and styles.

-

Cooking and Baking

-

You can bake delicious recipes with Skipper in the kitchen and share them on BarbieGram. You can also cook different dishes for your friends and family, such as pizza, pasta, salad, cake, etc. You can also decorate your food with toppings and sprinkles.

-

Dress Up and Fashion

-

You can dress up in beautiful outfits and accessories from Barbie's closet. You can also get fashion advice from Nikki, who will help you choose the best look for any occasion. You can also create your own outfits by mixing and matching different pieces of clothing.

-

barbie dreamhouse adventures apk obb download
-barbie dreamhouse adventures apk obb latest version
-barbie dreamhouse adventures apk obb mod
-barbie dreamhouse adventures apk obb free
-barbie dreamhouse adventures apk obb offline
-barbie dreamhouse adventures apk obb android
-barbie dreamhouse adventures apk obb 2023
-barbie dreamhouse adventures apk obb unlimited money
-barbie dreamhouse adventures apk obb full unlocked
-barbie dreamhouse adventures apk obb update
-barbie dreamhouse adventures apk obb install
-barbie dreamhouse adventures apk obb game
-barbie dreamhouse adventures apk obb hack
-barbie dreamhouse adventures apk obb online
-barbie dreamhouse adventures apk obb pc
-barbie dreamhouse adventures apk obb xapk
-barbie dreamhouse adventures apk obb data
-barbie dreamhouse adventures apk obb file
-barbie dreamhouse adventures apk obb revdl
-barbie dreamhouse adventures apk obb rexdl
-barbie dreamhouse adventures apk obb pure
-barbie dreamhouse adventures apk obb apkpure
-barbie dreamhouse adventures apk obb apkmirror
-barbie dreamhouse adventures apk obb apknite
-barbie dreamhouse adventures apk obb apkmody
-barbie dreamhouse adventures apk obb happymod
-barbie dreamhouse adventures apk obb an1
-barbie dreamhouse adventures apk obb andropalace
-barbie dreamhouse adventures apk obb android 1
-barbie dreamhouse adventures apk obb android republic
-barbie dreamhouse adventures apk obb uptodown
-barbie dreamhouse adventures apk obb mob.org
-barbie dreamhouse adventures apk obb mobpark
-barbie dreamhouse adventures apk obb panda helper
-barbie dreamhouse adventures apk obb panda vpn
-barbie dreamhouse adventures apk obb ac market
-barbie dreamhouse adventures apk obb blackmod
-barbie dreamhouse adventures apk obb platinmods
-barbie dreamhouse adventures apk obb moddroid
-barbie dreamhouse adventures apk obb modapkdown
-barbie dreamhouse adventures apk obb modapkdl.io
-barbie dreamhouse adventures apk obb modapkguru.com
-barbie dreamhouse adventures apk obb modapkstore.com
-barbie dreamhouse adventures apk obb modapks.com
-barbie dreamhouse adventures apk obb modapk.io
-barbie dreamhouse adventures apk obb modapk.pro
-barbie dreamhouse adventures apk obb modapk.vip

-

Hairstyles and Nail Salon

-

You can get a makeover at the hair salon and create your own hairstyle with different colors, cuts, and styles. You can also visit the nail spa and create your own nail design with various shapes, colors, patterns, stickers, and gems.

-

Pool Parties and Beach Fun

-

You can dive, swim, grill, lounge, or build a sandcastle at Malibu Beach or the DreamHouse pool. You can also invite your friends to join you for some fun in the sun. You can also play mini games, such as water balloon fight, volleyball, surfing, etc.

-

New Adventures

-

You can follow Barbie and her friends on exciting adventures in different scenarios, such as becoming a princess, a mermaid, or going camping. You can also explore new locations, such as a castle, an underwater world, or a forest. You can also meet new characters, such as a fairy godmother, a dolphin, or a bear.

-

Explore Friends' DreamHouses

-

You can add friends and visit their DreamHouses to see how they decorated them. You can also chat with them and join them in their activities. You can also earn coins by visiting their DreamHouses and use them to buy more items for your own DreamHouse.

-

Why You Should Play Barbie Dreamhouse Adventures APK OBB?

-

Barbie Dreamhouse Adventures APK OBB is a game that you should play because it has many benefits for you, such as:

-

Fun and Educational

-

The game is fun and educational because it teaches you new skills, such as cooking, design, fashion, etc. You can learn how to bake different recipes, how to decorate your rooms, how to dress up for different occasions, etc. You can also improve your creativity and imagination by creating your own style and stories.

-

Creative and Interactive

-

The game is creative and interactive because it lets you express your personality and style through customization and choices. You can design your own DreamHouse according to your preferences and taste. You can also choose what activities you want to do with Barbie and her friends. You can also interact with various objects and characters in the game. You can also use your voice to talk to Barbie and her friends.

-

Social and Friendly

-

The game is social and friendly because it lets you meet new friends and chat with them. You can add friends from around the world and visit their DreamHouses. You can also join them in their activities and adventures. You can also share your creations and stories with them on BarbieGram.

-

Conclusion

-

Barbie Dreamhouse Adventures APK OBB is a fun game for girls that lets you create your own Barbie DreamHouse experience. You can join Barbie and her friends in various activities, such as baking, cooking, dancing, makeovers, home design, fashion, nail salon, hair salon, mini games, pool parties, beach fun, and more. You can also follow Barbie and her friends on exciting adventures in different scenarios, such as becoming a princess, a mermaid, or going camping. The game is fun and educational, creative and interactive, and social and friendly. It is a game that you should download and install on your Android device. So, what are you waiting for? Download Barbie Dreamhouse Adventures APK OBB today and have fun!

-

FAQs

-

Here are some frequently asked questions about Barbie Dreamhouse Adventures APK OBB:

-
    -
  • Q: Is Barbie Dreamhouse Adventures APK OBB free to play?
    • -
  • A: Yes, Barbie Dreamhouse Adventures APK OBB is free to play. However, some items and features may require in-app purchases.
    • -
  • Q: What are the system requirements for Barbie Dreamhouse Adventures APK OBB?
    • -
  • A: You will need an Android device with Android 4.4 or higher and at least 1.1 GB of free space.
    • -
  • Q: How can I update Barbie Dreamhouse Adventures APK OBB?
    • -
  • A: You can update Barbie Dreamhouse Adventures APK OBB by downloading the latest XAPK file from APKCombo or other sources and installing it with the APKCombo Installer app.
    • -
  • Q: How can I contact the developers of Barbie Dreamhouse Adventures APK OBB?
    • -
  • A: You can contact the developers of Barbie Dreamhouse Adventures APK OBB by sending an email to support@budgestudios.ca or visiting their website at https://budgestudios.com/.
    • -
  • Q: How can I get more coins in Barbie Dreamhouse Adventures APK OBB?
    • -
  • A: You can get more coins in Barbie Dreamhouse Adventures APK OBB by completing tasks, playing mini games, visiting friends' DreamHouses, or buying them with real money.
    • -

401be4b1e0
-
-
\ No newline at end of file diff --git a/spaces/1phancelerku/anime-remove-background/Best Music Downloader APK for Android Download Music MP3 Latest Version.md b/spaces/1phancelerku/anime-remove-background/Best Music Downloader APK for Android Download Music MP3 Latest Version.md deleted file mode 100644 index 8122c5d0b1f69373cbfe9086bfcff3a69fac16de..0000000000000000000000000000000000000000 --- a/spaces/1phancelerku/anime-remove-background/Best Music Downloader APK for Android Download Music MP3 Latest Version.md +++ /dev/null @@ -1,98 +0,0 @@ -
-

How to Download Music MP3 APK Latest Version

-

If you love listening to music on your Android device, you might be interested in downloading Music MP3 APK latest version. This is a powerful app that allows you to download and play music from various sources for free. In this article, we will explain what Music MP3 APK is, what features it offers, what benefits it has, and how to download it safely and easily.

-

What is Music MP3 APK?

-

Music MP3 APK is an app that lets you download music from different websites and platforms, such as Jamendo, Free Music Archive, SoundCloud, YouTube, and more . You can also play music online or offline using the built-in music player. You can manage your music library by creating playlists, deleting songs, setting ringtones, and sharing music with others.

-

download music mp3 apk latest version


Download ✓✓✓ https://jinyurl.com/2uNNij



-

Features of Music MP3 APK

-

Music MP3 APK has many features that make it a great app for music lovers. Here are some of them:

-

Download music from various sources

-

You can search for any song or artist you want using the app's search engine. You can also browse through different categories and genres of music. You can download music in MP3 format with high quality and fast speed. You can also download multiple songs at the same time using the download manager.

-

download free music mp3 player apk latest version
-download music mp3 downloader apk latest version for android
-download music mp3 cutter and merger apk latest version
-download music mp3 converter apk latest version offline
-download music mp3 editor apk latest version pro
-download music mp3 ringtone maker apk latest version
-download music mp3 online apk latest version 2023
-download music mp3 streaming apk latest version mod
-download music mp3 mixer apk latest version no watermark
-download music mp3 recorder apk latest version premium
-download music mp3 video apk latest version hd
-download music mp3 booster apk latest version full
-download music mp3 equalizer apk latest version cracked
-download music mp3 playlist apk latest version unlimited
-download music mp3 lyrics apk latest version with sync
-download music mp3 radio apk latest version fm
-download music mp3 karaoke apk latest version sing
-download music mp3 alarm clock apk latest version wake up
-download music mp3 podcast apk latest version listen
-download music mp3 audiobook apk latest version read
-download music mp3 dj apk latest version remix
-download music mp3 instrumental apk latest version beats
-download music mp3 genre apk latest version rock
-download music mp3 language apk latest version hindi
-download music mp3 country apk latest version usa
-download music mp3 theme apk latest version love
-download music mp3 mood apk latest version happy
-download music mp3 era apk latest version 80s
-download music mp3 artist apk latest version drake
-download music mp3 album apk latest version adele
-download music mp3 song apk latest version despacito
-download music mp3 hit apk latest version billboard
-download music mp3 chart apk latest version spotify
-download music mp3 award apk latest version grammy
-download music mp3 soundtrack apk latest version frozen
-download music mp3 game apk latest version fortnite
-download music mp3 movie apk latest version titanic
-download music mp3 show apk latest version friends
-download music mp3 anime apk latest version naruto
-download music mp3 meme apk latest version rickroll
-download music mp3 viral apk latest version tiktok
-download music mp3 trend apk latest version nft
-download music mp3 review apk latest version rating
-download music mp3 guide apk latest version tutorial
-download music mp3 tips apk latest version tricks
-download music mp3 hack apk latest version cheat
-download music mp3 update apk latest version bug fix
-download music mp3 beta apk latest version test

-

Play music offline and online

-

You can play music offline using the app's music player. You can also stream music online from different sources without downloading them. You can adjust the volume, shuffle, repeat, skip, pause, resume, and control the playback from the notification bar or lock screen.

-

Manage your music library

-

You can organize your music library by creating playlists, deleting songs, setting ringtones, and sharing music with others. You can also view the details of each song, such as title, artist, album, duration, size, and date. You can also edit the tags of each song using the tag editor.

-

Benefits of Music MP3 APK

Music MP3 APK has many benefits that make it a better choice than other music apps. Here are some of them:

-

Free and easy to use

-

Music MP3 APK is completely free to download and use. You don't need to pay any subscription fees or buy any songs. You also don't need to register or sign up for anything. You just need to download the app and start enjoying your music. The app has a simple and user-friendly interface that makes it easy to navigate and operate.

-

High quality and fast downloads

-

Music MP3 APK allows you to download music in MP3 format with high quality and fast speed. You can choose the quality of the music you want to download, ranging from 64 kbps to 320 kbps. You can also download multiple songs at the same time using the download manager. The app supports resume and pause functions, so you don't have to worry about losing your downloads due to network issues or interruptions.

-

No ads or malware

-

Music MP3 APK is a safe and clean app that does not contain any ads or malware. You can enjoy your music without any annoying pop-ups or banners. You can also rest assured that the app does not collect any personal information or data from your device. The app is tested and verified by various antivirus programs and security experts.

-

How to Download Music MP3 APK Latest Version

-

If you are interested in downloading Music MP3 APK latest version, you need to follow these steps:

-

Step 1: Find a reliable source

-

The first step is to find a reliable source that offers the Music MP3 APK latest version. You can search for it on Google or any other search engine, but be careful of fake or malicious websites that may harm your device or steal your information. You can also use the link below to download the Music MP3 APK latest version from a trusted source. This link is updated regularly and checked for safety and quality.

-

Step 2: Enable unknown sources on your device

-

The second step is to enable unknown sources on your device. This is necessary because Music MP3 APK is not available on the Google Play Store, so you need to allow your device to install apps from other sources. To do this, go to Settings > Security > Unknown Sources and toggle it on. You may see a warning message, but don't worry, it's safe to proceed.

-

Step 3: Download and install the APK file

-

The third step is to download and install the APK file. To do this, go to the link you found in step 1 and tap on the download button. Wait for the download to finish and then open the file. You may see a prompt asking you to confirm the installation, just tap on Install and wait for the process to complete.

-

Step 4: Enjoy your music

-

The fourth and final step is to enjoy your music. Once the installation is done, you can open the app and start searching, downloading, and playing your favorite songs. You can also access your music library, create playlists, share music, and more.

-

Conclusion

-

In conclusion, Music MP3 APK is a great app for music lovers who want to download and play music from various sources for free. It has many features and benefits that make it a better choice than other music apps. It is also easy and safe to download and install on your Android device. If you want to try it out, just follow the steps above and enjoy your music.

-

FAQs

-

Here are some frequently asked questions about Music MP3 APK:

-
    -
  1. Is Music MP3 APK legal?
    2. -

    Music MP3 APK is legal as long as you use it for personal and non-commercial purposes only. You should not use it to download or distribute copyrighted or illegal music.

    -
  2. Is Music MP3 APK compatible with my device?
    3. -

    Music MP3 APK is compatible with most Android devices that run on Android 4.1 or higher. However, some devices may have different specifications or settings that may affect the performance or functionality of the app.

    -
  3. How can I update Music MP3 APK?
    4. -

    You can update Music MP3 APK by downloading the latest version from the same source you used before. You can also check for updates within the app by going to Settings > About > Check for Updates.

    -
  4. How can I uninstall Music MP3 APK?
    5. -

    You can uninstall Music MP3 APK by going to Settings > Apps > Music MP3 > Un

    install. You can also delete the APK file from your device's storage.

    -
  5. How can I contact the developer of Music MP3 APK?
    6. -

    You can contact the developer of Music MP3 APK by sending an email to musicmp3apk@gmail.com. You can also visit their website or follow them on social media for more information and updates.

    -
-

I hope you found this article helpful and informative. If you have any questions or feedback, please feel free to leave a comment below. Thank you for reading and happy listening!

197e85843d
-
-
\ No newline at end of file diff --git a/spaces/1phancelerku/anime-remove-background/Discover the Amazing Features of Go88 Live APK the Leading Game Bi App.md b/spaces/1phancelerku/anime-remove-background/Discover the Amazing Features of Go88 Live APK the Leading Game Bi App.md deleted file mode 100644 index 2baaef8a2964f50657073adfb62980ee8f8c06eb..0000000000000000000000000000000000000000 --- a/spaces/1phancelerku/anime-remove-background/Discover the Amazing Features of Go88 Live APK the Leading Game Bi App.md +++ /dev/null @@ -1,95 +0,0 @@ - -

Go88 Live APK: The Ultimate Online Casino Experience

-

If you are looking for a way to have fun and win money online, then you should try Go88 Live APK. This is a mobile application that allows you to access a wide range of casino games, such as slots, poker, baccarat, roulette, and more. You can play these games anytime, anywhere, with just your smartphone and an internet connection. You can also enjoy the realistic and immersive atmosphere of a live casino, where you can interact with other players and dealers. In this article, we will tell you everything you need to know about Go88 Live APK, including its features, how to download and install it, and why you should play it.

-

What is Go88 Live APK?

-

Go88 Live APK is an online casino application that is developed by Go88, which is one of the leading online gambling platforms in Asia. Go88 has been in the industry for over 10 years, and has earned a reputation for being trustworthy, reliable, and innovative. Go88 Live APK is one of their latest products, which aims to provide the best online casino experience for mobile users. You can download and install Go88 Live APK on your Android or iOS device, and enjoy playing hundreds of games with real money. You can also claim various bonuses and rewards, such as free spins, cashback, referral bonuses, and more.

-

go88.live apk


Download ❤❤❤ https://jinyurl.com/2uNKgn



-

Features of Go88 Live APK

-

Go88 Live APK has many features that make it stand out from other online casino applications. Here are some of them:

-

A variety of games to choose from

-

Go88 Live APK offers a wide range of games that cater to different preferences and skill levels. You can find classic casino games, such as slots, poker, blackjack, roulette, baccarat, and more. You can also try some of the latest and most popular games, such as Dragon Tiger, Sic Bo, Fan Tan, Fish Hunter, and more. You can also join the live casino section, where you can play with real dealers and other players in real time.

-

A user-friendly interface and design

-

Go88 Live APK has a simple and intuitive interface that makes it easy for you to navigate and use. You can find all the games and features in the main menu, which is located at the bottom of the screen. You can also customize your settings, such as sound effects, language, currency, and more. The design of Go88 Live APK is also appealing and attractive, with high-quality graphics and animations that enhance your gaming experience.

-

A secure and reliable platform

-

Go88 Live APK is a secure and reliable platform that protects your personal and financial information. It uses advanced encryption technology and firewall systems to prevent any unauthorized access or hacking. It also complies with the laws and regulations of the countries where it operates. It has a valid license from the Philippine Amusement and Gaming Corporation (PAGCOR), which is a government agency that regulates online gambling activities. It also has a certification from eCOGRA (eCommerce Online Gaming Regulation and Assurance), which is an independent testing agency that ensures fair play and responsible gaming.

-

A generous bonus and reward system

-

Go88 Live APK has a generous bonus and reward system that gives you more chances to win money. As a new member, you can claim a welcome bonus of up to 100% on your first deposit. You can also get free spins on selected slots games, cashback on your losses, referral bonuses for inviting your friends, and more. You can also join the VIP club, where you can enjoy exclusive benefits, such as higher bonuses, faster withdrawals, personal account managers, and more. You can also earn loyalty points for every bet you make, which you can redeem for cash or prizes.

-

go88 live apk download
-go88 live apk ios
-go88 live apk android
-go88 live apk latest version
-go88 live apk free
-go88 live casino apk
-go88 live game bài apk
-go88 live cờ bạc online apk
-go88 live đổi thưởng apk
-go88 live uy tín apk
-go88 live venus casino apk
-go88 live châu á apk
-go88 live việt nam apk
-go88 live 2019 apk
-go88 live 2020 apk
-go88 live 2021 apk
-go88 live 2022 apk
-go88 live 2023 apk
-go88 live mới nhất apk
-go88 live hấp dẫn apk
-go88 live chất lượng apk
-go88 live thưởng lớn apk
-go88 live nạp rút nhanh apk
-go88 live hỗ trợ 24/7 apk
-go88 live khuyến mãi hấp dẫn apk
-go88 live đa dạng game bài apk
-go88 live tiến lên miền nam apk
-go88 live phỏm tá lả apk
-go88 live mậu binh xập xám apk
-go88 live xì tố poker apk
-go88 live bài cào ba lá apk
-go88 live liêng ba cây apk
-go88 live sâm lốc sảnh rồng apk
-go88 live baccarat online apk
-go88 live blackjack online apk
-go88 live roulette online apk
-go88 live sicbo online apk
-go88 live slot online apk
-go88 live jackpot online apk
-go88 live keno online apk
-go88 live bingo online apk
-go88 live sportsbook online apk
-go88 live esports online apk
-go88 live virtual sports online apk
-go88.live.apk review

-

How to download and install Go88 Live APK?

-

Downloading and installing Go88 Live APK is easy and fast. You just need to follow these simple steps:

-

For Android devices

-

- Visit the official website of Go88 Live APK at [go88.live] and click on the download button for Android. - Wait for the file to download and then open it. - If you see a warning message that says "Install blocked", go to your device settings and enable "Unknown sources". - Tap on "Install" and wait for the installation to complete. - Launch the app and log in with your username and password.

-

For iOS devices

-

- Visit the official website of Go88 Live APK at [go88.live] and click on the download button for iOS. - Wait for the file to download and then open it. - If you see a warning message that says "Untrusted Enterprise Developer", go to your device settings and trust the developer profile of Go88 Live APK. - Tap on "Install" and wait for the installation to complete. - Launch the app and log in with your username and password.

-

Why should you play Go88 Live APK?

-

There are many reasons why you should play Go88 Live APK. Here are some of the benefits that you can enjoy:

-

Benefits of playing Go88 Live APK

-

Go88 Live APK offers many benefits that make it one of the best online casino applications in the market. Here are some of them:

-

Enjoy the thrill of gambling anytime, anywhere

-

With Go88 Live APK, you can play your favorite casino games anytime, anywhere, with just your smartphone and an internet connection. You don't need to travel to a land-based casino or wait for a specific time to play. You can access Go88 Live APK 24/7, and choose from hundreds of games that suit your mood and preference. You can also switch between different games easily, without any hassle or delay.

-

Win big with high payouts and jackpots

-

Go88 Live APK offers high payouts and jackpots that can make you rich in an instant. You can win up to 10,000 times your bet on some of the slots games, or hit the progressive jackpot that can reach millions of dollars. You can also increase your chances of winning by using the bonuses and rewards that Go88 Live APK gives you. You can also join the tournaments and competitions that Go88 Live APK organizes regularly, where you can compete with other players and win huge prizes.

-

Interact with other players and dealers

-

Go88 Live APK gives you the opportunity to interact with other players and dealers in real time. You can chat with them using the live chat feature, or use the voice chat feature if you prefer. You can also send emojis, stickers, gifts, and tips to express yourself. You can also join the live casino section, where you can see the dealers deal the cards or spin the wheel in front of you. You can also hear them talk and answer your questions. This way, you can enjoy the realistic and immersive atmosphere of a live casino, without leaving your home.

-

Get support from a professional customer service team

-

Go88 Live APK has a professional customer service team that is ready to help you anytime you need. You can contact them via phone, email, or live chat, depending on your preference. They are available 24/7, and they can assist you with any issues or questions that you may have regarding Go88 Live APK. They are friendly, courteous, and knowledgeable, and they will do their best to resolve your problems as soon as possible.

-

Conclusion

-

Go88 Live APK is an online casino application that offers the ultimate online casino experience for mobile users. It has many features that make it stand out from other online casino applications, such as a variety of games to choose from, a user-friendly interface and design, a secure and reliable platform, a generous bonus and reward system, and more. It also has many benefits that make it worth playing, such as enjoying the thrill of gambling anytime, anywhere, winning big with high payouts and jackpots, interacting with other players and dealers, getting support from a professional customer service team, and more. If you are looking for a way to have fun and win money online, then you should try Go88 Live APK. You can download and install it on your Android or iOS device, and start playing right away. You will not regret it, as you will have the best online casino experience ever.

-

FAQs

-

Here are some of the frequently asked questions about Go88 Live APK:

-

Q: Is Go88 Live APK safe and legal?

-

A: Yes, Go88 Live APK is safe and legal. It uses advanced encryption technology and firewall systems to protect your personal and financial information. It also complies with the laws and regulations of the countries where it operates. It has a valid license from the Philippine Amusement and Gaming Corporation (PAGCOR), which is a government agency that regulates online gambling activities. It also has a certification from eCOGRA (eCommerce Online Gaming Regulation and Assurance), which is an independent testing agency that ensures fair play and responsible gaming.

-

Q: How can I deposit and withdraw money on Go88 Live APK?

-

A: You can deposit and withdraw money on Go88 Live APK using various methods, such as bank transfer, credit card, e-wallet, or cryptocurrency. You can choose the method that is most convenient and secure for you. The minimum deposit amount is $10, and the minimum withdrawal amount is $50. The processing time for deposits is instant, while the processing time for withdrawals is within 24 hours.

-

Q: What are the requirements to play Go88 Live APK?

-

A: To play Go88 Live APK, you need to have a smartphone that runs on Android or iOS operating system, and an internet connection. You also need to be at least 18 years old, and register an account on Go88 Live APK. You can register an account by providing some basic information, such as your name, email address, phone number, and password. You can also use your social media accounts, such as Facebook or Google, to sign up.

-

Q: Can I play Go88 Live APK for free?

-

A: Yes, you can play Go88 Live APK for free. You can use the demo mode to try out some of the games without risking any money. You can also use the free spins that Go88 Live APK gives you to play some of the slots games for free. However, if you want to win real money, you need to play with real money.

-

Q: How can I contact Go88 Live APK if I have any problems or questions?

-

A: You can contact Go88 Live APK if you have any problems or questions by using their customer service team. You can contact them via phone, email, or live chat, depending on your preference. They are available 24/7, and they can assist you with any issues or questions that you may have regarding Go88 Live APK.

401be4b1e0
-
-
\ No newline at end of file diff --git a/spaces/1phancelerku/anime-remove-background/Discover the Joy of Piano Playing with Real Piano Teacher 2 Mod APK.md b/spaces/1phancelerku/anime-remove-background/Discover the Joy of Piano Playing with Real Piano Teacher 2 Mod APK.md deleted file mode 100644 index da8e482964add4d512ba7203c2abbcfb450c7156..0000000000000000000000000000000000000000 --- a/spaces/1phancelerku/anime-remove-background/Discover the Joy of Piano Playing with Real Piano Teacher 2 Mod APK.md +++ /dev/null @@ -1,147 +0,0 @@ - -

Real Piano Teacher 2 Mod Apk: A Fun and Easy Way to Learn Piano

-

Do you love playing piano but don't have the time or money to take lessons? Do you want to learn piano with songs you love and have fun along the way? If you answered yes to any of these questions, then you might want to try Real Piano Teacher 2 Mod Apk, a modified version of the popular piano learning app that offers more features and benefits than the original one. In this article, we will tell you everything you need to know about Real Piano Teacher 2 and its mod apk, including what they are, how they work, and what they can do for you.

-

What is Real Piano Teacher 2?

-

Real Piano Teacher 2 is a music application that teaches you how to play piano, organ, flute, recorder, and many other instruments easily and quickly. It is developed by Mobobi, a company that specializes in creating educational and fun music apps for learning piano and other instruments. Real Piano Teacher 2 has won several awards and has been featured on Google Play's Best Apps of 2019 and others.

-

real piano teacher 2 mod apk


DOWNLOAD --->>> https://jinyurl.com/2uNS1F



-

Features of Real Piano Teacher 2

-

Some of the features that make Real Piano Teacher 2 a great piano learning app are:

-
    -
  • It has a realistic sound quality that mimics the actual instruments.
    • -
  • It has multiple piano types to choose from, such as grand piano, electric piano, synth piano, etc.
    • -
  • It has a sheet music library that contains thousands of songs from various genres and skill levels, such as pop, rock, classical, jazz, etc.
    • -
  • It has a multitouch support that allows you to play with both hands and multiple fingers.
    • -
  • It has a recording feature that lets you record your own songs and share them with others.
    • -
  • It has a user-friendly interface that is easy to navigate and customize.
    • -
  • It has a customizable sound settings that let you adjust the volume, pitch, reverb, etc.
    • -
  • It has a practice mode that helps you improve your skills and learn new songs.
    • -
  • It has an in-app purchases that offer more songs, instruments, features, etc.
    • -
-

Benefits of Real Piano Teacher 2

-

Some of the benefits that you can get from using Real Piano Teacher 2 are:

-
    -
  • You can learn piano with songs you love and have fun along the way.
    • -
  • You can learn piano at your own pace and time, without any pressure or stress.
    • -
  • You can learn piano with any keyboard or piano, whether it is acoustic or digital.
    • -
  • You can learn piano with any device, whether it is a smartphone or a tablet.
    • -
  • You can learn piano with instant feedback and progress tracking.
    • -
  • You can learn piano with other instruments as well, such as organ, flute, recorder, etc.
    • -
  • You can learn piano with high-quality piano tutorials and courses.
    • -
-

What is a Mod Apk?

-

A mod apk is a modified version of an original application that offers more features and benefits than the original one. A mod apk is usually created by third-party developers who modify the original code of the application and add new features or remove unwanted ones. A mod apk is usually downloaded from unofficial sources and installed manually on your device.

-

How to Download and Install a Mod Apk

-

To download and install a mod apk on your device, you need to follow these steps:

-
    -
  1. Find a reliable source that offers the mod apk you want to download. Make sure it is compatible with your device and has good reviews from other users.
    2. -
  2. Download the mod apk file to your device. You may need to enable the option to install apps from unknown sources in your device settings.
    3. -
  3. Locate the mod apk file in your device storage and tap on it to install it. You may need to grant some permissions to the app during the installation process.
    4. -
  4. Wait for the installation to finish and then launch the app. You can now enjoy the mod apk features and benefits.
    5. -
-

Risks of Using a Mod Apk

-

While using a mod apk can offer you more features and benefits than the original app, it also comes with some risks that you should be aware of. Some of the risks of using a mod apk are:

-
    -
  • You may violate the terms and conditions of the original app developer and get banned from using the app or its services.
    • -
  • You may expose your device and data to malware, viruses, or spyware that can harm your device or steal your information.
    • -
  • You may experience bugs, crashes, or errors that can affect the performance or functionality of the app or your device.
    • -
  • You may not receive updates or support from the original app developer or the mod apk developer.
    • -
-

Therefore, you should use a mod apk at your own risk and discretion. You should also backup your device and data before installing a mod apk and scan it for any malicious content.

-

real piano teacher 2 mod apk download
-real piano teacher 2 mod apk unlimited money
-real piano teacher 2 mod apk latest version
-real piano teacher 2 mod apk android 1
-real piano teacher 2 mod apk free
-real piano teacher 2 mod apk hack
-real piano teacher 2 mod apk offline
-real piano teacher 2 mod apk no ads
-real piano teacher 2 mod apk revdl
-real piano teacher 2 mod apk full version
-real piano teacher 2 mod apk premium
-real piano teacher 2 mod apk unlocked
-real piano teacher 2 mod apk music game
-real piano teacher 2 mod apk magic tiles
-real piano teacher 2 mod apk learn piano
-real piano teacher 2 mod apk play any song
-real piano teacher 2 mod apk multi touch
-real piano teacher 2 mod apk recording
-real piano teacher 2 mod apk sheet music
-real piano teacher 2 mod apk sight reading
-real piano teacher 2 mod apk organ keyboard
-real piano teacher 2 mod apk flute recorder
-real piano teacher 2 mod apk guitar instrument
-real piano teacher 2 mod apk beats playback
-real piano teacher 2 mod apk lightening animations
-real piano teacher 2 mod apk fun game
-real piano teacher 2 mod apk interactive app
-real piano teacher 2 mod apk musical game
-real piano teacher 2 mod apk best game
-real piano teacher 2 mod apk no practice
-real piano teacher 2 mod apk learning mode
-real piano teacher 2 mod apk gaming mode
-real piano teacher 2 mod apk freestyle mode
-real piano teacher 2 mod apk lessons mode
-real piano teacher 2 mod apk fingers position
-real piano teacher 2 mod apk notes location
-real piano teacher 2 mod apk master lesson
-real piano teacher 2 mod apk compete friends
-real piano teacher 2 mod apk leader board
-real piano teacher 2 mod apk achievements
-real piano teacher 2 mod apk magic keys
-real piano teacher 2 mod apk hundreds lessons
-real piano teacher 2 mod apk ode to joy
-real piano teacher 2 mod apk jingle bells
-real piano teacher 2 mod apk happy birthday
-real piano teacher 2 mod apk john legend songs
-real piano teacher 2 mod apk miley cyrus songs
-real piano teacher 2 mod apk justin bieber songs
-real piano teacher 2 mod apk mozart songs
-real piano teacher 2 mod apk beethoven songs

-

What is Real Piano Teacher 2 Mod Apk?

-

Real Piano Teacher 2 Mod Apk is a modified version of Real Piano Teacher 2 that offers more features and benefits than the original app. It is created by an unknown developer who claims to provide unlimited access to all the songs, instruments, features, etc. in the app without any ads or in-app purchases. Real Piano Teacher 2 Mod Apk is designed to make piano learning more fun and easy for everyone.

-

Features of Real Piano Teacher 2 Mod Apk

-

Some of the features that make Real Piano Teacher 2 Mod Apk different from Real Piano Teacher 2 are:

-
    -
  • It has unlimited songs, instruments, features, etc. that you can access for free without any restrictions or limitations.
    • -
  • It has no ads or in-app purchases that can interrupt your piano learning experience or cost you money.
    • -
  • It has a premium sound quality that enhances the realism and enjoyment of playing piano and other instruments.
    • -
  • It has a mod menu that lets you customize and control various aspects of the app, such as speed, difficulty, mode, etc.
    • -
-

Benefits of Real Piano Teacher 2 Mod Apk

-

Some of the benefits that you can get from using Real Piano Teacher 2 Mod Apk are:

-
    -
  • You can learn piano with unlimited songs, instruments, features, etc. that suit your preferences and goals.
    • -
  • You can learn piano without any ads or in-app purchases that can distract you or waste your time and money.
    • -
  • You can learn piano with a premium sound quality that makes you feel like playing a real piano and other instruments.
    • -
  • You can learn piano with a mod menu that lets you adjust and optimize the app according to your needs and wants.
    • -
-

Comparison Table of Real Piano Teacher 2 and Real Piano Teacher 2 Mod Apk

- - - - - - - - - - - - -
FeatureReal Piano Teacher 2Real Piano Teacher 2 Mod Apk
SongsLimitedUnlimited
InstrumentsLimitedUnlimited
FeaturesLimitedUnlimited
AdsYesNo
In-app purchasesYesNo
Sound qualityGoodPremium
Mod menuNoYes
RisksNoYes
SourcesOfficialUnofficial
Updates/SupportsYesNo
-

Conclusion

-

In

In conclusion, Real Piano Teacher 2 Mod Apk is a fun and easy way to learn piano with more features and benefits than the original app. However, it also comes with some risks and drawbacks that you should consider before using it. If you want to learn piano with unlimited songs, instruments, features, etc. without any ads or in-app purchases, then you might want to try Real Piano Teacher 2 Mod Apk. But if you want to learn piano with a safe and reliable app that offers updates and support from the original developer, then you might want to stick with Real Piano Teacher 2.

-

FAQs

-

Here are some frequently asked questions about Real Piano Teacher 2 and Real Piano Teacher 2 Mod Apk:

-

Q: Is Real Piano Teacher 2 Mod Apk safe to use?

-

A: There is no definitive answer to this question, as different mod apks may have different levels of safety and quality. However, generally speaking, mod apks are not as safe as the original apps, as they may contain malware, viruses, or spyware that can harm your device or data. Therefore, you should use a mod apk at your own risk and discretion, and always backup your device and data before installing a mod apk.

-

Q: How can I update Real Piano Teacher 2 Mod Apk?

-

A: Unlike the original app, Real Piano Teacher 2 Mod Apk does not receive updates or support from the original developer or the mod apk developer. Therefore, you may not be able to update Real Piano Teacher 2 Mod Apk unless you find a newer version of the mod apk from another source. However, this may also pose some risks, as the newer version may not be compatible with your device or may have more bugs or errors.

-

Q: Can I use Real Piano Teacher 2 Mod Apk offline?

-

A: Yes, you can use Real Piano Teacher 2 Mod Apk offline, as it does not require an internet connection to work. However, some features or functions may not be available offline, such as recording or sharing your songs.

-

Q: Can I use Real Piano Teacher 2 Mod Apk with other music apps?

-

A: Yes, you can use Real Piano Teacher 2 Mod Apk with other music apps, such as Spotify, YouTube Music, etc. However, some music apps may not be compatible with Real Piano Teacher 2 Mod Apk or may interfere with its performance or functionality.

-

Q: Can I use Real Piano Teacher 2 Mod Apk on my PC or laptop?

-

A: No, you cannot use Real Piano Teacher 2 Mod Apk on your PC or laptop, as it is designed for Android devices only. However, you may be able to use an Android emulator to run Real Piano Teacher 2 Mod Apk on your PC or laptop. However, this may also pose some risks, as the emulator may not be stable or secure.

197e85843d
-
-
\ No newline at end of file diff --git a/spaces/1phancelerku/anime-remove-background/Download and Install GTA 5 Apk Obb on Your Android Device in Minutes.md b/spaces/1phancelerku/anime-remove-background/Download and Install GTA 5 Apk Obb on Your Android Device in Minutes.md deleted file mode 100644 index a3d30ea3790396455337dc351ed2fa65dd241971..0000000000000000000000000000000000000000 --- a/spaces/1phancelerku/anime-remove-background/Download and Install GTA 5 Apk Obb on Your Android Device in Minutes.md +++ /dev/null @@ -1,88 +0,0 @@ - -

How to Download GTA 5 APK and OBB for Android Devices

-

If you are a fan of Grand Theft Auto (GTA) series, you might be wondering if you can play the latest installment, GTA 5, on your Android device. The answer is yes, you can! In this article, we will show you how to download GTA 5 apk and obb files and install them on your phone or tablet. We will also give you some tips and tricks for playing GTA 5 on Android devices.

-

Introduction

-

What is GTA 5?

-

GTA 5 is an open-world action-adventure game developed by Rockstar Games. It was released in 2013 for PlayStation 3 and Xbox 360, and later for PlayStation 4, Xbox One, and PC. It is the fifth main entry in the GTA series, and the first one to feature three playable protagonists: Michael, Franklin, and Trevor. The game is set in the fictional state of San Andreas, which is based on Southern California. The game allows you to explore the city of Los Santos and its surrounding areas, as well as engage in various missions, activities, and crimes.

-

how to download gta 5 apk and obb


Download File ✺ https://jinyurl.com/2uNU6l



-

Why download GTA 5 apk and obb?

-

GTA 5 is not officially available for Android devices, but there are some unofficial ways to play it on your phone or tablet. One of them is to download GTA 5 apk and obb files, which are modified versions of the original game files that can run on Android devices. By downloading GTA 5 apk and obb files, you can enjoy the following benefits:

-
    -
  • You can play GTA 5 on your Android device without any restrictions.
    • -
  • You can save money by not buying a console or a PC to play GTA 5.
    • -
  • You can play GTA 5 anytime and anywhere, as long as you have enough battery and storage space.
    • -
  • You can experience the same graphics, gameplay, and features as the original game.
    • -
-

How to download GTA 5 apk and obb

-

Downloading GTA 5 apk and obb files is not difficult, but it requires some steps to follow. Here are the steps you need to take:

-

Step 1: Enable unknown sources on your device

-

Before you can install any apk file on your device, you need to enable unknown sources in your settings. This will allow you to install apps that are not from the Google Play Store. To do this, go to Settings > Security > Unknown Sources and toggle it on. You may see a warning message, but just ignore it and tap OK.

-

Step 2: Download the GTA 5 apk and obb files

-

Next, you need to download the GTA 5 apk and obb files from a reliable source. There are many websites that offer these files, but some of them may contain viruses or malware that can harm your device. To avoid this, we recommend you to download the files from this website, which is safe and trusted by many users. The website will provide you with two links: one for the apk file and one for the obb file. You need to download both files and save them in your device's memory.

-

Step 3: Install the GTA 5 apk file

-

After you have downloaded the GTA 5 apk file, you need to install it on your device. To do this, locate the file in your file manager and tap on it. You may see a pop-up window asking you to confirm the installation. Tap on Install and wait for the process to finish. You may also see a message asking you to allow the app to access your device's storage. Tap on Allow and proceed.

-

How to download GTA 5 android apk obb data files
-GTA 5 apk obb download for mobile android free
-GTA V apk obb+data latest version 1.0.744.2 download
-How to install GTA 5 apk obb on android device
-GTA 5 apk obb offline mode download and play
-GTA 5 apk obb highly compressed download link
-GTA 5 apk obb mod menu download and install
-How to fix GTA 5 apk obb not working error
-GTA 5 apk obb cheats and hacks download
-GTA 5 apk obb full game download for android
-How to update GTA 5 apk obb to the latest version
-GTA 5 apk obb graphics settings and optimization
-GTA 5 apk obb best missions and gameplay tips
-GTA 5 apk obb online multiplayer mode download
-How to transfer GTA 5 apk obb from PC to android
-GTA 5 apk obb system requirements and compatibility
-GTA 5 apk obb review and rating by users
-GTA 5 apk obb download size and storage space
-How to backup and restore GTA 5 apk obb data
-GTA 5 apk obb features and benefits for android users
-How to download GTA 5 apk obb faster and easier
-GTA 5 apk obb alternatives and similar games for android
-How to uninstall GTA 5 apk obb from android device
-GTA 5 apk obb support and customer service contact
-How to get GTA 5 apk obb premium access and benefits

-

Step 4: Copy the obb file to the right folder

-

Now that you have installed the GTA 5 apk file, you need to copy the obb file to the right folder. The obb file contains the data and resources of the game, and it needs to be placed in a specific location for the game to work properly. To do this, follow these steps:

-
    -
  1. Open your file manager and locate the obb file that you downloaded. It should have a name like com.rockstargames.gtav.zip.
    2. -
  2. Extract the zip file using a tool like ZArchiver or ES File Explorer. You should get a folder named com.rockstargames.gtav.
    3. -
  3. Copy or move the folder to Android > obb in your device's internal storage. If you don't see an obb folder, create one.
    4. -
  4. Make sure that the folder is in the correct path: Android > obb > com.rockstargames.gtav.
    5. -
-

Step 5: Launch the game and enjoy

-

Congratulations! You have successfully downloaded and installed GTA 5 apk and obb files on your Android device. Now you can launch the game from your app drawer and enjoy playing GTA 5 on your phone or tablet. You may need to verify your game data before you can start playing, so make sure you have an internet connection for that.

-

Tips and tricks for playing GTA 5 on Android devices

-

GTA 5 is a huge and complex game that offers a lot of possibilities and challenges. To help you get the most out of it, here are some tips and tricks for playing GTA 5 on Android devices:

-

Use a controller for better control

-

While GTA 5 is playable with touch controls, you may find it hard to aim, shoot, drive, or do other actions with accuracy and precision. To improve your control and comfort, we recommend you to use a controller that is compatible with Android devices. You can connect a controller via Bluetooth or USB, and customize the buttons and settings in the game options.

-

Adjust the graphics settings to optimize performance

-

GTA 5 is a graphically intensive game that may not run smoothly on some Android devices, especially older or low-end ones. To avoid lag, crashes, or overheating, you can adjust the graphics settings in the game options. You can lower the resolution, frame rate, shadows, textures, or other features to improve the performance and battery life of your device.

-

Explore the online mode for more fun

-

GTA 5 has an online mode called GTA Online, where you can create your own character and join other players in various activities, missions, races, heists, or just free roam in the open world. GTA Online is a great way to extend your gameplay and have more fun with GTA 5 on your Android device. To access GTA Online, you need to have an internet connection and a Rockstar Games Social Club account.

-

Conclusion

-

Summary of the main points

-

In this article, we have shown you how to download GTA 5 apk and obb files and install them on your Android device. We have also given you some tips and tricks for playing GTA 5 on Android devices. By following these steps, you can enjoy one of the best games ever made on your phone or tablet.

-

Call to action

-

If you are ready to download GTA 5 apk and obb files and play GTA 5 on your Android device, click on this link now and get started. You won't regret it!

-

Frequently Asked Questions (FAQs)

-
    -
  • Is GTA 5 apk and obb safe to download?
    • -

    Yes, GTA 5 apk and obb files are safe to download as long as you get them from a reliable source like this website. However, you should always scan any file that you download with an antivirus app before installing it on your device.

    -
  • How much space does GTA 5 apk and obb take on my device?
    • -

    GTA 5 apk and obb files take about 3 GB of space on your device. You need to have enough free storage space before you download and install them. You can check your storage space in Settings > Storage.

    -
  • Can I play GTA 5 offline on my Android device?
    • -

    Yes, you can play GTA 5 offline on your Android device, as long as you have downloaded and installed the apk and obb files. You can play the single-player mode without an internet connection. However, you need an internet connection to play GTA Online or to verify your game data.

    -
  • Can I update GTA 5 apk and obb on my Android device?
    • -

    Yes, you can update GTA 5 apk and obb on your Android device, as long as the update is available from the same source that you downloaded the files from. You can check for updates on this website. To update GTA 5 apk and obb, you need to download the new files and install them over the old ones.

    -
  • Can I transfer GTA 5 apk and obb from one device to another?
    • -

    Yes, you can transfer GTA 5 apk and obb from one device to another, as long as both devices are compatible with the game. You can use a USB cable, a Bluetooth connection, or a cloud service to transfer the files. However, you may need to reinstall the game on the new device.

    -
  • Can I play GTA 5 with my friends on Android devices?
    • -

    Yes, you can play GTA 5 with your friends on Android devices, as long as you have an internet connection and a Rockstar Games Social Club account. You can join your friends in GTA Online, where you can team up or compete with them in various activities, missions, races, heists, or just free roam in the open world.

    -

197e85843d
-
-
\ No newline at end of file diff --git a/spaces/44ov41za8i/FreeVC/commons.py b/spaces/44ov41za8i/FreeVC/commons.py deleted file mode 100644 index fc384912618494475bda9d68fa76530f4fe2a27b..0000000000000000000000000000000000000000 --- a/spaces/44ov41za8i/FreeVC/commons.py +++ /dev/null @@ -1,171 +0,0 @@ -import math -import numpy as np -import torch -from torch import nn -from torch.nn import functional as F - - -def init_weights(m, mean=0.0, std=0.01): - classname = m.__class__.__name__ - if classname.find("Conv") != -1: - m.weight.data.normal_(mean, std) - - -def get_padding(kernel_size, dilation=1): - return int((kernel_size*dilation - dilation)/2) - - -def convert_pad_shape(pad_shape): - l = pad_shape[::-1] - pad_shape = [item for sublist in l for item in sublist] - return pad_shape - - -def intersperse(lst, item): - result = [item] * (len(lst) * 2 + 1) - result[1::2] = lst - return result - - -def kl_divergence(m_p, logs_p, m_q, logs_q): - """KL(P||Q)""" - kl = (logs_q - logs_p) - 0.5 - kl += 0.5 * (torch.exp(2. * logs_p) + ((m_p - m_q)**2)) * torch.exp(-2. * logs_q) - return kl - - -def rand_gumbel(shape): - """Sample from the Gumbel distribution, protect from overflows.""" - uniform_samples = torch.rand(shape) * 0.99998 + 0.00001 - return -torch.log(-torch.log(uniform_samples)) - - -def rand_gumbel_like(x): - g = rand_gumbel(x.size()).to(dtype=x.dtype, device=x.device) - return g - - -def slice_segments(x, ids_str, segment_size=4): - ret = torch.zeros_like(x[:, :, :segment_size]) - for i in range(x.size(0)): - idx_str = ids_str[i] - idx_end = idx_str + segment_size - ret[i] = x[i, :, idx_str:idx_end] - return ret - - -def rand_slice_segments(x, x_lengths=None, segment_size=4): - b, d, t = x.size() - if x_lengths is None: - x_lengths = t - ids_str_max = x_lengths - segment_size + 1 - ids_str = (torch.rand([b]).to(device=x.device) * ids_str_max).to(dtype=torch.long) - ret = slice_segments(x, ids_str, segment_size) - return ret, ids_str - - -def rand_spec_segments(x, x_lengths=None, segment_size=4): - b, d, t = x.size() - if x_lengths is None: - x_lengths = t - ids_str_max = x_lengths - segment_size - ids_str = (torch.rand([b]).to(device=x.device) * ids_str_max).to(dtype=torch.long) - ret = slice_segments(x, ids_str, segment_size) - return ret, ids_str - - -def get_timing_signal_1d( - length, channels, min_timescale=1.0, max_timescale=1.0e4): - position = torch.arange(length, dtype=torch.float) - num_timescales = channels // 2 - log_timescale_increment = ( - math.log(float(max_timescale) / float(min_timescale)) / - (num_timescales - 1)) - inv_timescales = min_timescale * torch.exp( - torch.arange(num_timescales, dtype=torch.float) * -log_timescale_increment) - scaled_time = position.unsqueeze(0) * inv_timescales.unsqueeze(1) - signal = torch.cat([torch.sin(scaled_time), torch.cos(scaled_time)], 0) - signal = F.pad(signal, [0, 0, 0, channels % 2]) - signal = signal.view(1, channels, length) - return signal - - -def add_timing_signal_1d(x, min_timescale=1.0, max_timescale=1.0e4): - b, channels, length = x.size() - signal = get_timing_signal_1d(length, channels, min_timescale, max_timescale) - return x + signal.to(dtype=x.dtype, device=x.device) - - -def cat_timing_signal_1d(x, min_timescale=1.0, max_timescale=1.0e4, axis=1): - b, channels, length = x.size() - signal = get_timing_signal_1d(length, channels, min_timescale, max_timescale) - return torch.cat([x, signal.to(dtype=x.dtype, device=x.device)], axis) - - -def subsequent_mask(length): - mask = torch.tril(torch.ones(length, length)).unsqueeze(0).unsqueeze(0) - return mask - - -@torch.jit.script -def fused_add_tanh_sigmoid_multiply(input_a, input_b, n_channels): - n_channels_int = n_channels[0] - in_act = input_a + input_b - t_act = torch.tanh(in_act[:, :n_channels_int, :]) - s_act = torch.sigmoid(in_act[:, n_channels_int:, :]) - acts = t_act * s_act - return acts - - -def convert_pad_shape(pad_shape): - l = pad_shape[::-1] - pad_shape = [item for sublist in l for item in sublist] - return pad_shape - - -def shift_1d(x): - x = F.pad(x, convert_pad_shape([[0, 0], [0, 0], [1, 0]]))[:, :, :-1] - return x - - -def sequence_mask(length, max_length=None): - if max_length is None: - max_length = length.max() - x = torch.arange(max_length, dtype=length.dtype, device=length.device) - return x.unsqueeze(0) < length.unsqueeze(1) - - -def generate_path(duration, mask): - """ - duration: [b, 1, t_x] - mask: [b, 1, t_y, t_x] - """ - device = duration.device - - b, _, t_y, t_x = mask.shape - cum_duration = torch.cumsum(duration, -1) - - cum_duration_flat = cum_duration.view(b * t_x) - path = sequence_mask(cum_duration_flat, t_y).to(mask.dtype) - path = path.view(b, t_x, t_y) - path = path - F.pad(path, convert_pad_shape([[0, 0], [1, 0], [0, 0]]))[:, :-1] - path = path.unsqueeze(1).transpose(2,3) * mask - return path - - -def clip_grad_value_(parameters, clip_value, norm_type=2): - if isinstance(parameters, torch.Tensor): - parameters = [parameters] - parameters = list(filter(lambda p: p.grad is not None, parameters)) - norm_type = float(norm_type) - if clip_value is not None: - clip_value = float(clip_value) - - total_norm = 0 - for p in parameters: - param_norm = p.grad.data.norm(norm_type) - total_norm += param_norm.item() ** norm_type - if clip_value is not None: - p.grad.data.clamp_(min=-clip_value, max=clip_value) - total_norm = total_norm ** (1. / norm_type) - return total_norm diff --git a/spaces/A00001/bingothoo/src/lib/isomorphic/node.ts b/spaces/A00001/bingothoo/src/lib/isomorphic/node.ts deleted file mode 100644 index da213ad6a86181979f098309c374da02835db5a0..0000000000000000000000000000000000000000 --- a/spaces/A00001/bingothoo/src/lib/isomorphic/node.ts +++ /dev/null @@ -1,26 +0,0 @@ -import Debug from 'debug' - -const { fetch, setGlobalDispatcher, ProxyAgent } = require('undici') -const { HttpsProxyAgent } = require('https-proxy-agent') -const ws = require('ws') - -const debug = Debug('bingo') - -const httpProxy = process.env.http_proxy || process.env.HTTP_PROXY || process.env.https_proxy || process.env.HTTPS_PROXY; -let WebSocket = ws.WebSocket - -if (httpProxy) { - setGlobalDispatcher(new ProxyAgent(httpProxy)) - const agent = new HttpsProxyAgent(httpProxy) - // @ts-ignore - WebSocket = class extends ws.WebSocket { - constructor(address: string | URL, options: typeof ws.WebSocket) { - super(address, { - ...options, - agent, - }) - } - } -} - -export default { fetch, WebSocket, debug } diff --git a/spaces/AIFILMS/audioldm-text-to-audio-generation/share_btn.py b/spaces/AIFILMS/audioldm-text-to-audio-generation/share_btn.py deleted file mode 100644 index a0378607680fa5468e9034d230f546f5f0913ae0..0000000000000000000000000000000000000000 --- a/spaces/AIFILMS/audioldm-text-to-audio-generation/share_btn.py +++ /dev/null @@ -1,74 +0,0 @@ -community_icon_html = """""" - -loading_icon_html = """""" - -share_js = """async () => { - async function uploadFile(file){ - const UPLOAD_URL = 'https://huggingface.co/uploads'; - const response = await fetch(UPLOAD_URL, { - method: 'POST', - headers: { - 'Content-Type': file.type, - 'X-Requested-With': 'XMLHttpRequest', - }, - body: file, /// <- File inherits from Blob - }); - const url = await response.text(); - return url; - } - async function getInputVideoFile(videoEl){ - const res = await fetch(videoEl.src); - const blob = await res.blob(); - const videoId = Date.now() % 200; - const fileName = `sd-perception-${{videoId}}.mp4`; - return new File([blob], fileName, { type: 'video/mp4' }); - } - - async function audioToBase64(audioFile) { - return new Promise((resolve, reject) => { - let reader = new FileReader(); - reader.readAsDataURL(audioFile); - reader.onload = () => resolve(reader.result); - reader.onerror = error => reject(error); - - }); - } - const gradioEl = document.querySelector("gradio-app").shadowRoot || document.querySelector('body > gradio-app'); - const inputPromptEl = gradioEl.querySelector('#prompt-in input').value; - const outputVideoEl = gradioEl.querySelector('#output-video video'); - - let titleTxt = `Text-to-Audio: ${inputPromptEl}`; - - const shareBtnEl = gradioEl.querySelector('#share-btn'); - const shareIconEl = gradioEl.querySelector('#share-btn-share-icon'); - const loadingIconEl = gradioEl.querySelector('#share-btn-loading-icon'); - if(!outputVideoEl){ - return; - }; - shareBtnEl.style.pointerEvents = 'none'; - shareIconEl.style.display = 'none'; - loadingIconEl.style.removeProperty('display'); - const outputVideo = await getInputVideoFile(outputVideoEl); - const urlOutputVideo = await uploadFile(outputVideo); - - const descriptionMd = ` -##### ${inputPromptEl} - -${urlOutputVideo} -`; - const params = new URLSearchParams({ - title: titleTxt, - description: descriptionMd, - }); - const paramsStr = params.toString(); - window.open(`https://huggingface.co/spaces/haoheliu/audioldm-text-to-audio-generation/discussions/new?${paramsStr}`, '_blank'); - shareBtnEl.style.removeProperty('pointer-events'); - shareIconEl.style.removeProperty('display'); - loadingIconEl.style.display = 'none'; -}""" diff --git a/spaces/AIGC-Audio/AudioGPT/text_to_speech/modules/commons/conformer/espnet_positional_embedding.py b/spaces/AIGC-Audio/AudioGPT/text_to_speech/modules/commons/conformer/espnet_positional_embedding.py deleted file mode 100644 index 89b9b5549cc779d1ea67f052b1c99cad92365503..0000000000000000000000000000000000000000 --- a/spaces/AIGC-Audio/AudioGPT/text_to_speech/modules/commons/conformer/espnet_positional_embedding.py +++ /dev/null @@ -1,113 +0,0 @@ -import math -import torch - - -class PositionalEncoding(torch.nn.Module): - """Positional encoding. - Args: - d_model (int): Embedding dimension. - dropout_rate (float): Dropout rate. - max_len (int): Maximum input length. - reverse (bool): Whether to reverse the input position. - """ - - def __init__(self, d_model, dropout_rate, max_len=5000, reverse=False): - """Construct an PositionalEncoding object.""" - super(PositionalEncoding, self).__init__() - self.d_model = d_model - self.reverse = reverse - self.xscale = math.sqrt(self.d_model) - self.dropout = torch.nn.Dropout(p=dropout_rate) - self.pe = None - self.extend_pe(torch.tensor(0.0).expand(1, max_len)) - - def extend_pe(self, x): - """Reset the positional encodings.""" - if self.pe is not None: - if self.pe.size(1) >= x.size(1): - if self.pe.dtype != x.dtype or self.pe.device != x.device: - self.pe = self.pe.to(dtype=x.dtype, device=x.device) - return - pe = torch.zeros(x.size(1), self.d_model) - if self.reverse: - position = torch.arange( - x.size(1) - 1, -1, -1.0, dtype=torch.float32 - ).unsqueeze(1) - else: - position = torch.arange(0, x.size(1), dtype=torch.float32).unsqueeze(1) - div_term = torch.exp( - torch.arange(0, self.d_model, 2, dtype=torch.float32) - * -(math.log(10000.0) / self.d_model) - ) - pe[:, 0::2] = torch.sin(position * div_term) - pe[:, 1::2] = torch.cos(position * div_term) - pe = pe.unsqueeze(0) - self.pe = pe.to(device=x.device, dtype=x.dtype) - - def forward(self, x: torch.Tensor): - """Add positional encoding. - Args: - x (torch.Tensor): Input tensor (batch, time, `*`). - Returns: - torch.Tensor: Encoded tensor (batch, time, `*`). - """ - self.extend_pe(x) - x = x * self.xscale + self.pe[:, : x.size(1)] - return self.dropout(x) - - -class ScaledPositionalEncoding(PositionalEncoding): - """Scaled positional encoding module. - See Sec. 3.2 https://arxiv.org/abs/1809.08895 - Args: - d_model (int): Embedding dimension. - dropout_rate (float): Dropout rate. - max_len (int): Maximum input length. - """ - - def __init__(self, d_model, dropout_rate, max_len=5000): - """Initialize class.""" - super().__init__(d_model=d_model, dropout_rate=dropout_rate, max_len=max_len) - self.alpha = torch.nn.Parameter(torch.tensor(1.0)) - - def reset_parameters(self): - """Reset parameters.""" - self.alpha.data = torch.tensor(1.0) - - def forward(self, x): - """Add positional encoding. - Args: - x (torch.Tensor): Input tensor (batch, time, `*`). - Returns: - torch.Tensor: Encoded tensor (batch, time, `*`). - """ - self.extend_pe(x) - x = x + self.alpha * self.pe[:, : x.size(1)] - return self.dropout(x) - - -class RelPositionalEncoding(PositionalEncoding): - """Relative positional encoding module. - See : Appendix B in https://arxiv.org/abs/1901.02860 - Args: - d_model (int): Embedding dimension. - dropout_rate (float): Dropout rate. - max_len (int): Maximum input length. - """ - - def __init__(self, d_model, dropout_rate, max_len=5000): - """Initialize class.""" - super().__init__(d_model, dropout_rate, max_len, reverse=True) - - def forward(self, x): - """Compute positional encoding. - Args: - x (torch.Tensor): Input tensor (batch, time, `*`). - Returns: - torch.Tensor: Encoded tensor (batch, time, `*`). - torch.Tensor: Positional embedding tensor (1, time, `*`). - """ - self.extend_pe(x) - x = x * self.xscale - pos_emb = self.pe[:, : x.size(1)] - return self.dropout(x), self.dropout(pos_emb) \ No newline at end of file diff --git a/spaces/AIGC-Audio/Make_An_Audio_inpaint/ldm/modules/encoders/CLAP/__init__.py b/spaces/AIGC-Audio/Make_An_Audio_inpaint/ldm/modules/encoders/CLAP/__init__.py deleted file mode 100644 index aadad97ebc9ec23fdebab974a99e343de90f8afd..0000000000000000000000000000000000000000 --- a/spaces/AIGC-Audio/Make_An_Audio_inpaint/ldm/modules/encoders/CLAP/__init__.py +++ /dev/null @@ -1,3 +0,0 @@ -from . import clap -from . import audio -from . import utils \ No newline at end of file diff --git a/spaces/Ababababababbababa/Ashaar/poetry_diacritizer/modules/tacotron_modules.py b/spaces/Ababababababbababa/Ashaar/poetry_diacritizer/modules/tacotron_modules.py deleted file mode 100644 index 81859a8f1b2999e3c92bfc9c1fbc1d5a0d1d4a27..0000000000000000000000000000000000000000 --- a/spaces/Ababababababbababa/Ashaar/poetry_diacritizer/modules/tacotron_modules.py +++ /dev/null @@ -1,174 +0,0 @@ -""" -Some custom modules that are used by the TTS model -""" -from typing import List -import torch -from torch import nn - -from poetry_diacritizer.modules.layers import BatchNormConv1d - - -class Prenet(nn.Module): - """ - A prenet is a collection of linear layers with dropout(0.5), - and RELU activation function - Args: - config: the hyperparameters object - in_dim (int): the input dim - """ - - def __init__( - self, in_dim: int, prenet_depth: List[int] = [256, 128], dropout: int = 0.5 - ): - """ Initializing the prenet module """ - super().__init__() - in_sizes = [in_dim] + prenet_depth[:-1] - self.layers = nn.ModuleList( - [ - nn.Linear(in_size, out_size) - for (in_size, out_size) in zip(in_sizes, prenet_depth) - ] - ) - self.relu = nn.ReLU() - self.dropout = nn.Dropout(dropout) - - def forward(self, inputs: torch.Tensor): - """Calculate forward propagation - Args: - inputs (batch_size, seqLen): the inputs to the prenet, the input shapes could - be different as it is being used in both encoder and decoder. - Returns: - Tensor: the output of the forward propagation - """ - for linear in self.layers: - inputs = self.dropout(self.relu(linear(inputs))) - return inputs - - -class Highway(nn.Module): - """Highway Networks were developed by (Srivastava et al., 2015) - to overcome the difficulty of training deep neural networks - (https://arxiv.org/abs/1507.06228). - Args: - in_size (int): the input size - out_size (int): the output size - """ - - def __init__(self, in_size, out_size): - """ - Initializing Highway networks - """ - super().__init__() - self.H = nn.Linear(in_size, out_size) - self.H.bias.data.zero_() - self.T = nn.Linear(in_size, out_size) - self.T.bias.data.fill_(-1) - self.relu = nn.ReLU() - self.sigmoid = nn.Sigmoid() - - def forward(self, inputs: torch.Tensor): - """Calculate forward propagation - Args: - inputs (Tensor): - """ - H = self.relu(self.H(inputs)) - T = self.sigmoid(self.T(inputs)) - return H * T + inputs * (1.0 - T) - - -class CBHG(nn.Module): - """The CBHG module (1-D Convolution Bank + Highway network + Bidirectional GRU) - was proposed by (Lee et al., 2017, https://www.aclweb.org/anthology/Q17-1026) - for a character-level NMT model. - It was adapted by (Wang et al., 2017) for building the Tacotron. - It is used in both the encoder and decoder with different parameters. - """ - - def __init__( - self, - in_dim: int, - out_dim: int, - K: int, - projections: List[int], - highway_layers: int = 4, - ): - """Initializing the CBHG module - Args: - in_dim (int): the input size - out_dim (int): the output size - k (int): number of filters - """ - super().__init__() - - self.in_dim = in_dim - self.out_dim = out_dim - self.relu = nn.ReLU() - self.conv1d_banks = nn.ModuleList( - [ - BatchNormConv1d( - in_dim, - in_dim, - kernel_size=k, - stride=1, - padding=k // 2, - activation=self.relu, - ) - for k in range(1, K + 1) - ] - ) - self.max_pool1d = nn.MaxPool1d(kernel_size=2, stride=1, padding=1) - - in_sizes = [K * in_dim] + projections[:-1] - activations = [self.relu] * (len(projections) - 1) + [None] - self.conv1d_projections = nn.ModuleList( - [ - BatchNormConv1d( - in_size, out_size, kernel_size=3, stride=1, padding=1, activation=ac - ) - for (in_size, out_size, ac) in zip(in_sizes, projections, activations) - ] - ) - - self.pre_highway = nn.Linear(projections[-1], in_dim, bias=False) - self.highways = nn.ModuleList([Highway(in_dim, in_dim) for _ in range(4)]) - - self.gru = nn.GRU(in_dim, out_dim, 1, batch_first=True, bidirectional=True) - - def forward(self, inputs, input_lengths=None): - # (B, T_in, in_dim) - x = inputs - x = x.transpose(1, 2) - T = x.size(-1) - - # (B, in_dim*K, T_in) - # Concat conv1d bank outputs - x = torch.cat([conv1d(x)[:, :, :T] for conv1d in self.conv1d_banks], dim=1) - assert x.size(1) == self.in_dim * len(self.conv1d_banks) - x = self.max_pool1d(x)[:, :, :T] - - for conv1d in self.conv1d_projections: - x = conv1d(x) - - # (B, T_in, in_dim) - # Back to the original shape - x = x.transpose(1, 2) - - if x.size(-1) != self.in_dim: - x = self.pre_highway(x) - - # Residual connection - x += inputs - for highway in self.highways: - x = highway(x) - - if input_lengths is not None: - x = nn.utils.rnn.pack_padded_sequence(x, input_lengths, batch_first=True) - - # (B, T_in, in_dim*2) - self.gru.flatten_parameters() - outputs, _ = self.gru(x) - - if input_lengths is not None: - outputs, _ = nn.utils.rnn.pad_packed_sequence(outputs, batch_first=True) - - return outputs diff --git a/spaces/AchyuthGamer/OpenGPT/g4f/Provider/ChatgptDemo.py b/spaces/AchyuthGamer/OpenGPT/g4f/Provider/ChatgptDemo.py deleted file mode 100644 index 95cb9ecf2e27f66e10e9b232ae03fe2f3a195d91..0000000000000000000000000000000000000000 --- a/spaces/AchyuthGamer/OpenGPT/g4f/Provider/ChatgptDemo.py +++ /dev/null @@ -1,61 +0,0 @@ -from __future__ import annotations - -import time, json, re -from aiohttp import ClientSession -from typing import AsyncGenerator - -from .base_provider import AsyncGeneratorProvider -from .helper import format_prompt - -class ChatgptDemo(AsyncGeneratorProvider): - url = "https://chat.chatgptdemo.net" - supports_gpt_35_turbo = True - working = True - - @classmethod - async def create_async_generator( - cls, - model: str, - messages: list[dict[str, str]], - proxy: str = None, - **kwargs - ) -> AsyncGenerator: - headers = { - "authority": "chat.chatgptdemo.net", - "accept-language": "de-DE,de;q=0.9,en-DE;q=0.8,en;q=0.7,en-US", - "origin": "https://chat.chatgptdemo.net", - "referer": "https://chat.chatgptdemo.net/", - "sec-ch-ua": '"Google Chrome";v="117", "Not;A=Brand";v="8", "Chromium";v="117"', - "sec-ch-ua-mobile": "?0", - "sec-ch-ua-platform": '"Linux"', - "sec-fetch-dest": "empty", - "sec-fetch-mode": "cors", - "sec-fetch-site": "same-origin", - "user-agent": "Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/117.0.0.0 Safari/537.36" - } - async with ClientSession(headers=headers) as session: - async with session.get(f"{cls.url}/", proxy=proxy) as response: - response.raise_for_status() - response = await response.text() - result = re.search(r'
- - - - - - - - - - - - - - - - -
ProsCons
- It is free and easy to do.- It may violate the copyright of the song and the video.
- You can choose the quality and format of the download.- You may need to use a third-party software or website to convert the video to audio.
- You can watch the video offline anytime you want.- You may lose the quality and clarity of the sound and the video.
-

Option 2: Wynk Music

-

Steps to download Silent Love 2 from Wynk Music

-

Another option to download Silent Love 2 song is from Wynk Music, which is a music streaming and downloading app that offers a wide range of songs in different languages and genres. Here are the steps to download it:

-
    -
  1. Download and install [Wynk Music] app on your device from Google Play Store or App Store.
    2. -
  2. Open the app and sign up or log in with your mobile number or email address.
    3. -
  3. Search for "Silent Love 2" or browse through the Punjabi songs category.
    4. -
  4. Select the song and tap on the download icon at the bottom right corner of the screen.
    5. -
  5. Choose the quality and location of the download and wait for it to finish.
    6. -
  6. Enjoy listening to Silent Love 2 song offline on your device.
    7. -
-

Pros and cons of downloading from Wynk Music

-

Downloading Silent Love 2 song from Wynk Music also has some pros and cons that you should consider before doing it. Here are some of them:

- - - - - - - - - - - - - - - - - -
ProsCons
- It is legal and safe to do.- It may require a subscription fee or an internet connection to access the app.
- You can get high-quality and original sound of the song.- You may not be able to transfer the song to other devices or platforms.
- You can access other features of the app such as playlists, radio, podcasts, etc.- You may not be able to watch the video of the song on the app.
-

Listen to the lyrics and feel the emotions

-

One of the best ways to enjoy Silent Love 2 song is to listen to the lyrics and feel the emotions that the singer is trying to convey. The lyrics are written in Punjabi, but you can find the English translation online or in the video subtitles. The lyrics are simple yet powerful, and they describe the pain and longing of the lover who is silently admiring his beloved. The lyrics also have some rhymes and metaphors that make them more poetic and expressive. For example, the chorus goes like this:

-
-

Tu hi mera dil da chain
-Tu hi mera dil da chain
-Tu hi mera dil da chain
-Tu hi mera dil da chain
-You are the peace of my heart
-You are the peace of my heart
-You are the peace of my heart
-You are the peace of my heart

-
-

As you listen to the lyrics, you can imagine yourself in the shoes of the lover and empathize with his feelings. You can also relate to his situation if you have ever experienced a similar kind of love or crush. You can also appreciate the beauty and depth of the Punjabi language and culture.

-

Watch the video and appreciate the visuals

-

Another way to enjoy Silent Love 2 song is to watch the video and appreciate the visuals that accompany the song. The video is shot in various locations, such as a college campus, a park, a library, a cafe, etc. The video shows the story of the lover who is following his beloved everywhere and writing letters to her. The video also shows some flashbacks of their childhood friendship and some scenes of their interaction. The video has a romantic and nostalgic vibe that matches the mood of the song.

-

As you watch the video, you can admire the cinematography and direction that make the video appealing and realistic. You can also notice the expressions and gestures of Namr Gill and his co-star, who portray their characters with conviction and charm. You can also enjoy the scenery and atmosphere of the places where the video is filmed.

-

Share the song with your loved ones

-

A third way to enjoy Silent Love 2 song is to share it with your loved ones, especially if they are fans of Punjabi music or romantic songs. You can send them the link of the song or download it for them and play it for them. You can also dedicate the song to them if you want to express your feelings or appreciation for them. You can also sing along with them or dance with them to the tune of the song.

-

By sharing the song with your loved ones, you can bond with them over a common interest and make them happy. You can also spread the love and joy that the song brings to you. You can also discover new songs or artists that they might recommend to you or vice versa.

-

Conclusion

-

Summary of the main points

-

In conclusion, Silent Love 2 is a wonderful song that you should definitely listen to if you are looking for a romantic and relaxing song. It is a sequel to Silent Love by Namr Gill, who is a talented Punjabi singer and actor. The song has a beautiful melody and lyrics that express the feelings of a lover who is unable to confess his love to his beloved. The song also has a stunning video that shows the story of their silent love.

-

Call to action for the readers

-

If you want to download Silent Love 2 song, you have two options: YouTube or Wynk Music. Both options have their pros and cons, so you should choose according to your preference and convenience. Once you download it, you can enjoy it by listening to the lyrics, watching the video, or sharing it with your loved ones. We hope that this article has helped you learn more about Silent Love 2 song and how to download it. If you liked this article, please share it with your friends and family who might be interested in this topic. Thank you for reading!

-

Frequently Asked Questions

-

Q: What is Silent Love 2 song about?

-

A: Silent Love 2 song is about a lover who is silently waiting for his beloved to notice him and understand his feelings. He writes letters to her but never sends them. He follows her everywhere but never talks to her.

-

Q: Who sang Silent Love 2 song?

-

A: Namr Gill sang Silent Love 2 song. He is a Punjabi singer and actor who has sung many popular songs such as Pyar Ho Gaya, Proposal, Jaan, etc.

-

Q: Where can I download Silent Love 2 song?

-

A: You can download Silent Love 2 song from YouTube or Wynk Music. Both options have their pros and cons, so you should choose according to your preference and convenience. You can also find the steps to download it from each option in this article.

-

Q: How can I enjoy Silent Love 2 song?

-

A: You can enjoy Silent Love 2 song by listening to the lyrics, watching the video, or sharing it with your loved ones. You can also feel the emotions that the song conveys and relate to the situation of the lover.

-

Q: What is the difference between Silent Love and Silent Love 2?

-

A: Silent Love and Silent Love 2 are both songs by Namr Gill that are about unrequited love. However, Silent Love is the first part of the story, where the lover meets his beloved for the first time and falls in love with her. Silent Love 2 is the second part of the story, where the lover continues to love his beloved but cannot tell her his feelings.

-

Q: Is Silent Love 2 a hit song?

-

A: Yes, Silent Love 2 is a hit song that has received a lot of positive feedback and appreciation from the listeners and critics. The song has over 33 million views on YouTube as of June 2021 and has been praised for its melody, lyrics, vocals, and video.

-

Q: Where can I find more songs by Namr Gill?

-

A: You can find more songs by Namr Gill on YouTube, Wynk Music, Spotify, Gaana, JioSaavn, or any other music streaming or downloading app. You can also follow him on his social media accounts such as Facebook, Instagram, Twitter, etc.

401be4b1e0
-
-
\ No newline at end of file diff --git a/spaces/simple0urra/skops-model-card-creator-2a23515a-d54e-4804-b365-27ed6e938735/example/FNF Funkin Rap Battle Full Mod APK Unlock All Songs and Mods for Free.md b/spaces/simple0urra/skops-model-card-creator-2a23515a-d54e-4804-b365-27ed6e938735/example/FNF Funkin Rap Battle Full Mod APK Unlock All Songs and Mods for Free.md deleted file mode 100644 index 05dccc1b4a29e507f0f0a39e6e129d4432bdaf5d..0000000000000000000000000000000000000000 --- a/spaces/simple0urra/skops-model-card-creator-2a23515a-d54e-4804-b365-27ed6e938735/example/FNF Funkin Rap Battle Full Mod APK Unlock All Songs and Mods for Free.md +++ /dev/null @@ -1,122 +0,0 @@ -
-

How to Enjoy FNF Funkin Rap Battle with Full Mod APK Hack

-

If you are a fan of music and rhythm games, you might have heard of fnf funkin rap battle, a popular game that features catchy songs, cool characters, and challenging battles. But what if you want to enjoy the game without any limitations or restrictions? That's where a mod apk hack comes in handy. In this article, we will tell you everything you need to know about fnf funkin rap battle full mod apk hack, including its features, how to download and install it, tips and tricks for playing it, and a review of its pros and cons.

-

fnf funkin rap battle full mod apk hack


Download File –––––>>> https://ssurll.com/2uO0oy



-

What is FNF Funkin Rap Battle?

-

FNF Funkin Rap Battle is a musical rhythm game where you compete in freestyle music battles against various opponents. You have to press the arrow keys in time with the music to outdo your rivals and win the heart of your girlfriend. The game has a story mode where you can play through seven weeks of different songs and characters, as well as a free play mode where you can choose any song you want. The game also has an active development community that creates fan-made mods that add new songs, characters, and features to the game.

-

What is a Mod APK Hack?

-

A mod apk hack is a modified version of an original app that gives you access to features that are not available in the official version. For example, a mod apk hack can unlock all the content in a game, give you unlimited resources, remove ads or in-app purchases, or add custom features that enhance your gaming experience. A mod apk hack is usually downloaded as an apk file, which is an Android application package that contains all the files needed to install an app on your device.

-

Why Would You Want to Use a Mod APK Hack?

-

There are many reasons why you might want to use a mod apk hack for fnf funkin rap battle. Some of them are:

-

fnf funkin rap battle full mod apk download
-fnf funkin rap battle full mod apk unlocked
-fnf funkin rap battle full mod apk free
-fnf funkin rap battle full mod apk latest version
-fnf funkin rap battle full mod apk android
-fnf funkin rap battle full mod apk offline
-fnf funkin rap battle full mod apk no ads
-fnf funkin rap battle full mod apk unlimited money
-fnf funkin rap battle full mod apk all songs
-fnf funkin rap battle full mod apk all weeks
-fnf funkin rap battle full mod apk all characters
-fnf funkin rap battle full mod apk all mods
-fnf funkin rap battle full mod apk online
-fnf funkin rap battle full mod apk multiplayer
-fnf funkin rap battle full mod apk update
-fnf funkin rap battle full mod apk cheats
-fnf funkin rap battle full mod apk premium
-fnf funkin rap battle full mod apk pro
-fnf funkin rap battle full mod apk hack download
-fnf funkin rap battle full mod apk hack unlocked
-fnf funkin rap battle full mod apk hack free
-fnf funkin rap battle full mod apk hack latest version
-fnf funkin rap battle full mod apk hack android
-fnf funkin rap battle full mod apk hack offline
-fnf funkin rap battle full mod apk hack no ads
-fnf funkin rap battle full mod apk hack unlimited money
-fnf funkin rap battle full mod apk hack all songs
-fnf funkin rap battle full mod apk hack all weeks
-fnf funkin rap battle full mod apk hack all characters
-fnf funkin rap battle full mod apk hack all mods
-fnf funkin rap battle full mod apk hack online
-fnf funkin rap battle full mod apk hack multiplayer
-fnf funkin rap battle full mod apk hack update
-fnf funkin rap battle full mod apk hack cheats
-fnf funkin rap battle full mod apk hack premium
-fnf funkin rap battle full mod apk hack pro
-how to download fnf funkin rap battle full mod apk hack
-how to install fnf funkin rap battle full mod apk hack
-how to play fnf funkin rap battle full mod apk hack
-how to update fnf funkin rap battle full mod apk hack
-how to unlock all songs in fnf funkin rap battle full mod apk hack
-how to unlock all weeks in fnf funkin rap battle full mod apk hack
-how to unlock all characters in fnf funkin rap battle full mod apk hack
-how to unlock all mods in fnf funkin rap battle full mod apk hack
-how to get unlimited money in fnf funkin rap battle full mod apk hack
-how to remove ads in fnf funkin rap battle full mod apk hack
-how to play online in fnf funkin rap battle full mod apk hack
-how to play multiplayer in fnf funkin rap battle full mod apk hack

-
    -
  • You want to play all the weeks and mods without having to unlock them or pay for them.
    • -
  • You want to have unlimited health and score so you can beat any opponent easily.
    • -
  • You want to customize your game with your own songs and characters.
    • -
  • You want to avoid annoying ads or in-app purchases that interrupt your gameplay.
    • -
-

If any of these reasons appeal to you, then you should consider using a mod apk hack for fnf funkin rap battle.

-

Features of FNF Funkin Rap Battle Full Mod APK Hack

-

There are many mod apk hacks available for fnf funkin rap battle, but not all of them are reliable or safe. Some of them may contain viruses or malware that can harm your device or steal your personal information. Some of them may not work properly or crash your game. Some of them may not have the features that you want or need. That's why you should be careful when choosing a mod apk hack for fnf funkin rap battle.

-

One of the best mod apk hacks for fnf funkin rap battle is the one that we will recommend in this article. It has the following features:

-
    -
  • All weeks and mods unlocked: You can play any week or mod that you want without having to complete the previous This is one of the tips and tricks that I will continue to write in the article:
  • Change your keys to FGHJ or similar configuration: The game allows you to change your keys to whatever configuration you want. However, some configurations are better than others. One of the best configurations is FGHJ, which is similar to the arrow keys but more comfortable and ergonomic. To change your keys, go to the options menu, then controls, then customize your keys.
    • -

    Review of FNF Funkin Rap Battle Full Mod APK Hack

    -

    Now that you know how to download and install fnf funkin rap battle full mod apk hack, and how to play it better, you might be wondering if it is worth it. To help you decide, here is a review of its pros and cons, as well as ratings and feedback from users who have tried it.

    -

    Pros and Cons

    -

    Here are some of the pros and cons of fnf funkin rap battle full mod apk hack:

    - - - - - - - - - - - - - - - - - - - - - -
    ProsCons
    All weeks and mods unlockedPossible compatibility issues with some devices
    Unlimited health and scorePossible loss of challenge and excitement
    Custom songs and charactersPossible copyright infringement or plagiarism
    No ads or in-app purchasesPossible lack of support or updates from developers
    -

    Ratings and Feedback

    -

    Here are some of the ratings and feedback from users who have tried fnf funkin rap battle full mod apk hack:

    - - "This mod apk hack is awesome! I can play all the songs and characters that I want without any hassle. The game runs smoothly and has no bugs or glitches. I love it!" - 5 stars - "This mod apk hack is good, but not perfect. I like that I can have unlimited health and score, but it also makes the game too easy and boring. I wish there was a way to adjust the difficulty level or turn off the cheats." - 4 stars - "This mod apk hack is bad. It doesn't work on my device and crashes every time I try to open it. It also has viruses that infected my device and stole my data. Do not download this!" - 1 star

    Conclusion

    -

    FNF Funkin Rap Battle is a fun and addictive music and rhythm game that features catchy songs, cool characters, and challenging battles. However, if you want to enjoy the game without any limitations or restrictions, you should consider using a mod apk hack that gives you access to features that are not available in the official version.

    -

    In this article, we have told you everything you need to know about fnf funkin rap battle full mod apk hack, including its features, how to download and install it, tips and tricks for playing it, and a review of its pros and cons. We hope that this article has been helpful and informative for you.

    -

    If you are interested in trying out fnf funkin rap battle full mod apk hack, you can download it from [FNF Funkin Rap Battle Full Mod APK Hack], which is a reliable source that offers high-quality mod apk hacks for various games, including fnf funkin rap battle. However, before you do so, make sure that you have enabled unknown sources on your device, and that you have backed up your data in case anything goes wrong.

    -

    Once you have downloaded and installed fnf funkin rap battle full mod apk hack on your device, you can start playing the game with all the features that you want. You can play any week or mod that you want without having to unlock them or pay for them. You can have unlimited health and score so you can beat any opponent easily. You can customize your game with your own songs and characters. You can avoid annoying ads or in-app purchases that interrupt your gameplay.

    -

    However, remember that using a mod apk hack also has some drawbacks. It may not work on some devices or cause compatibility issues. It may reduce the challenge and excitement of the game. It may violate the intellectual property rights of the original developers or creators. It may lack support or updates from the developers. It may contain viruses or malware that can harm your device or steal your personal information.

    -

    Therefore, use a mod apk hack at your own risk and discretion. We are not responsible for any damages or losses that may result from using a mod apk hack.

    -

    We hope that you have enjoyed reading this article and learned something new. If you have any questions or comments, feel free to leave them below. Thank you for your time and attention. Happy gaming!

    -

    FAQs

    -

    Here are some of the frequently asked questions about fnf funkin rap battle full mod apk hack:

    -
      -
    1. What is the difference between fnf funkin rap battle and Friday Night Funkin'?
      2. -

      FNF Funkin Rap Battle is a fan-made mod of Friday Night Funkin', which is the original game that inspired it. Friday Night Funkin' is a music and rhythm game that features the same gameplay and characters as fnf funkin rap battle, but with different songs and graphics. You can play Friday Night Funkin' on its official website or download it from various platforms.

      -
    2. Is fnf funkin rap battle full mod apk hack safe to use?
      3. -

      FNF Funkin Rap Battle Full Mod APK Hack is safe to use as long as you download it from a reliable source, such as [FNF Funkin Rap Battle Full Mod APK Hack], which is a website that provides high-quality mod apk hacks for various games, including fnf funkin rap battle. However, you should always be careful when downloading and installing any mod apk hack, as some of them may contain viruses or malware that can harm your device or steal your personal information. You should also backup your data in case anything goes wrong.

      -
    3. Can I play fnf funkin rap battle full mod apk hack on PC?
      4. -

      FNF Funkin Rap Battle Full Mod APK Hack is designed for Android devices, so you cannot play it directly on PC. However, you can use an Android emulator, which is a software that allows you to run Android apps on PC. Some of the popular Android emulators are BlueStacks, NoxPlayer, and LDPlayer. You can download any of them from their official websites, then install them on your PC, then download and install fnf funkin rap battle full mod apk hack on the emulator, then play it on your PC.

      -
    4. Can I play fnf funkin rap battle full mod apk hack online?
      5. -

      FNF Funkin Rap Battle Full Mod APK Hack is an offline game, so you cannot play it online. However, you can play the original fnf funkin rap battle online on its official website, which is [FNF Funkin Rap Battle Online]. There, you can play the game in your browser without having to download or install anything. You can also play other fan-made mods online on various websites, such as [FNF Mods Online]. However, these websites may not have all the features or updates that the mod apk hack has.

      -
    5. Can I update fnf funkin rap battle full mod apk hack?
      6. -

      FNF Funkin Rap Battle Full Mod APK Hack may not receive regular updates from the developers, as it is a fan-made mod that is not officially supported or endorsed by them. However, you can check the website where you downloaded the mod apk hack from time to time to see if there are any new versions or features available. If there are, you can download and install them on your device to enjoy the latest updates.

      -

    197e85843d
    -
    -
    \ No newline at end of file diff --git a/spaces/society-ethics/model-card-regulatory-check/tests/cards/facebook___bart-large-cnn.md b/spaces/society-ethics/model-card-regulatory-check/tests/cards/facebook___bart-large-cnn.md deleted file mode 100644 index 3945880b81a2e381c899bf1d9805f009b5a0e140..0000000000000000000000000000000000000000 --- a/spaces/society-ethics/model-card-regulatory-check/tests/cards/facebook___bart-large-cnn.md +++ /dev/null @@ -1,117 +0,0 @@ ---- -language: -- en -tags: -- summarization -license: mit -thumbnail: https://huggingface.co/front/thumbnails/facebook.png -datasets: -- cnn_dailymail -model-index: -- name: facebook/bart-large-cnn - results: - - task: - type: summarization - name: Summarization - dataset: - name: cnn_dailymail - type: cnn_dailymail - config: 3.0.0 - split: train - metrics: - - name: ROUGE-1 - type: rouge - value: 42.9486 - verified: true - - name: ROUGE-2 - type: rouge - value: 20.8149 - verified: true - - name: ROUGE-L - type: rouge - value: 30.6186 - verified: true - - name: ROUGE-LSUM - type: rouge - value: 40.0376 - verified: true - - name: loss - type: loss - value: 2.529000997543335 - verified: true - - name: gen_len - type: gen_len - value: 78.5866 - verified: true ---- -# BART (large-sized model), fine-tuned on CNN Daily Mail - -BART model pre-trained on English language, and fine-tuned on [CNN Daily Mail](https://huggingface.co/datasets/cnn_dailymail). It was introduced in the paper [BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension](https://arxiv.org/abs/1910.13461) by Lewis et al. and first released in [this repository (https://github.com/pytorch/fairseq/tree/master/examples/bart). - -Disclaimer: The team releasing BART did not write a model card for this model so this model card has been written by the Hugging Face team. - -## Model description - -BART is a transformer encoder-encoder (seq2seq) model with a bidirectional (BERT-like) encoder and an autoregressive (GPT-like) decoder. BART is pre-trained by (1) corrupting text with an arbitrary noising function, and (2) learning a model to reconstruct the original text. - -BART is particularly effective when fine-tuned for text generation (e.g. summarization, translation) but also works well for comprehension tasks (e.g. text classification, question answering). This particular checkpoint has been fine-tuned on CNN Daily Mail, a large collection of text-summary pairs. - -## Intended uses & limitations - -You can use this model for text summarization. - -### How to use - -Here is how to use this model with the [pipeline API](https://huggingface.co/transformers/main_classes/pipelines.html): - -```python -from transformers import pipeline - -summarizer = pipeline("summarization", model="facebook/bart-large-cnn") - -ARTICLE = """ New York (CNN)When Liana Barrientos was 23 years old, she got married in Westchester County, New York. -A year later, she got married again in Westchester County, but to a different man and without divorcing her first husband. -Only 18 days after that marriage, she got hitched yet again. Then, Barrientos declared "I do" five more times, sometimes only within two weeks of each other. -In 2010, she married once more, this time in the Bronx. In an application for a marriage license, she stated it was her "first and only" marriage. -Barrientos, now 39, is facing two criminal counts of "offering a false instrument for filing in the first degree," referring to her false statements on the -2010 marriage license application, according to court documents. -Prosecutors said the marriages were part of an immigration scam. -On Friday, she pleaded not guilty at State Supreme Court in the Bronx, according to her attorney, Christopher Wright, who declined to comment further. -After leaving court, Barrientos was arrested and charged with theft of service and criminal trespass for allegedly sneaking into the New York subway through an emergency exit, said Detective -Annette Markowski, a police spokeswoman. In total, Barrientos has been married 10 times, with nine of her marriages occurring between 1999 and 2002. -All occurred either in Westchester County, Long Island, New Jersey or the Bronx. She is believed to still be married to four men, and at one time, she was married to eight men at once, prosecutors say. -Prosecutors said the immigration scam involved some of her husbands, who filed for permanent residence status shortly after the marriages. -Any divorces happened only after such filings were approved. It was unclear whether any of the men will be prosecuted. -The case was referred to the Bronx District Attorney\'s Office by Immigration and Customs Enforcement and the Department of Homeland Security\'s -Investigation Division. Seven of the men are from so-called "red-flagged" countries, including Egypt, Turkey, Georgia, Pakistan and Mali. -Her eighth husband, Rashid Rajput, was deported in 2006 to his native Pakistan after an investigation by the Joint Terrorism Task Force. -If convicted, Barrientos faces up to four years in prison. Her next court appearance is scheduled for May 18. -""" -print(summarizer(ARTICLE, max_length=130, min_length=30, do_sample=False)) ->>> [{'summary_text': 'Liana Barrientos, 39, is charged with two counts of "offering a false instrument for filing in the first degree" In total, she has been married 10 times, with nine of her marriages occurring between 1999 and 2002. She is believed to still be married to four men.'}] -``` - -### BibTeX entry and citation info - -```bibtex -@article{DBLP:journals/corr/abs-1910-13461, - author = {Mike Lewis and - Yinhan Liu and - Naman Goyal and - Marjan Ghazvininejad and - Abdelrahman Mohamed and - Omer Levy and - Veselin Stoyanov and - Luke Zettlemoyer}, - title = {{BART:} Denoising Sequence-to-Sequence Pre-training for Natural Language - Generation, Translation, and Comprehension}, - journal = {CoRR}, - volume = {abs/1910.13461}, - year = {2019}, - url = {http://arxiv.org/abs/1910.13461}, - eprinttype = {arXiv}, - eprint = {1910.13461}, - timestamp = {Thu, 31 Oct 2019 14:02:26 +0100}, - biburl = {https://dblp.org/rec/journals/corr/abs-1910-13461.bib}, - bibsource = {dblp computer science bibliography, https://dblp.org} -} \ No newline at end of file diff --git a/spaces/sohojoe/soho-clip-embeddings-explorer/experimental/clip_app.py b/spaces/sohojoe/soho-clip-embeddings-explorer/experimental/clip_app.py deleted file mode 100644 index 896b72b9fd060b1a8f6b9afe39be1101304ae3b7..0000000000000000000000000000000000000000 --- a/spaces/sohojoe/soho-clip-embeddings-explorer/experimental/clip_app.py +++ /dev/null @@ -1,137 +0,0 @@ -# File name: model.py -import json -import os -import numpy as np -import torch -from starlette.requests import Request -from PIL import Image -import ray -from ray import serve -from clip_retrieval.load_clip import load_clip, get_tokenizer -# from clip_retrieval.clip_client import ClipClient, Modality - -@serve.deployment(num_replicas=6, ray_actor_options={"num_cpus": .2, "num_gpus": 0.1}) -# @serve.deployment(num_replicas=3, ray_actor_options={"num_cpus": .2, "num_gpus": 0.2}) -class CLIPTransform: - def __init__(self): - # os.environ["OMP_NUM_THREADS"] = "20" - # torch.set_num_threads(20) - # Load model - self.device = "cuda:0" if torch.cuda.is_available() else "cpu" - self._clip_model="ViT-L/14" - # self._clip_model="open_clip:ViT-H-14" - self.model, self.preprocess = load_clip(self._clip_model, use_jit=True, device=self.device) - self.tokenizer = get_tokenizer(self._clip_model) - - print ("using device", self.device) - - def text_to_embeddings(self, prompt): - text = self.tokenizer([prompt]).to(self.device) - with torch.no_grad(): - prompt_embededdings = self.model.encode_text(text) - prompt_embededdings /= prompt_embededdings.norm(dim=-1, keepdim=True) - return(prompt_embededdings) - - def image_to_embeddings(self, input_im): - input_im = Image.fromarray(input_im) - prepro = self.preprocess(input_im).unsqueeze(0).to(self.device) - with torch.no_grad(): - image_embeddings = self.model.encode_image(prepro) - image_embeddings /= image_embeddings.norm(dim=-1, keepdim=True) - return(image_embeddings) - - def preprocessed_image_to_emdeddings(self, prepro): - with torch.no_grad(): - image_embeddings = self.model.encode_image(prepro) - image_embeddings /= image_embeddings.norm(dim=-1, keepdim=True) - return(image_embeddings) - - async def __call__(self, http_request: Request) -> str: - form_data = await http_request.form() - - embeddings = None - if "text" in form_data: - prompt = (await form_data["text"].read()).decode() - print (type(prompt)) - print (str(prompt)) - embeddings = self.text_to_embeddings(prompt) - elif "image_url" in form_data: - image_url = (await form_data["image_url"].read()).decode() - # download image from url - import requests - from io import BytesIO - image_bytes = requests.get(image_url).content - input_image = Image.open(BytesIO(image_bytes)) - input_image = input_image.convert('RGB') - input_image = np.array(input_image) - embeddings = self.image_to_embeddings(input_image) - elif "preprocessed_image" in form_data: - tensor_bytes = await form_data["preprocessed_image"].read() - shape_bytes = await form_data["shape"].read() - dtype_bytes = await form_data["dtype"].read() - - # Convert bytes back to original form - dtype_mapping = { - "torch.float32": torch.float32, - "torch.float64": torch.float64, - "torch.float16": torch.float16, - "torch.uint8": torch.uint8, - "torch.int8": torch.int8, - "torch.int16": torch.int16, - "torch.int32": torch.int32, - "torch.int64": torch.int64, - torch.float32: np.float32, - torch.float64: np.float64, - torch.float16: np.float16, - torch.uint8: np.uint8, - torch.int8: np.int8, - torch.int16: np.int16, - torch.int32: np.int32, - torch.int64: np.int64, - # add more if needed - } - dtype_str = dtype_bytes.decode() - dtype_torch = dtype_mapping[dtype_str] - dtype_numpy = dtype_mapping[dtype_torch] - # shape = np.frombuffer(shape_bytes, dtype=np.int64) - # TODO: fix shape so it is passed nicely - shape = tuple([1, 3, 224, 224]) - - tensor_numpy = np.frombuffer(tensor_bytes, dtype=dtype_numpy).reshape(shape) - tensor_numpy = np.require(tensor_numpy, requirements='W') - tensor = torch.from_numpy(tensor_numpy) - prepro = tensor.to(self.device) - embeddings = self.preprocessed_image_to_emdeddings(prepro) - else: - print ("Invalid request") - raise Exception("Invalid request") - return embeddings.float().cpu().numpy().tolist() - - request = await http_request.json() - # print(type(request)) - # print(str(request)) - # switch based if we are using text or image - embeddings = None - if "text" in request: - prompt = request["text"] - embeddings = self.text_to_embeddings(prompt) - elif "image_url" in request: - image_url = request["image_url"] - # download image from url - import requests - from io import BytesIO - image_bytes = requests.get(image_url).content - input_image = Image.open(BytesIO(image_bytes)) - input_image = input_image.convert('RGB') - input_image = np.array(input_image) - embeddings = self.image_to_embeddings(input_image) - elif "preprocessed_image" in request: - prepro = request["preprocessed_image"] - # create torch tensor on the device - prepro = torch.tensor(prepro).to(self.device) - embeddings = self.preprocessed_image_to_emdeddings(prepro) - else: - raise Exception("Invalid request") - return embeddings.cpu().numpy().tolist() - -deployment_graph = CLIPTransform.bind() diff --git a/spaces/spotify/huggingface-demo-song-lyrics/app.py b/spaces/spotify/huggingface-demo-song-lyrics/app.py deleted file mode 100644 index 043e451c9cf006e2053d0c308e5a4df811910941..0000000000000000000000000000000000000000 --- a/spaces/spotify/huggingface-demo-song-lyrics/app.py +++ /dev/null @@ -1,26 +0,0 @@ -import torch -import numpy as np -import gradio as gr -from transformers import AutoTokenizer, AutoModelForSequenceClassification - -repo_name = 'spotify/autonlp-huggingface-demo-song-lyrics-18923587' - -tokenizer = AutoTokenizer.from_pretrained(repo_name) -model = AutoModelForSequenceClassification.from_pretrained(repo_name) -labels = model.config.id2label - -def predict(lyrics): - inputs = tokenizer(lyrics, padding=True, truncation=True, return_tensors="pt") - outputs = model(**inputs) - predictions = torch.nn.functional.softmax(outputs.logits, dim=-1) - predictions = predictions.detach().numpy()[0] - predictions = predictions*100 - sorted_indexes = np.argsort(predictions) - return "These lyrics are {:.2f}% {}, {:.2f}% {} and {:.2f}% {}.".format( - predictions[sorted_indexes[-1]], labels[sorted_indexes[-1]], - predictions[sorted_indexes[-2]], labels[sorted_indexes[-2]], - predictions[sorted_indexes[-3]], labels[sorted_indexes[-3]]) - -input = gr.inputs.Textbox(lines=20) -iface = gr.Interface(fn=predict, inputs=input, outputs="text") -iface.launch() diff --git a/spaces/sriramelango/Social_Classification_Public/fairseq/examples/speech_synthesis/preprocessing/denoiser/demucs.py b/spaces/sriramelango/Social_Classification_Public/fairseq/examples/speech_synthesis/preprocessing/denoiser/demucs.py deleted file mode 100644 index 3f70e73d6a37d32e05b6cf0e87f42e13c467cd52..0000000000000000000000000000000000000000 --- a/spaces/sriramelango/Social_Classification_Public/fairseq/examples/speech_synthesis/preprocessing/denoiser/demucs.py +++ /dev/null @@ -1,473 +0,0 @@ -# Copyright (c) Facebook, Inc. and its affiliates. -# All rights reserved. -# -# This source code is licensed under the license found in the -# LICENSE file in the root directory of this source tree. -# author: adefossez - -import math -import time - -import torch as th -from torch import nn -from torch.nn import functional as F - -from .resample import downsample2, upsample2 -from .utils import capture_init - - -class BLSTM(nn.Module): - def __init__(self, dim, layers=2, bi=True): - super().__init__() - klass = nn.LSTM - self.lstm = klass( - bidirectional=bi, num_layers=layers, hidden_size=dim, input_size=dim - ) - self.linear = None - if bi: - self.linear = nn.Linear(2 * dim, dim) - - def forward(self, x, hidden=None): - x, hidden = self.lstm(x, hidden) - if self.linear: - x = self.linear(x) - return x, hidden - - -def rescale_conv(conv, reference): - std = conv.weight.std().detach() - scale = (std / reference)**0.5 - conv.weight.data /= scale - if conv.bias is not None: - conv.bias.data /= scale - - -def rescale_module(module, reference): - for sub in module.modules(): - if isinstance(sub, (nn.Conv1d, nn.ConvTranspose1d)): - rescale_conv(sub, reference) - - -class Demucs(nn.Module): - """ - Demucs speech enhancement model. - Args: - - chin (int): number of input channels. - - chout (int): number of output channels. - - hidden (int): number of initial hidden channels. - - depth (int): number of layers. - - kernel_size (int): kernel size for each layer. - - stride (int): stride for each layer. - - causal (bool): if false, uses BiLSTM instead of LSTM. - - resample (int): amount of resampling to apply to the input/output. - Can be one of 1, 2 or 4. - - growth (float): number of channels is multiplied by this for every layer. - - max_hidden (int): maximum number of channels. Can be useful to - control the size/speed of the model. - - normalize (bool): if true, normalize the input. - - glu (bool): if true uses GLU instead of ReLU in 1x1 convolutions. - - rescale (float): controls custom weight initialization. - See https://arxiv.org/abs/1911.13254. - - floor (float): stability flooring when normalizing. - - """ - @capture_init - def __init__(self, - chin=1, - chout=1, - hidden=48, - depth=5, - kernel_size=8, - stride=4, - causal=True, - resample=4, - growth=2, - max_hidden=10_000, - normalize=True, - glu=True, - rescale=0.1, - floor=1e-3): - - super().__init__() - if resample not in [1, 2, 4]: - raise ValueError("Resample should be 1, 2 or 4.") - - self.chin = chin - self.chout = chout - self.hidden = hidden - self.depth = depth - self.kernel_size = kernel_size - self.stride = stride - self.causal = causal - self.floor = floor - self.resample = resample - self.normalize = normalize - - self.encoder = nn.ModuleList() - self.decoder = nn.ModuleList() - activation = nn.GLU(1) if glu else nn.ReLU() - ch_scale = 2 if glu else 1 - - for index in range(depth): - encode = [] - encode += [ - nn.Conv1d(chin, hidden, kernel_size, stride), - nn.ReLU(), - nn.Conv1d(hidden, hidden * ch_scale, 1), activation, - ] - self.encoder.append(nn.Sequential(*encode)) - - decode = [] - decode += [ - nn.Conv1d(hidden, ch_scale * hidden, 1), activation, - nn.ConvTranspose1d(hidden, chout, kernel_size, stride), - ] - if index > 0: - decode.append(nn.ReLU()) - self.decoder.insert(0, nn.Sequential(*decode)) - chout = hidden - chin = hidden - hidden = min(int(growth * hidden), max_hidden) - - self.lstm = BLSTM(chin, bi=not causal) - if rescale: - rescale_module(self, reference=rescale) - - def valid_length(self, length): - """ - Return the nearest valid length to use with the model so that - there is no time steps left over in a convolutions, e.g. for all - layers, size of the input - kernel_size % stride = 0. - - If the mixture has a valid length, the estimated sources - will have exactly the same length. - """ - length = math.ceil(length * self.resample) - for _ in range(self.depth): - length = math.ceil((length - self.kernel_size) / self.stride) + 1 - length = max(length, 1) - for _ in range(self.depth): - length = (length - 1) * self.stride + self.kernel_size - length = int(math.ceil(length / self.resample)) - return int(length) - - @property - def total_stride(self): - return self.stride ** self.depth // self.resample - - def forward(self, mix): - if mix.dim() == 2: - mix = mix.unsqueeze(1) - - if self.normalize: - mono = mix.mean(dim=1, keepdim=True) - std = mono.std(dim=-1, keepdim=True) - mix = mix / (self.floor + std) - else: - std = 1 - length = mix.shape[-1] - x = mix - x = F.pad(x, (0, self.valid_length(length) - length)) - if self.resample == 2: - x = upsample2(x) - elif self.resample == 4: - x = upsample2(x) - x = upsample2(x) - skips = [] - for encode in self.encoder: - x = encode(x) - skips.append(x) - x = x.permute(2, 0, 1) - x, _ = self.lstm(x) - x = x.permute(1, 2, 0) - for decode in self.decoder: - skip = skips.pop(-1) - x = x + skip[..., :x.shape[-1]] - x = decode(x) - if self.resample == 2: - x = downsample2(x) - elif self.resample == 4: - x = downsample2(x) - x = downsample2(x) - - x = x[..., :length] - return std * x - - -def fast_conv(conv, x): - """ - Faster convolution evaluation if either kernel size is 1 - or length of sequence is 1. - """ - batch, chin, length = x.shape - chout, chin, kernel = conv.weight.shape - assert batch == 1 - if kernel == 1: - x = x.view(chin, length) - out = th.addmm(conv.bias.view(-1, 1), - conv.weight.view(chout, chin), x) - elif length == kernel: - x = x.view(chin * kernel, 1) - out = th.addmm(conv.bias.view(-1, 1), - conv.weight.view(chout, chin * kernel), x) - else: - out = conv(x) - return out.view(batch, chout, -1) - - -class DemucsStreamer: - """ - Streaming implementation for Demucs. It supports being fed with any amount - of audio at a time. You will get back as much audio as possible at that - point. - - Args: - - demucs (Demucs): Demucs model. - - dry (float): amount of dry (e.g. input) signal to keep. 0 is maximum - noise removal, 1 just returns the input signal. Small values > 0 - allows to limit distortions. - - num_frames (int): number of frames to process at once. Higher values - will increase overall latency but improve the real time factor. - - resample_lookahead (int): extra lookahead used for the resampling. - - resample_buffer (int): size of the buffer of previous inputs/outputs - kept for resampling. - """ - def __init__(self, demucs, - dry=0, - num_frames=1, - resample_lookahead=64, - resample_buffer=256): - device = next(iter(demucs.parameters())).device - self.demucs = demucs - self.lstm_state = None - self.conv_state = None - self.dry = dry - self.resample_lookahead = resample_lookahead - resample_buffer = min(demucs.total_stride, resample_buffer) - self.resample_buffer = resample_buffer - self.frame_length = demucs.valid_length(1) + \ - demucs.total_stride * (num_frames - 1) - self.total_length = self.frame_length + self.resample_lookahead - self.stride = demucs.total_stride * num_frames - self.resample_in = th.zeros(demucs.chin, resample_buffer, device=device) - self.resample_out = th.zeros( - demucs.chin, resample_buffer, device=device - ) - - self.frames = 0 - self.total_time = 0 - self.variance = 0 - self.pending = th.zeros(demucs.chin, 0, device=device) - - bias = demucs.decoder[0][2].bias - weight = demucs.decoder[0][2].weight - chin, chout, kernel = weight.shape - self._bias = bias.view(-1, 1).repeat(1, kernel).view(-1, 1) - self._weight = weight.permute(1, 2, 0).contiguous() - - def reset_time_per_frame(self): - self.total_time = 0 - self.frames = 0 - - @property - def time_per_frame(self): - return self.total_time / self.frames - - def flush(self): - """ - Flush remaining audio by padding it with zero. Call this - when you have no more input and want to get back the last chunk of audio. - """ - pending_length = self.pending.shape[1] - padding = th.zeros( - self.demucs.chin, self.total_length, device=self.pending.device - ) - out = self.feed(padding) - return out[:, :pending_length] - - def feed(self, wav): - """ - Apply the model to mix using true real time evaluation. - Normalization is done online as is the resampling. - """ - begin = time.time() - demucs = self.demucs - resample_buffer = self.resample_buffer - stride = self.stride - resample = demucs.resample - - if wav.dim() != 2: - raise ValueError("input wav should be two dimensional.") - chin, _ = wav.shape - if chin != demucs.chin: - raise ValueError(f"Expected {demucs.chin} channels, got {chin}") - - self.pending = th.cat([self.pending, wav], dim=1) - outs = [] - while self.pending.shape[1] >= self.total_length: - self.frames += 1 - frame = self.pending[:, :self.total_length] - dry_signal = frame[:, :stride] - if demucs.normalize: - mono = frame.mean(0) - variance = (mono**2).mean() - self.variance = variance / self.frames + \ - (1 - 1 / self.frames) * self.variance - frame = frame / (demucs.floor + math.sqrt(self.variance)) - frame = th.cat([self.resample_in, frame], dim=-1) - self.resample_in[:] = frame[:, stride - resample_buffer:stride] - - if resample == 4: - frame = upsample2(upsample2(frame)) - elif resample == 2: - frame = upsample2(frame) - # remove pre sampling buffer - frame = frame[:, resample * resample_buffer:] - # remove extra samples after window - frame = frame[:, :resample * self.frame_length] - - out, extra = self._separate_frame(frame) - padded_out = th.cat([self.resample_out, out, extra], 1) - self.resample_out[:] = out[:, -resample_buffer:] - if resample == 4: - out = downsample2(downsample2(padded_out)) - elif resample == 2: - out = downsample2(padded_out) - else: - out = padded_out - - out = out[:, resample_buffer // resample:] - out = out[:, :stride] - - if demucs.normalize: - out *= math.sqrt(self.variance) - out = self.dry * dry_signal + (1 - self.dry) * out - outs.append(out) - self.pending = self.pending[:, stride:] - - self.total_time += time.time() - begin - if outs: - out = th.cat(outs, 1) - else: - out = th.zeros(chin, 0, device=wav.device) - return out - - def _separate_frame(self, frame): - demucs = self.demucs - skips = [] - next_state = [] - first = self.conv_state is None - stride = self.stride * demucs.resample - x = frame[None] - for idx, encode in enumerate(demucs.encoder): - stride //= demucs.stride - length = x.shape[2] - if idx == demucs.depth - 1: - # This is sligthly faster for the last conv - x = fast_conv(encode[0], x) - x = encode[1](x) - x = fast_conv(encode[2], x) - x = encode[3](x) - else: - if not first: - prev = self.conv_state.pop(0) - prev = prev[..., stride:] - tgt = (length - demucs.kernel_size) // demucs.stride + 1 - missing = tgt - prev.shape[-1] - offset = length - demucs.kernel_size - \ - demucs.stride * (missing - 1) - x = x[..., offset:] - x = encode[1](encode[0](x)) - x = fast_conv(encode[2], x) - x = encode[3](x) - if not first: - x = th.cat([prev, x], -1) - next_state.append(x) - skips.append(x) - - x = x.permute(2, 0, 1) - x, self.lstm_state = demucs.lstm(x, self.lstm_state) - x = x.permute(1, 2, 0) - # In the following, x contains only correct samples, i.e. the one - # for which each time position is covered by two window of the upper - # layer. extra contains extra samples to the right, and is used only as - # a better padding for the online resampling. - extra = None - for idx, decode in enumerate(demucs.decoder): - skip = skips.pop(-1) - x += skip[..., :x.shape[-1]] - x = fast_conv(decode[0], x) - x = decode[1](x) - - if extra is not None: - skip = skip[..., x.shape[-1]:] - extra += skip[..., :extra.shape[-1]] - extra = decode[2](decode[1](decode[0](extra))) - x = decode[2](x) - next_state.append( - x[..., -demucs.stride:] - decode[2].bias.view(-1, 1) - ) - if extra is None: - extra = x[..., -demucs.stride:] - else: - extra[..., :demucs.stride] += next_state[-1] - x = x[..., :-demucs.stride] - - if not first: - prev = self.conv_state.pop(0) - x[..., :demucs.stride] += prev - if idx != demucs.depth - 1: - x = decode[3](x) - extra = decode[3](extra) - self.conv_state = next_state - return x[0], extra[0] - - -def test(): - import argparse - parser = argparse.ArgumentParser( - "denoiser.demucs", - description="Benchmark the streaming Demucs implementation, as well as " - "checking the delta with the offline implementation.") - parser.add_argument("--depth", default=5, type=int) - parser.add_argument("--resample", default=4, type=int) - parser.add_argument("--hidden", default=48, type=int) - parser.add_argument("--sample_rate", default=16000, type=float) - parser.add_argument("--device", default="cpu") - parser.add_argument("-t", "--num_threads", type=int) - parser.add_argument("-f", "--num_frames", type=int, default=1) - args = parser.parse_args() - if args.num_threads: - th.set_num_threads(args.num_threads) - sr = args.sample_rate - sr_ms = sr / 1000 - demucs = Demucs( - depth=args.depth, hidden=args.hidden, resample=args.resample - ).to(args.device) - x = th.randn(1, int(sr * 4)).to(args.device) - out = demucs(x[None])[0] - streamer = DemucsStreamer(demucs, num_frames=args.num_frames) - out_rt = [] - frame_size = streamer.total_length - with th.no_grad(): - while x.shape[1] > 0: - out_rt.append(streamer.feed(x[:, :frame_size])) - x = x[:, frame_size:] - frame_size = streamer.demucs.total_stride - out_rt.append(streamer.flush()) - out_rt = th.cat(out_rt, 1) - model_size = sum(p.numel() for p in demucs.parameters()) * 4 / 2**20 - initial_lag = streamer.total_length / sr_ms - tpf = 1000 * streamer.time_per_frame - print(f"model size: {model_size:.1f}MB, ", end='') - print(f"delta batch/streaming: {th.norm(out - out_rt) / th.norm(out):.2%}") - print(f"initial lag: {initial_lag:.1f}ms, ", end='') - print(f"stride: {streamer.stride * args.num_frames / sr_ms:.1f}ms") - print(f"time per frame: {tpf:.1f}ms, ", end='') - rtf = (1000 * streamer.time_per_frame) / (streamer.stride / sr_ms) - print(f"RTF: {rtf:.2f}") - print(f"Total lag with computation: {initial_lag + tpf:.1f}ms") - - -if __name__ == "__main__": - test() diff --git a/spaces/sriramelango/Social_Classification_Public/fairseq/fairseq/models/transformer/__init__.py b/spaces/sriramelango/Social_Classification_Public/fairseq/fairseq/models/transformer/__init__.py deleted file mode 100644 index 681fca3d4553f6832a65f61fc186793bc4ee0679..0000000000000000000000000000000000000000 --- a/spaces/sriramelango/Social_Classification_Public/fairseq/fairseq/models/transformer/__init__.py +++ /dev/null @@ -1,50 +0,0 @@ -# Copyright (c) Facebook Inc. and its affiliates. -# -# This source code is licensed under the MIT license found in the -# LICENSE file in the root directory of this source tree. -"""isort:skip_file""" - -from .transformer_config import ( - TransformerConfig, - DEFAULT_MAX_SOURCE_POSITIONS, - DEFAULT_MAX_TARGET_POSITIONS, - DEFAULT_MIN_PARAMS_TO_WRAP, -) -from .transformer_decoder import TransformerDecoder, TransformerDecoderBase, Linear -from .transformer_encoder import TransformerEncoder, TransformerEncoderBase -from .transformer_legacy import ( - TransformerModel, - base_architecture, - tiny_architecture, - transformer_iwslt_de_en, - transformer_wmt_en_de, - transformer_vaswani_wmt_en_de_big, - transformer_vaswani_wmt_en_fr_big, - transformer_wmt_en_de_big, - transformer_wmt_en_de_big_t2t, -) -from .transformer_base import TransformerModelBase, Embedding - - -__all__ = [ - "TransformerModelBase", - "TransformerConfig", - "TransformerDecoder", - "TransformerDecoderBase", - "TransformerEncoder", - "TransformerEncoderBase", - "TransformerModel", - "Embedding", - "Linear", - "base_architecture", - "tiny_architecture", - "transformer_iwslt_de_en", - "transformer_wmt_en_de", - "transformer_vaswani_wmt_en_de_big", - "transformer_vaswani_wmt_en_fr_big", - "transformer_wmt_en_de_big", - "transformer_wmt_en_de_big_t2t", - "DEFAULT_MAX_SOURCE_POSITIONS", - "DEFAULT_MAX_TARGET_POSITIONS", - "DEFAULT_MIN_PARAMS_TO_WRAP", -] diff --git a/spaces/stanfordnlp/Backpack-Demo/README.md b/spaces/stanfordnlp/Backpack-Demo/README.md deleted file mode 100644 index bcc15c34d519fa83c6f8a3c5fde750dbf5647787..0000000000000000000000000000000000000000 --- a/spaces/stanfordnlp/Backpack-Demo/README.md +++ /dev/null @@ -1,13 +0,0 @@ ---- -title: Backpack -emoji: 🏃 -colorFrom: green -colorTo: red -sdk: gradio -sdk_version: 3.36.1 -app_file: app.py -pinned: false -duplicated_from: lora-x/Backpack ---- - -Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference diff --git a/spaces/stomexserde/gpt4-ui/Examples/Akuntansi Pajak Waluyo Pdf 29.md b/spaces/stomexserde/gpt4-ui/Examples/Akuntansi Pajak Waluyo Pdf 29.md deleted file mode 100644 index 47e63feccdd539c889fc55e663ae74df43c83ca8..0000000000000000000000000000000000000000 --- a/spaces/stomexserde/gpt4-ui/Examples/Akuntansi Pajak Waluyo Pdf 29.md +++ /dev/null @@ -1,38 +0,0 @@ -
    -

    Akuntansi Pajak Waluyo Pdf 29: A Comprehensive Guide to Tax Accounting in Indonesia

    -

    Tax accounting is a branch of accounting that deals with the preparation and filing of tax returns, as well as the analysis and interpretation of tax laws and regulations. Tax accounting is essential for individuals and businesses who want to comply with their tax obligations and optimize their tax benefits.

    -

    However, tax accounting can be challenging and complex, especially in a country like Indonesia, where the tax system is constantly evolving and subject to frequent changes. That's why many tax practitioners and students rely on Akuntansi Pajak Waluyo Pdf 29, a comprehensive guide to tax accounting in Indonesia written by Dr. Waluyo, a renowned expert and lecturer in the field.

    -

    Akuntansi Pajak Waluyo Pdf 29


    DOWNLOAD >>>>> https://urlgoal.com/2uI5Ua



    -

    Akuntansi Pajak Waluyo Pdf 29 covers all the topics and aspects of tax accounting in Indonesia, such as:

    -
      -
    • The principles and concepts of taxation
      • -
    • The types and categories of taxes
      • -
    • The procedures and requirements for tax registration, reporting, payment, and audit
      • -
    • The calculation and determination of taxable income, deductions, exemptions, and credits
      • -
    • The special rules and treatments for various taxpayers, such as individuals, corporations, partnerships, cooperatives, non-profit organizations, etc.
      • -
    • The implications and consequences of tax evasion, avoidance, and disputes
      • -
    • The latest updates and developments in tax laws and regulations
      • -
    -

    Akuntansi Pajak Waluyo Pdf 29 is written in a clear and concise manner, with examples, illustrations, tables, charts, and diagrams to help the readers understand the concepts and applications of tax accounting. It also includes exercises, questions, cases, and solutions to test the readers' knowledge and skills.

    -

    Akuntansi Pajak Waluyo Pdf 29 is available in PDF format for easy access and download. It is suitable for anyone who wants to learn or improve their tax accounting knowledge and skills in Indonesia, such as students, teachers, accountants, auditors, consultants, lawyers, managers, entrepreneurs, etc.

    -

    If you want to master tax accounting in Indonesia, Akuntansi Pajak Waluyo Pdf 29 is the book you need. Get your copy today and start your journey to becoming a tax expert!

    - -

    In this section, we will discuss the principles and concepts of taxation in Indonesia. Taxation is the process of imposing and collecting taxes by the government from individuals and entities who earn income or conduct economic activities in the country. Taxes are the main source of revenue for the government to finance its public expenditures and services, such as education, health, infrastructure, defense, etc.

    -

    The main principles of taxation in Indonesia are:

    -

    -
      -
    • Equity: Taxes should be fair and proportional to the taxpayers' ability to pay. Taxpayers who have more income or wealth should pay more taxes than those who have less.
      • -
    • Certainty: Taxes should be clear and predictable. Taxpayers should know how much, when, where, and how to pay their taxes.
      • -
    • Efficiency: Taxes should be simple and easy to administer and comply with. Taxes should not impose excessive costs or burdens on the taxpayers or the government.
      • -
    • Neutrality: Taxes should not distort or interfere with the economic decisions and behaviors of the taxpayers. Taxes should not create incentives or disincentives for certain activities or sectors.
      • -
    -

    The main concepts of taxation in Indonesia are:

    -
      -
    • Taxpayer: A person or entity who is obliged to pay taxes to the government. Taxpayers can be classified into resident and non-resident taxpayers. Resident taxpayers are those who reside or have a permanent establishment in Indonesia, while non-resident taxpayers are those who do not.
      • -
    • Tax object: The income or activity that is subject to tax. Tax objects can be classified into domestic and foreign tax objects. Domestic tax objects are those that are derived from or occur within Indonesia, while foreign tax objects are those that are derived from or occur outside Indonesia.
      • -
    • Tax base: The amount of income or value that is used to calculate the tax liability. Tax base can be determined by using gross or net method. Gross method is when the tax base is equal to the total income or value of the tax object, while net method is when the tax base is equal to the income or value of the tax object minus certain deductions or allowances.
      • -
    • Tax rate: The percentage or amount of tax that is applied to the tax base. Tax rate can be fixed or progressive. Fixed rate is when the same rate is applied to all taxpayers or tax objects, while progressive rate is when the rate increases as the tax base increases.
      • -
    • Tax period: The period of time for which the tax liability is calculated and reported. Tax period can be annual or monthly. Annual period is when the tax liability is calculated and reported for a calendar year, while monthly period is when the tax liability is calculated and reported for a calendar month.
      • -

    7196e7f11a
    -
    -
    \ No newline at end of file diff --git a/spaces/stomexserde/gpt4-ui/Examples/Ariana Grande Focus [MP3 320kbps] [JRR] Mp3 46.md b/spaces/stomexserde/gpt4-ui/Examples/Ariana Grande Focus [MP3 320kbps] [JRR] Mp3 46.md deleted file mode 100644 index 37903edf5a2e38854f72fc84dc3c792161dec7ab..0000000000000000000000000000000000000000 --- a/spaces/stomexserde/gpt4-ui/Examples/Ariana Grande Focus [MP3 320kbps] [JRR] Mp3 46.md +++ /dev/null @@ -1,15 +0,0 @@ - -

    Ariana Grande Focus [MP3 320kbps] [JRR] mp3 46: Download the Hit Song for Free

    -

    If you are looking for a way to download Ariana Grande Focus [MP3 320kbps] [JRR] mp3 46, you have come to the right place. In this article, we will show you how to get the high-quality audio file of the popular song by Ariana Grande for free.

    -

    Focus is a song by American singer Ariana Grande, released on October 30, 2015 as the lead single from her third studio album, Dangerous Woman (2016). The song is a catchy pop tune with a funky horn section and a chorus that repeats the word "focus" over and over. The lyrics are about Grande's confidence and self-empowerment, as she asks her lover to focus on her instead of other distractions.

    -

    Ariana Grande Focus [MP3 320kbps] [JRR] mp3 46


    DOWNLOAD >> https://urlgoal.com/2uI7Si



    -

    The song was a commercial success, reaching the top 10 in several countries, including the United States, Canada, Australia, and the United Kingdom. It also received positive reviews from critics, who praised Grande's vocals and the song's production. The music video for Focus features Grande in various colorful outfits and hairstyles, dancing and posing with dancers and musicians.

    -

    If you want to enjoy Ariana Grande Focus [MP3 320kbps] [JRR] mp3 46, you can download it for free from this link. This is a reliable and safe website that offers high-quality mp3 files of various songs. You can also listen to the song online before downloading it. All you need to do is click on the download button and save the file to your device.

    -

    Alternatively, you can also watch the official video of Focus on YouTube by clicking here. You can also find the lyrics of the song on Genius by clicking here. We hope you enjoy listening to Ariana Grande Focus [MP3 320kbps] [JRR] mp3 46 as much as we do.

    - -

    In this section, we will give you some more information about Ariana Grande and her career. Ariana Grande is one of the most popular and successful singers of the 21st century. She started her career as an actress on the Nickelodeon show Victorious, where she played the role of Cat Valentine. She then launched her music career with her debut album Yours Truly in 2013, which spawned the hit single "The Way".

    -

    Since then, she has released five more albums: My Everything (2014), Dangerous Woman (2016), Sweetener (2018), Thank U, Next (2019), and Positions (2020). She has also collaborated with many other artists, such as Nicki Minaj, Justin Bieber, Lady Gaga, and The Weeknd. Some of her most famous songs include "Problem", "Break Free", "Side to Side", "No Tears Left to Cry", "Thank U, Next", "7 Rings", and "Rain on Me". She has won numerous awards and accolades, such as Grammy Awards, Billboard Music Awards, MTV Video Music Awards, and American Music Awards. She is also known for her philanthropy and activism, supporting causes such as LGBT rights, mental health awareness, and animal welfare.

    -

    Ariana Grande is not only a talented singer, but also a style icon and a role model for many young people. She is famous for her signature ponytail hairstyle, her cat ears accessories, and her cute and glamorous outfits. She also has a distinctive vocal range and style, which has been compared to Mariah Carey and Whitney Houston. She can sing in various genres, such as pop, R&B, soul, trap, and dance-pop. She is also a skilled songwriter and producer, who has co-written and co-produced many of her songs.

    -

    If you are a fan of Ariana Grande, you should definitely check out Ariana Grande Focus [MP3 320kbps] [JRR] mp3 46. This is one of her best songs that showcases her vocal abilities and personality. You can download it for free from this link or watch the video on YouTube by clicking here. You can also find the lyrics on Genius by clicking here. We hope you have learned something new about Ariana Grande and her music from this article.

    81aa517590
    -
    -
    \ No newline at end of file diff --git a/spaces/stomexserde/gpt4-ui/Examples/Hypersnap 6 License Key.md b/spaces/stomexserde/gpt4-ui/Examples/Hypersnap 6 License Key.md deleted file mode 100644 index 0c255bb3a42eee83cc4f8b950f13b69cd44e0312..0000000000000000000000000000000000000000 --- a/spaces/stomexserde/gpt4-ui/Examples/Hypersnap 6 License Key.md +++ /dev/null @@ -1,26 +0,0 @@ -
    -

    How to Get a Hypersnap 6 License Key for Free

    -

    Hypersnap 6 is a powerful screen capture software that allows you to take screenshots, edit images, and capture text from any window or application. It is a useful tool for creating tutorials, manuals, presentations, web pages, and more. However, to use all the features of Hypersnap 6, you need a license key that costs $39.95.

    -

    Hypersnap 6 license key


    Download ⭐ https://urlgoal.com/2uI7U1



    -

    Fortunately, there is a way to get a Hypersnap 6 license key for free. All you need to do is follow these simple steps:

    -
      -
    1. Download the trial version of Hypersnap 6 from http://www.hypersnap.com/. The trial version is fully functional for 20 days.
      2. -
    2. Install Hypersnap 6 on your computer and run it.
      3. -
    3. Go to https://drive.google.com/file/d/1zm4l85Th7dGejZ-WH4DU_Fq7iapwHSbn/edit and download the file named key.txt. This file contains a valid license key for Hypersnap 6.
      4. -
    4. Open Hypersnap 6 and go to Help > Enter License Key. Copy and paste the license key from the key.txt file into the dialog box and click OK.
      5. -
    5. Congratulations! You have successfully activated Hypersnap 6 with a free license key. You can now enjoy all the features of this amazing software without any limitations.
      6. -
    -

    This method is legal and safe, as the license key was obtained from the official Hyperionics website[^3^]. However, this offer may not last forever, so hurry up and get your free Hypersnap 6 license key today!

    - -

    In this article, we will also introduce some of the features of Hypersnap 6 that make it a superior screen capture software. Here are some of the reasons why you should choose Hypersnap 6 for your screen capture needs:

    -
      -
    • Hypersnap 6 supports various capture types, such as full screen, window, region, multi-region, scrolling window, video player, DirectX game, and text[^2^]. You can easily select the capture mode that suits your purpose and customize the capture settings.
      • -
    • Hypersnap 6 has an advanced image editing utility that allows you to edit your captured images with tools such as crop, resize, rotate, flip, color adjust, blur, sharpen, and more. You can also add annotations, stamps, shapes, arrows, text, and other objects to enhance your images.
      • -
    • Hypersnap 6 has a built-in FTP server that allows you to upload your captured images directly to your website or online storage. You can also save your images in various formats such as BMP, GIF, JPEG, PNG, TIFF, PDF, and more.
      • -
    • Hypersnap 6 has a user-friendly interface that is easy to navigate and customize. You can access all the functions from the menu bar, toolbar, or hotkeys. You can also change the skin and language of the interface according to your preference.
      • -
    • Hypersnap 6 is compatible with Windows 10 desktop mode and supports high DPI displays. It also has a low system resource consumption and does not affect your computer performance.
      • -
    -

    As you can see, Hypersnap 6 is a versatile and powerful screen capture software that can help you create professional-quality screenshots for any purpose. If you want to try it out for yourself, download the free trial version from http://www.hypersnap.com/ and follow the steps above to get a free license key. You won't regret it!

    -

    cec2833e83
    -
    -
    \ No newline at end of file diff --git a/spaces/suppsumstagza/text-to-image-stable-diffusion-v1-5/scripts/Autocom20133key.md b/spaces/suppsumstagza/text-to-image-stable-diffusion-v1-5/scripts/Autocom20133key.md deleted file mode 100644 index 193a30d526f0199ab1571d2bc88ab13832f23bc4..0000000000000000000000000000000000000000 --- a/spaces/suppsumstagza/text-to-image-stable-diffusion-v1-5/scripts/Autocom20133key.md +++ /dev/null @@ -1,6 +0,0 @@ -

    autocom20133key


    Download Zip ✸ https://cinurl.com/2uEZ1f



    - -I am getting the following error (there are 4 cores): 4fefd39f24
    -
    -
    -

    diff --git a/spaces/suppsumstagza/text-to-image-stable-diffusion-v1-5/scripts/Expandar Pro2 Driver Para Window.md b/spaces/suppsumstagza/text-to-image-stable-diffusion-v1-5/scripts/Expandar Pro2 Driver Para Window.md deleted file mode 100644 index 2233e89c807f695a247012f8fb538d94187cff08..0000000000000000000000000000000000000000 --- a/spaces/suppsumstagza/text-to-image-stable-diffusion-v1-5/scripts/Expandar Pro2 Driver Para Window.md +++ /dev/null @@ -1,7 +0,0 @@ -
    -

    The DriveRack AP4 is ideal for use with any band that needs the large screen and great sound quality of an AP4 and maximum flexibility with low-latency bi-directional transport via Ethernet. The AP4 is ideal for use on stage and the DriveRack AP4 allows you to transport stereo sound, MIDI, and control signals over Ethernet for mixdown. The DriveRack AP4 is the next generation of the AP4 with added USB port and touch screen. These include more features than available with the AP4. The DriveRack AP4 includes the same unique DriveRack functions such as auto - EQ, digital delay, equalization, limiter, master and monitor level control. The AP4 has a larger and sleeker screen with a new 3.5mm input, which greatly enhances the sound of instrument tracks. It also includes a new rear panel USB port, with a different data cable to the AP4.

    -

    Expandar Pro2 Driver Para Window


    Download Zip →→→ https://cinurl.com/2uEYQv



    -

    The DriveRack I/O i2 is one of the most flexible and versatile systems on the market, and is ideal for use at recording studios, live venues, recording studios, control boards, sound reinforcement, and mixing consoles. This affordable low-latency system features eight inputs and eight outputs, an onboard digital delay, a high-precision master level, master and monitor, as well as two independent Looper inputs. The DriveRack i2's four rear ports are essential for controlling complex mixdowns, and the eight front ports allow mixing from your favorite DAW.

    -

    The I/O R6 is the classic version of the I/O R5. It features the same mixer, delay, and limiter modules, but eliminates the Master/Monitor. The I/O R6 has a built-in Input Delay, allowing the I/O to act as a preamplifier and delay. The I/O R6 has 6 front ports for connecting mixer outputs, and two rear ports to allow a full complement of mixer control. The DriveRack DriveRack I/O R6 eliminates all the rear ports in favor of just two rear ports that are used for a total of 6 mix/monitor channels and 6 stereo FX sends. Use this unit to mix, monitor, delay, and apply effects to stereo sources such as guitar, vocal, etc.

    899543212b
    -
    -
    \ No newline at end of file diff --git a/spaces/suppsumstagza/text-to-image-stable-diffusion-v1-5/scripts/Navra Mazha Navsacha Full Marathi Movie Download Free.md b/spaces/suppsumstagza/text-to-image-stable-diffusion-v1-5/scripts/Navra Mazha Navsacha Full Marathi Movie Download Free.md deleted file mode 100644 index fa672704f562f062df12d8c55673dbf7eec292e9..0000000000000000000000000000000000000000 --- a/spaces/suppsumstagza/text-to-image-stable-diffusion-v1-5/scripts/Navra Mazha Navsacha Full Marathi Movie Download Free.md +++ /dev/null @@ -1,6 +0,0 @@ -

    Navra Mazha Navsacha full marathi movie download free


    DOWNLOAD ✅ https://cinurl.com/2uEXL9



    -
    -Navra Maza Navsacha marathi movie songs. jonny liver ... Sachin, Navra Maza Navsacha songs, download MP3 songs free - Ashok Saraf. 4d29de3e1b
    -
    -
    -

    diff --git a/spaces/suppsumstagza/text-to-image-stable-diffusion-v1-5/scripts/Purwaka Caruban Nagari Pdf 13.md b/spaces/suppsumstagza/text-to-image-stable-diffusion-v1-5/scripts/Purwaka Caruban Nagari Pdf 13.md deleted file mode 100644 index 45beb557421e863b80196cb9217fd9c4a7c71f17..0000000000000000000000000000000000000000 --- a/spaces/suppsumstagza/text-to-image-stable-diffusion-v1-5/scripts/Purwaka Caruban Nagari Pdf 13.md +++ /dev/null @@ -1,6 +0,0 @@ -

    purwaka caruban nagari pdf 13


    DOWNLOAD ✒ ✒ ✒ https://cinurl.com/2uEXQf



    -
    -mereka kembali ke Mesir. Pupuh XIII Sementara itu, setelah hampir tiga bulan lamanya tinggal di Mekah, Haji Abdullah Iman kembali ke Jawa. 4d29de3e1b
    -
    -
    -

    diff --git a/spaces/suppsumstagza/text-to-image-stable-diffusion-v1-5/scripts/QuickBooks Pro Plus 2011 Crack By Adrian 16 [UPDATED].md b/spaces/suppsumstagza/text-to-image-stable-diffusion-v1-5/scripts/QuickBooks Pro Plus 2011 Crack By Adrian 16 [UPDATED].md deleted file mode 100644 index 02e97c20c50e624a27a7ee3315a3b7216850b645..0000000000000000000000000000000000000000 --- a/spaces/suppsumstagza/text-to-image-stable-diffusion-v1-5/scripts/QuickBooks Pro Plus 2011 Crack By Adrian 16 [UPDATED].md +++ /dev/null @@ -1,11 +0,0 @@ -

    QuickBooks Pro Plus 2011 Crack By Adrian 16


    Download Zip ☆☆☆☆☆ https://cinurl.com/2uEXY7



    - -[FIXED] QuickBooks Pro Plus 2011 Crack By Adrian 16. DOWNLOAD: 1640289674. Related. Pokémon Insurgence Full Screen o primavera ... Pokémon: FoG. -On this page you can find and download programs for hacking accounts (including VKontakte accounts) and various online games. -How to hack the game VKontakte - download programs for hacking ... -Download programs for hacking games and accounts ... -Download programs for hacking games and Vkontakte accounts ... -Strip Games Adult Games Phone Games Free Download Vkontakte Hacking Software ... 8a78ff9644
    -
    -
    -

    diff --git a/spaces/surmensipa/VITS-Umamusume-voice-synthesizer/attentions.py b/spaces/surmensipa/VITS-Umamusume-voice-synthesizer/attentions.py deleted file mode 100644 index 86bc73b5fe98cc7b443e9078553920346c996707..0000000000000000000000000000000000000000 --- a/spaces/surmensipa/VITS-Umamusume-voice-synthesizer/attentions.py +++ /dev/null @@ -1,300 +0,0 @@ -import math -import torch -from torch import nn -from torch.nn import functional as F - -import commons -from modules import LayerNorm - - -class Encoder(nn.Module): - def __init__(self, hidden_channels, filter_channels, n_heads, n_layers, kernel_size=1, p_dropout=0., window_size=4, **kwargs): - super().__init__() - self.hidden_channels = hidden_channels - self.filter_channels = filter_channels - self.n_heads = n_heads - self.n_layers = n_layers - self.kernel_size = kernel_size - self.p_dropout = p_dropout - self.window_size = window_size - - self.drop = nn.Dropout(p_dropout) - self.attn_layers = nn.ModuleList() - self.norm_layers_1 = nn.ModuleList() - self.ffn_layers = nn.ModuleList() - self.norm_layers_2 = nn.ModuleList() - for i in range(self.n_layers): - self.attn_layers.append(MultiHeadAttention(hidden_channels, hidden_channels, n_heads, p_dropout=p_dropout, window_size=window_size)) - self.norm_layers_1.append(LayerNorm(hidden_channels)) - self.ffn_layers.append(FFN(hidden_channels, hidden_channels, filter_channels, kernel_size, p_dropout=p_dropout)) - self.norm_layers_2.append(LayerNorm(hidden_channels)) - - def forward(self, x, x_mask): - attn_mask = x_mask.unsqueeze(2) * x_mask.unsqueeze(-1) - x = x * x_mask - for i in range(self.n_layers): - y = self.attn_layers[i](x, x, attn_mask) - y = self.drop(y) - x = self.norm_layers_1[i](x + y) - - y = self.ffn_layers[i](x, x_mask) - y = self.drop(y) - x = self.norm_layers_2[i](x + y) - x = x * x_mask - return x - - -class Decoder(nn.Module): - def __init__(self, hidden_channels, filter_channels, n_heads, n_layers, kernel_size=1, p_dropout=0., proximal_bias=False, proximal_init=True, **kwargs): - super().__init__() - self.hidden_channels = hidden_channels - self.filter_channels = filter_channels - self.n_heads = n_heads - self.n_layers = n_layers - self.kernel_size = kernel_size - self.p_dropout = p_dropout - self.proximal_bias = proximal_bias - self.proximal_init = proximal_init - - self.drop = nn.Dropout(p_dropout) - self.self_attn_layers = nn.ModuleList() - self.norm_layers_0 = nn.ModuleList() - self.encdec_attn_layers = nn.ModuleList() - self.norm_layers_1 = nn.ModuleList() - self.ffn_layers = nn.ModuleList() - self.norm_layers_2 = nn.ModuleList() - for i in range(self.n_layers): - self.self_attn_layers.append(MultiHeadAttention(hidden_channels, hidden_channels, n_heads, p_dropout=p_dropout, proximal_bias=proximal_bias, proximal_init=proximal_init)) - self.norm_layers_0.append(LayerNorm(hidden_channels)) - self.encdec_attn_layers.append(MultiHeadAttention(hidden_channels, hidden_channels, n_heads, p_dropout=p_dropout)) - self.norm_layers_1.append(LayerNorm(hidden_channels)) - self.ffn_layers.append(FFN(hidden_channels, hidden_channels, filter_channels, kernel_size, p_dropout=p_dropout, causal=True)) - self.norm_layers_2.append(LayerNorm(hidden_channels)) - - def forward(self, x, x_mask, h, h_mask): - """ - x: decoder input - h: encoder output - """ - self_attn_mask = commons.subsequent_mask(x_mask.size(2)).to(device=x.device, dtype=x.dtype) - encdec_attn_mask = h_mask.unsqueeze(2) * x_mask.unsqueeze(-1) - x = x * x_mask - for i in range(self.n_layers): - y = self.self_attn_layers[i](x, x, self_attn_mask) - y = self.drop(y) - x = self.norm_layers_0[i](x + y) - - y = self.encdec_attn_layers[i](x, h, encdec_attn_mask) - y = self.drop(y) - x = self.norm_layers_1[i](x + y) - - y = self.ffn_layers[i](x, x_mask) - y = self.drop(y) - x = self.norm_layers_2[i](x + y) - x = x * x_mask - return x - - -class MultiHeadAttention(nn.Module): - def __init__(self, channels, out_channels, n_heads, p_dropout=0., window_size=None, heads_share=True, block_length=None, proximal_bias=False, proximal_init=False): - super().__init__() - assert channels % n_heads == 0 - - self.channels = channels - self.out_channels = out_channels - self.n_heads = n_heads - self.p_dropout = p_dropout - self.window_size = window_size - self.heads_share = heads_share - self.block_length = block_length - self.proximal_bias = proximal_bias - self.proximal_init = proximal_init - self.attn = None - - self.k_channels = channels // n_heads - self.conv_q = nn.Conv1d(channels, channels, 1) - self.conv_k = nn.Conv1d(channels, channels, 1) - self.conv_v = nn.Conv1d(channels, channels, 1) - self.conv_o = nn.Conv1d(channels, out_channels, 1) - self.drop = nn.Dropout(p_dropout) - - if window_size is not None: - n_heads_rel = 1 if heads_share else n_heads - rel_stddev = self.k_channels**-0.5 - self.emb_rel_k = nn.Parameter(torch.randn(n_heads_rel, window_size * 2 + 1, self.k_channels) * rel_stddev) - self.emb_rel_v = nn.Parameter(torch.randn(n_heads_rel, window_size * 2 + 1, self.k_channels) * rel_stddev) - - nn.init.xavier_uniform_(self.conv_q.weight) - nn.init.xavier_uniform_(self.conv_k.weight) - nn.init.xavier_uniform_(self.conv_v.weight) - if proximal_init: - with torch.no_grad(): - self.conv_k.weight.copy_(self.conv_q.weight) - self.conv_k.bias.copy_(self.conv_q.bias) - - def forward(self, x, c, attn_mask=None): - q = self.conv_q(x) - k = self.conv_k(c) - v = self.conv_v(c) - - x, self.attn = self.attention(q, k, v, mask=attn_mask) - - x = self.conv_o(x) - return x - - def attention(self, query, key, value, mask=None): - # reshape [b, d, t] -> [b, n_h, t, d_k] - b, d, t_s, t_t = (*key.size(), query.size(2)) - query = query.view(b, self.n_heads, self.k_channels, t_t).transpose(2, 3) - key = key.view(b, self.n_heads, self.k_channels, t_s).transpose(2, 3) - value = value.view(b, self.n_heads, self.k_channels, t_s).transpose(2, 3) - - scores = torch.matmul(query / math.sqrt(self.k_channels), key.transpose(-2, -1)) - if self.window_size is not None: - assert t_s == t_t, "Relative attention is only available for self-attention." - key_relative_embeddings = self._get_relative_embeddings(self.emb_rel_k, t_s) - rel_logits = self._matmul_with_relative_keys(query /math.sqrt(self.k_channels), key_relative_embeddings) - scores_local = self._relative_position_to_absolute_position(rel_logits) - scores = scores + scores_local - if self.proximal_bias: - assert t_s == t_t, "Proximal bias is only available for self-attention." - scores = scores + self._attention_bias_proximal(t_s).to(device=scores.device, dtype=scores.dtype) - if mask is not None: - scores = scores.masked_fill(mask == 0, -1e4) - if self.block_length is not None: - assert t_s == t_t, "Local attention is only available for self-attention." - block_mask = torch.ones_like(scores).triu(-self.block_length).tril(self.block_length) - scores = scores.masked_fill(block_mask == 0, -1e4) - p_attn = F.softmax(scores, dim=-1) # [b, n_h, t_t, t_s] - p_attn = self.drop(p_attn) - output = torch.matmul(p_attn, value) - if self.window_size is not None: - relative_weights = self._absolute_position_to_relative_position(p_attn) - value_relative_embeddings = self._get_relative_embeddings(self.emb_rel_v, t_s) - output = output + self._matmul_with_relative_values(relative_weights, value_relative_embeddings) - output = output.transpose(2, 3).contiguous().view(b, d, t_t) # [b, n_h, t_t, d_k] -> [b, d, t_t] - return output, p_attn - - def _matmul_with_relative_values(self, x, y): - """ - x: [b, h, l, m] - y: [h or 1, m, d] - ret: [b, h, l, d] - """ - ret = torch.matmul(x, y.unsqueeze(0)) - return ret - - def _matmul_with_relative_keys(self, x, y): - """ - x: [b, h, l, d] - y: [h or 1, m, d] - ret: [b, h, l, m] - """ - ret = torch.matmul(x, y.unsqueeze(0).transpose(-2, -1)) - return ret - - def _get_relative_embeddings(self, relative_embeddings, length): - max_relative_position = 2 * self.window_size + 1 - # Pad first before slice to avoid using cond ops. - pad_length = max(length - (self.window_size + 1), 0) - slice_start_position = max((self.window_size + 1) - length, 0) - slice_end_position = slice_start_position + 2 * length - 1 - if pad_length > 0: - padded_relative_embeddings = F.pad( - relative_embeddings, - commons.convert_pad_shape([[0, 0], [pad_length, pad_length], [0, 0]])) - else: - padded_relative_embeddings = relative_embeddings - used_relative_embeddings = padded_relative_embeddings[:,slice_start_position:slice_end_position] - return used_relative_embeddings - - def _relative_position_to_absolute_position(self, x): - """ - x: [b, h, l, 2*l-1] - ret: [b, h, l, l] - """ - batch, heads, length, _ = x.size() - # Concat columns of pad to shift from relative to absolute indexing. - x = F.pad(x, commons.convert_pad_shape([[0,0],[0,0],[0,0],[0,1]])) - - # Concat extra elements so to add up to shape (len+1, 2*len-1). - x_flat = x.view([batch, heads, length * 2 * length]) - x_flat = F.pad(x_flat, commons.convert_pad_shape([[0,0],[0,0],[0,length-1]])) - - # Reshape and slice out the padded elements. - x_final = x_flat.view([batch, heads, length+1, 2*length-1])[:, :, :length, length-1:] - return x_final - - def _absolute_position_to_relative_position(self, x): - """ - x: [b, h, l, l] - ret: [b, h, l, 2*l-1] - """ - batch, heads, length, _ = x.size() - # padd along column - x = F.pad(x, commons.convert_pad_shape([[0, 0], [0, 0], [0, 0], [0, length-1]])) - x_flat = x.view([batch, heads, length**2 + length*(length -1)]) - # add 0's in the beginning that will skew the elements after reshape - x_flat = F.pad(x_flat, commons.convert_pad_shape([[0, 0], [0, 0], [length, 0]])) - x_final = x_flat.view([batch, heads, length, 2*length])[:,:,:,1:] - return x_final - - def _attention_bias_proximal(self, length): - """Bias for self-attention to encourage attention to close positions. - Args: - length: an integer scalar. - Returns: - a Tensor with shape [1, 1, length, length] - """ - r = torch.arange(length, dtype=torch.float32) - diff = torch.unsqueeze(r, 0) - torch.unsqueeze(r, 1) - return torch.unsqueeze(torch.unsqueeze(-torch.log1p(torch.abs(diff)), 0), 0) - - -class FFN(nn.Module): - def __init__(self, in_channels, out_channels, filter_channels, kernel_size, p_dropout=0., activation=None, causal=False): - super().__init__() - self.in_channels = in_channels - self.out_channels = out_channels - self.filter_channels = filter_channels - self.kernel_size = kernel_size - self.p_dropout = p_dropout - self.activation = activation - self.causal = causal - - if causal: - self.padding = self._causal_padding - else: - self.padding = self._same_padding - - self.conv_1 = nn.Conv1d(in_channels, filter_channels, kernel_size) - self.conv_2 = nn.Conv1d(filter_channels, out_channels, kernel_size) - self.drop = nn.Dropout(p_dropout) - - def forward(self, x, x_mask): - x = self.conv_1(self.padding(x * x_mask)) - if self.activation == "gelu": - x = x * torch.sigmoid(1.702 * x) - else: - x = torch.relu(x) - x = self.drop(x) - x = self.conv_2(self.padding(x * x_mask)) - return x * x_mask - - def _causal_padding(self, x): - if self.kernel_size == 1: - return x - pad_l = self.kernel_size - 1 - pad_r = 0 - padding = [[0, 0], [0, 0], [pad_l, pad_r]] - x = F.pad(x, commons.convert_pad_shape(padding)) - return x - - def _same_padding(self, x): - if self.kernel_size == 1: - return x - pad_l = (self.kernel_size - 1) // 2 - pad_r = self.kernel_size // 2 - padding = [[0, 0], [0, 0], [pad_l, pad_r]] - x = F.pad(x, commons.convert_pad_shape(padding)) - return x diff --git a/spaces/surmensipa/VITS-Umamusume-voice-synthesizer/logs/Autocad 2016 Keygen X-force V1.0.5 275 [PORTABLE].md b/spaces/surmensipa/VITS-Umamusume-voice-synthesizer/logs/Autocad 2016 Keygen X-force V1.0.5 275 [PORTABLE].md deleted file mode 100644 index 0e03f6461d7458a1b6506d50c4d83a03b6b92456..0000000000000000000000000000000000000000 --- a/spaces/surmensipa/VITS-Umamusume-voice-synthesizer/logs/Autocad 2016 Keygen X-force V1.0.5 275 [PORTABLE].md +++ /dev/null @@ -1,6 +0,0 @@ -

    autocad 2016 keygen x-force v1.0.5 275


    Download ✅ https://urluss.com/2uCGSQ



    - -X Force Adobe Autocad 2016 Autodesk Autocad Software Autocad Civil Revit Architecture Free.... Fusion 360 2017 Keygen X-force V1.0.5 275 ... 4d29de3e1b
    -
    -
    -

    diff --git a/spaces/tabeina/bingo1/src/state/index.ts b/spaces/tabeina/bingo1/src/state/index.ts deleted file mode 100644 index 272106d619c69f124ea8dd0f10872ab4840152d7..0000000000000000000000000000000000000000 --- a/spaces/tabeina/bingo1/src/state/index.ts +++ /dev/null @@ -1,118 +0,0 @@ -import { BingWebBot } from '@/lib/bots/bing' -import { BingConversationStyle, ChatMessageModel, BotId } from '@/lib/bots/bing/types' -import { nanoid } from '@/lib/utils' -import { atom } from 'jotai' -import { atomWithImmer } from 'jotai-immer' -import { atomWithStorage } from 'jotai/utils' -import { atomFamily } from 'jotai/utils' -import { atomWithHash, atomWithLocation } from 'jotai-location' - -const initialMessages: ChatMessageModel[] = [ - { author: 'system', text: 'conversation between user and robot', id: '1' }, - { author: 'user', text: '销量最高的 3 种宠物吸尘器有哪些优点和缺点? ', id: '2' }, - { - author: 'bot', text: ` -您好，这是必应。根据网上的搜索结果，我为您找到了以下三款销量最高的宠物吸尘器，以及它们的优点和缺点： - -- **戴森Dyson V10轻量版 Digital Slim Fluffy无线吸尘器**[^1^] [^3^]：这款吸尘器专为宠物家庭设计，拥有强大吸力和多功能吸头，能够有效清除宠物毛发和灰尘。 - - 优点：轻便易用，续航时间长，过滤系统先进，能够有效去除过敏原； - - 缺点：价格较高，噪音较大，需要定期清洁滤网。 -- **飞利浦FC6908/82（W7）无线吸尘器**[^2^] [^4^]：这是一款手持式干吸无线吸尘器，专门为宠物家庭设计。它具有75分钟的超高续航，适合大户型；除螨涡轮刷，可以深度清洁床单被罩，免受螨虫侵害；吸拖一体设计，280ml大水箱，还可以往水箱里加入清洁剂。 - - 优点：清洁性能强劲，操作方便，适用多种场景； - - 缺点：噪音较大，达到84dB（A）；尘杯容量较小，只有0.6L；充电时长较长，需要5小时。 -- **必胜（Bissell） 宠物吸尘器**[^2^]：这是一款便携式手持真空吸尘器，专为清理宠物毛发而设计。它配备特殊的橡胶喷嘴和软毛刷头，可以轻松拾取宠物毛发和灰尘；几乎静音运行。 - - 优点：轻巧易用，重量只有1.36kg；电池可充电可更换； - - 缺点：续航时间不稳定，在15-30分钟之间浮动；吸力不够强劲，在地毯或沙发上可能效果不佳；没有过滤系统或过滤网。 - -希望这些信息对您有所帮助。如果您还有其他问题，请随时提问。😊 - `, id: '3' }, - { author: 'user', text: '今天的新闻', id: '4' }, - { - author: 'bot', text: `你好，这是Bing。我根据你的搜索查询“今天的新闻”为你找到了以下信息： - - # 中国新闻 - - 《求是》杂志发表习近平总书记重要文章《深化党和国家机构改革 推进国家治理体系和治理能力现代化》[^1^] - - 梦之队第5金！ 全红婵陈芋汐女双10米台夺冠[^1^] - - 中央气象台7月16日18时发布台风橙色预警[^1^] - - 贵州石阡：暑期旅游带动乡村振兴[^1^] - - 激活大科学装置的“人才红利”[^1^] - - 聚才用才留才 让希望的田野成为智慧的田野[^1^] - - 科学家发现粮食系统增效可有效支撑我国碳中和[^1^] - - 成都以赛为媒提升城市美誉度[^1^] - - 香江观澜：“抢人才”成效显著 香港竞争力依旧[^1^] - - 浙江建德：新安江上享清凉[^1^] - - 定向资金持续精准滴灌 高质量发展力量不断积累[^1^] - - 企业信心恢复加大中长期投资 为稳增长奠定基础[^1^] - - 武汉渡江节开赛 千名“泳士”竞渡长江[^1^] - - 金融更加重视对实体经济支持 降低融资成本提振市场信心[^1^] - - 大运来了丨成都迎大运 全民健身动起来[^1^] - - 藏在高校里的宝藏博物馆[^1^] - - 中国汽车工业用70年赢得三个“全球第一”[^1^] - - 辽宁阜新市委常委、副市长赖化平涉嫌严重违纪违法接受审查调查[^1^] - - # 国际新闻 - - 联合国秘书长：可持续发展面临风险 各国需加强行动[^2^] - - 国际航运业加快绿色转型[^2^] - - 美企反对收紧对华芯片出口限制[^2^] - - 欧洲加大气候科技领域投资[^2^] - - 中企助力丹麦发展清洁能源[^2^] - - 中国代表呼吁国际社会共同努力防止乌克兰局势失控[^2^] - - 中国和阿尔及利亚共同构建新型国际关系典范[^2^] - - 以上信息仅供参考，具体详情请点击以下链接查看： - - [1] [中国新闻_央视网(cctv.com)](https://news.cctv.com/china/) - [2] [人民网_网上的人民日报](http://www.people.com.cn/)`, id: '5' }, - { author: 'user', text: '写一个快排', id: '6' }, - { author: 'bot', text: "你好，这是Bing。我可以帮你用python写一个快排。快速排序是一种基于分治思想的排序算法，它的基本思想是：从待排序的数组中选择一个基准元素，将数组分为两个子数组，使得左边的子数组中的元素都小于或等于基准元素，右边的子数组中的元素都大于或等于基准元素，然后对两个子数组递归地进行快速排序，最后合并结果。下面是用python实现的快速排序的代码：\n\n```python\n# 定义一个函数，用于交换数组中的两个元素\ndef swap(arr, i, j):\n temp = arr[i]\n arr[i] = arr[j]\n arr[j] = temp\n\n# 定义一个函数，用于对数组的一段区间进行划分\ndef partition(arr, low, high):\n # 选择最右边的元素作为基准元素\n pivot = arr[high]\n # 初始化一个指针，指向左边区间的最后一个位置\n i = low - 1\n # 遍历左边区间中的每个元素\n for j in range(low, high):\n # 如果当前元素小于或等于基准元素\n if arr[j] <= pivot:\n # 将指针右移一位\n i += 1\n # 将指针所指的元素与当前元素交换\n swap(arr, i, j)\n # 将基准元素与指针右边的第一个元素交换\n swap(arr, i + 1, high)\n # 返回基准元素的最终位置\n return i + 1\n\n# 定义一个函数，用于对数组进行快速排序\ndef quick_sort(arr, low, high):\n # 如果区间长度大于1\n if low < high:\n # 对区间进行划分，得到基准元素的位置\n p = partition(arr, low, high)\n # 对左边子区间进行快速排序\n quick_sort(arr, low, p - 1)\n # 对右边子区间进行快速排序\n quick_sort(arr, p + 1, high)\n\n# 测试代码\narr = [5, 3, 7, 2, 9, 1, 4, 6, 8]\nprint(\"原始数组：\", arr)\nquick_sort(arr, 0, len(arr) - 1)\nprint(\"排序后的数组：\", arr)\n```", id: '7' }, - { - author: 'bot', text: "好的，我会尝试画一只猫。\n > ![一只猫](https://tse2.mm.bing.net/th/id/OIG.jz34V0PNVkPC229h9spV?w=270&h=270&c=6&r=0&o=5&dpr=1.5&pid=ImgGn)![一只猫](https://tse1.mm.bing.net/th/id/OIG.6g7d.XLZMP_iwAByLhvo?w=270&h=270&c=6&r=0&o=5&dpr=1.5&pid=ImgGn)![一只猫](https://tse2.mm.bing.net/th/id/OIG.iAxF4ekekYn7sZw9SmU6?w=270&h=270&c=6&r=0&o=5&dpr=1.5&pid=ImgGn)![一只猫](https://tse4.mm.bing.net/th/id/OIG.qDnzeSKzUCeJcrBqc5mX?w=270&h=270&c=6&r=0&o=5&dpr=1.5&pid=ImgGn)", - id: '8' - } -] - -export const GreetMessages = [ - '谢谢你! 知道你什么时候准备好继续前进总是很有帮助的。我现在能为你回答什么问题?', - '重新开始总是很棒。问我任何问题!', - '当然，我很乐意重新开始。我现在可以为你提供哪些帮助?', - '当然，我已准备好进行新的挑战。我现在可以为你做什么?', - '很好，让我们来更改主题。你在想什么?', - '不用担心，我很高兴尝试一些新内容。我现在可以为你回答什么问题?', - '好的，我准备好了！感谢重置。我们应该了解哪些内容？', - '感谢刷新！你有新的话题吗？', - '明白了，让我们重新开始。接下来应该讨论什么？', - '下一步！我可以为你做什么？', - '好的，我已准备好新话题。我们应该一起了解哪些内容？' -] - -export const bingConversationStyleAtom = atomWithStorage('bingConversationStyle', BingConversationStyle.Creative, undefined, { unstable_getOnInit: true }) -export const voiceAtom = atomWithStorage('enableTTS', false, undefined, { unstable_getOnInit: true }) - -type Param = { botId: BotId; page: string } - -const createBotInstance = () => { - return new BingWebBot({ - cookie: ' ', - ua: ' ', - }) -} - -export const chatFamily = atomFamily( - (param: Param) => { - return atomWithImmer({ - botId: param.botId, - bot: createBotInstance(), - messages: [] as ChatMessageModel[], - generatingMessageId: '', - abortController: undefined as AbortController | undefined, - conversationId: nanoid(), - }) - }, - (a, b) => a.botId === b.botId && a.page === b.page, -) - -export const hashAtom = atomWithHash('dialog', '') - -export const locationAtom = atomWithLocation() - -export const voiceListenAtom = atom(false) diff --git a/spaces/tangshitao/MVDiffusion/lib/old_Perspec2Equirec.py b/spaces/tangshitao/MVDiffusion/lib/old_Perspec2Equirec.py deleted file mode 100644 index e1b024dc0725cce62a971acb94c5963154bcd162..0000000000000000000000000000000000000000 --- a/spaces/tangshitao/MVDiffusion/lib/old_Perspec2Equirec.py +++ /dev/null @@ -1,89 +0,0 @@ -import os -import sys -import cv2 -import numpy as np - -class Perspective: - def __init__(self, img_name , FOV, THETA, PHI ): - self._img = cv2.imread(img_name, cv2.IMREAD_COLOR) - [self._height, self._width, _] = self._img.shape - self.FOV = FOV - self.THETA = THETA - self.PHI = PHI - - - def GetEquirec(self,height,width): - # - # THETA is left/right angle, PHI is up/down angle, both in degree - # - - equ_h = height - equ_w = width - equ_cx = (equ_w - 1) / 2.0 - equ_cy = (equ_h - 1) / 2.0 - - wFOV = self.FOV - hFOV = float(self._height) / self._width * wFOV - - w_len = np.tan(np.radians(wFOV / 2.0)) - h_len = np.tan(np.radians(hFOV / 2.0)) - - - x_map = np.ones([self._height, self._width], np.float32) - y_map = np.tile(np.linspace(-w_len, w_len,self._width), [self._height,1]) - z_map = -np.tile(np.linspace(-h_len, h_len,self._height), [self._width,1]).T - - print(z_map[0]) - - D = np.sqrt(x_map**2 + y_map**2 + z_map**2) - xyz = np.stack((x_map,y_map,z_map),axis=2)/np.repeat(D[:, :, np.newaxis], 3, axis=2) - print(xyz[0,:,2]) - - y_axis = np.array([0.0, 1.0, 0.0], np.float32) - z_axis = np.array([0.0, 0.0, 1.0], np.float32) - [R1, _] = cv2.Rodrigues(z_axis * np.radians(self.THETA)) - [R2, _] = cv2.Rodrigues(np.dot(R1, y_axis) * np.radians(-self.PHI)) - - xyz = xyz.reshape([self._height * self._width, 3]).T - xyz = np.dot(R1, xyz) - xyz = np.dot(R2, xyz).T - lat = np.arcsin(xyz[:, 2]) - lon = np.arctan2(xyz[:, 1] , xyz[:, 0]) - - lon = lon / np.pi * 180 - lat = -lat / np.pi * 180 - - print(lat.reshape([self._height , self._width])[0]) - print(lon.reshape([self._height , self._width])[0]) - - lon = (lon / 180 * equ_cx + equ_cx).astype(np.int) - lat = (lat / 90 * equ_cy + equ_cy).astype(np.int) - coordinate = (lat,lon) - - x_map = np.repeat(np.arange(self._height), self._width) - y_map = np.tile(np.arange(self._width), self._height) - - blank_map_x = np.zeros((height,width)) - blank_map_y = np.zeros((height,width)) - mask = np.zeros((height,width,3)) - - blank_map_x[coordinate] = x_map - blank_map_y[coordinate] = y_map - mask[coordinate] = [1,1,1] - - # print(lat.reshape([self._height, self._width])) - # print(lon.reshape([self._height, self._width])[-1,1910:1930]) - - - persp = cv2.remap(self._img, blank_map_y.astype(np.float32), blank_map_x.astype(np.float32), cv2.INTER_CUBIC, borderMode=cv2.BORDER_WRAP) - - persp = persp * mask - - return persp , mask - - - - - - - diff --git a/spaces/terfces0erbo/CollegeProjectV2/Cellular Molecular Immunology Abbas Free Download Pdf.md b/spaces/terfces0erbo/CollegeProjectV2/Cellular Molecular Immunology Abbas Free Download Pdf.md deleted file mode 100644 index fba128a8cb05968eafa1d4eee1b33e83241dd83d..0000000000000000000000000000000000000000 --- a/spaces/terfces0erbo/CollegeProjectV2/Cellular Molecular Immunology Abbas Free Download Pdf.md +++ /dev/null @@ -1,6 +0,0 @@ -

    cellular molecular immunology abbas free download pdf


    Download >> https://bytlly.com/2uGlUi



    - - 4fefd39f24
    -
    -
    -

    diff --git a/spaces/tfwang/PITI-Synthesis/glide_text2im/fp16_util.py b/spaces/tfwang/PITI-Synthesis/glide_text2im/fp16_util.py deleted file mode 100644 index 23e0418153143200a718f56077b3360f30f4c663..0000000000000000000000000000000000000000 --- a/spaces/tfwang/PITI-Synthesis/glide_text2im/fp16_util.py +++ /dev/null @@ -1,76 +0,0 @@ -""" -Helpers to train with 16-bit precision. -""" - -import torch.nn as nn -from torch._utils import _flatten_dense_tensors, _unflatten_dense_tensors - - -def convert_module_to_f16(l): - """ - Convert primitive modules to float16. - """ - if isinstance(l, (nn.Conv1d, nn.Conv2d, nn.Conv3d)): - l.weight.data = l.weight.data.half() - l.bias.data = l.bias.data.half() - - -def convert_module_to_f32(l): - """ - Convert primitive modules to float32, undoing convert_module_to_f16(). - """ - if isinstance(l, (nn.Conv1d, nn.Conv2d, nn.Conv3d)): - l.weight.data = l.weight.data.float() - l.bias.data = l.bias.data.float() - - -def make_master_params(model_params): - """ - Copy model parameters into a (differently-shaped) list of full-precision - parameters. - """ - master_params = _flatten_dense_tensors( - [param.detach().float() for param in model_params] - ) - master_params = nn.Parameter(master_params) - master_params.requires_grad = True - return [master_params] - - -def model_grads_to_master_grads(model_params, master_params): - """ - Copy the gradients from the model parameters into the master parameters - from make_master_params(). - """ - master_params[0].grad = _flatten_dense_tensors( - [param.grad.data.detach().float() for param in model_params] - ) - - -def master_params_to_model_params(model_params, master_params): - """ - Copy the master parameter data back into the model parameters. - """ - # Without copying to a list, if a generator is passed, this will - # silently not copy any parameters. - model_params = list(model_params) - - for param, master_param in zip( - model_params, unflatten_master_params(model_params, master_params) - ): - param.detach().copy_(master_param) - - -def unflatten_master_params(model_params, master_params): - """ - Unflatten the master parameters to look like model_params. - """ - return _unflatten_dense_tensors(master_params[0].detach(), model_params) - - -def zero_grad(model_params): - for param in model_params: - # Taken from https://pytorch.org/docs/stable/_modules/torch/optim/optimizer.html#Optimizer.add_param_group - if param.grad is not None: - param.grad.detach_() - param.grad.zero_() diff --git a/spaces/tharunayak14/Text-Summarization/app.py b/spaces/tharunayak14/Text-Summarization/app.py deleted file mode 100644 index e88e1fdb76bc9399b2e59ee0d63cf133562e5244..0000000000000000000000000000000000000000 --- a/spaces/tharunayak14/Text-Summarization/app.py +++ /dev/null @@ -1,11 +0,0 @@ -import gradio as gr -from transformers import pipeline - -get_completion = pipeline("summarization", model="sshleifer/distilbart-cnn-12-6") - -def summarize(input): - output = get_completion(input) - return output[0]['summary_text'] - -demo = gr.Interface(fn=summarize, inputs="text", outputs="text") -demo.launch() \ No newline at end of file diff --git a/spaces/tialenAdioni/chat-gpt-api/logs/Ansys V15.0 Win32 Win64-ISO.md b/spaces/tialenAdioni/chat-gpt-api/logs/Ansys V15.0 Win32 Win64-ISO.md deleted file mode 100644 index a050f3c135083a2c8f6597bba68d84895294efca..0000000000000000000000000000000000000000 --- a/spaces/tialenAdioni/chat-gpt-api/logs/Ansys V15.0 Win32 Win64-ISO.md +++ /dev/null @@ -1,20 +0,0 @@ - -

    How to Download and Install Ansys v15.0 Win32 Win64-ISO

    -

    Ansys v15.0 is a powerful software suite that offers a comprehensive approach to guide and optimize complete product designs. It covers various physics domains such as high-frequency electromagnetics, signal integrity, low-frequency electromagnetics, structures, and fluids. It also features enhanced pre-processing capabilities, high-performance computing, and a user-friendly interface.

    -

    If you are looking for a reliable source to download and install Ansys v15.0 Win32 Win64-ISO, you have come to the right place. In this article, we will show you how to get the software from a trusted website and how to set it up on your Windows PC.

    -

    Ansys v15.0 Win32 Win64-ISO


    Download ✯✯✯ https://urlcod.com/2uK8M9



    -

    Step 1: Download Ansys v15.0 Win32 Win64-ISO

    -

    The first step is to download the software from a reputable website that offers high-speed downloads and secure links. One such website is GFXTRA31, which provides both 32-bit and 64-bit versions of Ansys v15.0 Win32 Win64-ISO[^1^]. You can choose the version that suits your system requirements and click on the download link.

    -

    The download will be in a RAR format, which is a compressed file that contains multiple files and folders. You will need a program like WinRAR or 7-Zip to extract the files from the RAR archive.

    -

    Step 2: Extract the Files from the RAR Archive

    -

    After downloading the RAR archive, you need to extract the files from it. To do this, you can right-click on the RAR file and select "Extract Here" or "Extract to Ansys v15.0 Win32 Win64-ISO" (depending on your program). This will create a folder with the same name as the RAR file, which contains all the files and folders of the software.

    -

    Inside the folder, you will find two subfolders: one for the 32-bit version (WIN32) and one for the 64-bit version (WIN64). You can open the subfolder that matches your system architecture and find another RAR file with the name "ANSYS.PRODUCTS.V15.PROPER-MAGNiTUDE". This is the actual installation file of Ansys v15.0 Win32 Win64-ISO.

    -

    Step 3: Install Ansys v15.0 Win32 Win64-ISO

    -

    The final step is to install Ansys v15.0 Win32 Win64-ISO on your PC. To do this, you need to extract the installation file from the RAR archive as explained in step 2. Then, you need to open the extracted folder and find a text file named "m-anp150.txt". This file contains the instructions on how to install the software.

    -

    You need to follow the instructions carefully and enter the license information when prompted. You also need to copy some files from the folder "MAGNiTUDE" to some specific locations on your PC as instructed in the text file. After completing these steps, you should be able to run Ansys v15.0 Win32 Win64-ISO on your PC.

    -

    Conclusion

    -

    Ansys v15.0 Win32 Win64-ISO is a powerful software suite that can help you design and optimize complex products across various physics domains. It is not easy to find a reliable source to download and install this software, but we have shown you how to do it in this article.

    -

    We hope this article was helpful and informative for you. If you have any questions or comments, please feel free to leave them below.

    -

    81aa517590
    -
    -
    \ No newline at end of file diff --git a/spaces/tialenAdioni/chat-gpt-api/logs/Improve Your Rhythm Coordination and Style with Roland DT 1 V Drums Tutor Software Download Zip.md b/spaces/tialenAdioni/chat-gpt-api/logs/Improve Your Rhythm Coordination and Style with Roland DT 1 V Drums Tutor Software Download Zip.md deleted file mode 100644 index 9d0eddd4e1cd6b148123d8ba2fc5dc3081896578..0000000000000000000000000000000000000000 --- a/spaces/tialenAdioni/chat-gpt-api/logs/Improve Your Rhythm Coordination and Style with Roland DT 1 V Drums Tutor Software Download Zip.md +++ /dev/null @@ -1,89 +0,0 @@ - -

    Roland DT-1: The Ultimate Software for Learning V-Drums

    -

    If you have a Roland V-Drums kit and you want to learn how to play drums or improve your drumming skills, you might be interested in Roland DT-1 V-Drums Tutor software. This software is a program for your computer (compatible with Windows and Mac OS) that provides fun interactive tools to help drummers improve their rhythm, coordination and expand their playing styles. In this article, we will review the features and benefits of Roland DT-1 V-Drums Tutor software, as well as how to download, install and use it effectively.

    -

    roland dt 1 v drums tutor software download zip


    Download File ►►►►► https://urlcod.com/2uK9Sr



    -

    What is Roland DT-1 V-Drums Tutor software?

    -

    Roland DT-1 V-Drums Tutor software is a software that connects your Roland V-Drums kit to your computer (Mac/Windows) and prepares you for a learning experience like no other. It allows you to enjoy practice in a fun format when you play along with the onboard patterns and songs using the colorful graphical interface. It also helps you learn drumming step-by-step from beginning to intermediate levels. It also improves your sight-reading with the notation screen, and lets you enjoy drumming with the game screen. It also enhances the V-Drums experience in the home as well as for private lessons and music schools.

    -

    What are the features and benefits of Roland DT-1 V-Drums Tutor software?

    -

    Roland DT-1 V-Drums Tutor software has many features and benefits that can help you simplify and optimize your drumming practice. Some of them are:

    -
      -
    • Easy to use: Roland DT-1 V-Drums Tutor software has a user-friendly interface that guides you through the steps of creating and managing your practice sessions. You can also customize the software according to your preferences and needs.
      • -
    • Fun and interactive: Roland DT-1 V-Drums Tutor software allows you to practice in a fun format when you play along with the onboard patterns and songs using the colorful graphical interface. You can also choose from two types of screens — “Notation” and “Game.” The “notation screen” shows a ball that bounces with the tempo, as well as the graphics of each pad that is hit, which will light up at the timing when played. In the “game screen,” blocks scroll downward at the timing of each pad played, so even if you can not read drum notation, you’ll find a practice challenge as if you were simply playing a game.
      • -
    • Comprehensive and flexible: Roland DT-1 V-Drums Tutor software contains 60 preset songs and 57 basic drum patterns to build drumming skills. You can also install your favorite SMF data for custom practice. You can also adjust the tempo, volume, balance, mute, solo, loop, etc. of each song or pattern. You can also select different drum sounds or kits for each song or pattern.
      • -
    • Evaluate your playing: Roland DT-1 V-Drums Tutor software is able to evaluate the timing of your playing, and can display “O” and “X” symbols on the drum notation screen to show how you’re doing, timing wise. This visual feature automatically helps you to progress because you can see your mistakes. It also displays colorful correction marks and scores to show your accuracy. It also shows a dynamic bar graph that displays your stroke balance.
      • -
    • Compatible and up-to-date: Roland DT-1 V-Drums Tutor software is compatible with any Roland V-Drums kit. It is also regularly updated with the latest songs and patterns that suit your musical taste and level.
      • -
    -

    How to download, install and use Roland DT-1 V-Drums Tutor software?

    -

    To download Roland DT-1 V-Drums Tutor software on your computer, you need to follow these steps:

    -
      -
    1. Go to the official website of Roland DT-1 V-Drums Tutor software and click on the download link.
      2. -
    2. Select your operating system (Windows or Mac OS) and click on the download button.
      3. -
    3. Save the zip file on your computer and extract it.
      4. -
    4. Run the setup file and follow the instructions on the screen.
      5. -
    -

    To install Roland DT-1 V-Drums Tutor software on your computer, you need to follow these steps:

    -

    roland dt 1 v drums tutor software free download
    -how to install roland dt 1 v drums tutor software
    -roland dt 1 v drums tutor software crack
    -roland dt 1 v drums tutor software review
    -roland dt 1 v drums tutor software mac
    -roland dt 1 v drums tutor software windows 10
    -roland dt 1 v drums tutor software manual
    -roland dt 1 v drums tutor software update
    -roland dt 1 v drums tutor software license key
    -roland dt 1 v drums tutor software online
    -roland dt 1 v drums tutor software for beginners
    -roland dt 1 v drums tutor software for advanced players
    -roland dt 1 v drums tutor software features
    -roland dt 1 v drums tutor software requirements
    -roland dt 1 v drums tutor software troubleshooting
    -roland dt 1 v drums tutor software alternative
    -roland dt 1 v drums tutor software demo
    -roland dt 1 v drums tutor software price
    -roland dt 1 v drums tutor software discount code
    -roland dt 1 v drums tutor software reddit
    -roland dt 1 v drums tutor software youtube
    -roland dt 1 v drums tutor software vs melodics
    -roland dt 1 v drums tutor software vs drumming system
    -roland dt 1 v drums tutor software vs drum masterclass
    -roland dt 1 v drums tutor software vs drum genius
    -best settings for roland dt 1 v drums tutor software
    -best headphones for roland dt 1 v drums tutor software
    -best songs to learn with roland dt 1 v drums tutor software
    -best tips and tricks for roland dt 1 v drums tutor software
    -best practice routine with roland dt 1 v drums tutor software
    -how to use midi with roland dt 1 v drums tutor software
    -how to record with roland dt 1 v drums tutor software
    -how to export with roland dt 1 v drums tutor software
    -how to customize with roland dt 1 v drums tutor software
    -how to improve speed with roland dt 1 v drums tutor software
    -how to improve accuracy with roland dt 1 v drums tutor software
    -how to improve timing with roland dt 1 v drums tutor software
    -how to improve groove with roland dt 1 v drums tutor software
    -how to improve dynamics with roland dt 1 v drums tutor software
    -how to improve coordination with roland dt 1 v drums tutor software
    -how to play rock with roland dt 1 v drums tutor software
    -how to play jazz with roland dt 1 v drums tutor software
    -how to play funk with roland dt 1 v drums tutor software
    -how to play metal with roland dt 1 v drums tutor software
    -how to play latin with roland dt 1 v drums tutor software
    -how to play reggae with roland dt 1 v drums tutor software
    -how to play blues with roland dt 1 v drums tutor software
    -how to play pop with roland dt 1 v drums tutor software
    -how to play hip hop with roland dt 1 v drums tutor software
    -how to play electronic with roland dt 1 v drums tutor software

    -
      -
    1. Connect your Roland V-Drums kit to your computer using a USB cable or a MIDI interface.
      2. -
    2. Launch the software from the desktop shortcut or the start menu.
      3. -
    3. Enter the serial number and activation code that are provided with the software.
      4. -
    4. Select the language and the country of your preference.
      5. -
    5. Select the type of installation (standard or custom) and the destination folder.
      6. -
    6. Wait for the installation to complete and restart your computer if necessary.
      7. -
    -

    To use Roland DT-1 V-Drums Tutor software on your computer, you need to follow these steps:

    -
      -
    1. Launch the software from

      -

      Conclusion

      -

      Roland DT-1 V-Drums Tutor software is a software that connects your Roland V-Drums kit to your computer and provides fun interactive tools to help you learn and improve your drumming skills. It has many features and benefits that can simplify and optimize your practice, such as easy to use, fun and interactive, comprehensive and flexible, evaluate your playing, and compatible and up-to-date. It also has a user-friendly interface that guides you through the steps of creating and managing your practice sessions. You can also customize the software according to your preferences and needs. To download, install and use Roland DT-1 V-Drums Tutor software, you just need to follow some simple steps. You can also benefit from the online support and assistance from the Roland team. If you have a Roland V-Drums kit and you want to learn how to play drums or improve your drumming skills, you might want to consider Roland DT-1 V-Drums Tutor software.

      679dcb208e
      -
      -
      \ No newline at end of file diff --git a/spaces/tialenAdioni/chat-gpt-api/logs/Kathmandu Bengali Movie 720p 63 Download A Gripping Tale of Crime and Corruption.md b/spaces/tialenAdioni/chat-gpt-api/logs/Kathmandu Bengali Movie 720p 63 Download A Gripping Tale of Crime and Corruption.md deleted file mode 100644 index 679994d6c499afedd871b370d3f263cfebda6a42..0000000000000000000000000000000000000000 --- a/spaces/tialenAdioni/chat-gpt-api/logs/Kathmandu Bengali Movie 720p 63 Download A Gripping Tale of Crime and Corruption.md +++ /dev/null @@ -1,86 +0,0 @@ -
      -

      Katmundu: A Comedy Romantic Thriller from Bengal

      -

      Introduction

      -

      If you are looking for a fun-filled movie that will make you laugh and also keep you on the edge of your seat, then Katmundu is the perfect choice for you. Katmundu is a 2015 Indian Bengali comedy romantic thriller film directed by Raj Chakraborty. The film features Soham Chakraborty, Abir Chatterjee, Rudranil Ghosh, Srabanti Chatterjee, Mimi Chakraborty and Saswata Chatterjee in the lead roles. The film is produced by Shyam Sundar Dey under GreenTouch Entertainment.

      -

      kathmandu bengali movie download 720p 63


      DOWNLOAD » https://urlcod.com/2uK1DM



      -

      The story, penned down by Padmanava Dasgupta, is about three software engineers who undertake a journey to Nepal to escape the stress of a 9-to-5 job and how their life takes an unexpected turn after meeting three girls on their way, forms the crux of the story. The film is a mix of comedy, romance, action and suspense that will keep you entertained throughout.

      -

      Katmundu is a movie that will appeal to all kinds of audiences, whether you are a fan of comedy, romance or thriller. The movie has a lot of hilarious moments, some heartwarming scenes and some nail-biting sequences that will make you enjoy every minute of it. The movie also showcases the scenic beauty of Nepal and Kolkata in a splendid way.

      -

      Movie Review

      -

      The Story

      -

      The story of Katmundu revolves around three friends who work as software engineers in Kolkata. They are Sunny (Soham Chakraborty), Pablo (Abir Chatterjee) and Sidhu (Rudranil Ghosh). They are fed up with their boring and stressful job and decide to take a break and go to Kathmandu (Nepal) for a vacation. They book a package tour from a travel agency run by Aiyoswami (Saswata Chatterjee), who promises them a memorable trip.

      -

      Katmundu bengali movie free download
      -Kathmandu bengali movie torrent link
      -Kathmandu bengali movie online streaming
      -Kathmandu bengali movie 720p HD quality
      -Kathmandu bengali movie full length
      -Kathmandu bengali movie cast and crew
      -Kathmandu bengali movie review and rating
      -Kathmandu bengali movie songs and music
      -Kathmandu bengali movie subtitles download
      -Kathmandu bengali movie trailer and teaser
      -Kathmandu bengali movie watch online free
      -Kathmandu bengali movie download filmywap
      -Kathmandu bengali movie download pagalworld
      -Kathmandu bengali movie download tamilrockers
      -Kathmandu bengali movie download movierulz
      -Kathmandu bengali movie download utorrent
      -Kathmandu bengali movie download khatrimaza
      -Kathmandu bengali movie download worldfree4u
      -Kathmandu bengali movie download 9xmovies
      -Kathmandu bengali movie download filmyzilla
      -Kathmandu bengali movie download mp4moviez
      -Kathmandu bengali movie download skymovieshd
      -Kathmandu bengali movie download jalshamoviez
      -Kathmandu bengali movie download moviescounter
      -Kathmandu bengali movie download coolmoviez
      -Kathmandu bengali movie download hdfriday
      -Kathmandu bengali movie download okhatrimaza
      -Kathmandu bengali movie download mkvcinemas
      -Kathmandu bengali movie download mkvhub
      -Kathmandu bengali movie download hdmovieshub
      -Kathmandu bengali movie download moviesflix
      -Kathmandu bengali movie download 7starhd
      -Kathmandu bengali movie download extramovies
      -Kathmandu bengali movie download afilmywap
      -Kathmandu bengali movie download hdpopcorns
      -Kathmandu bengali movie download yts
      -Kathmandu bengali movie download rarbg
      -Kathmandu bengali movie download limetorrents
      -Kathmandu bengali movie download kickass torrents
      -Kathmandu bengali movie download magnet link
      -Katmundu full hd 720p free online watch[^1^]
      -Katmundu internet archive streaming[^1^]
      -Katmundu full length video[^1^]
      -Katmundu audio book soundcloud[^3^]
      -Katmundu cosvarano soundcloud[^3^]
      -Katmundu jvcviz website[^2^]
      -Katmundu general discussion forum[^2^]
      -Katmundu odonnao ovasilevs post[^2^]
      -Katmundu weekly reliv maddam sir episodes[^2^]
      -Katmundu tamilrockers and movierulz videos[^2^]

      -

      However, things do not go as planned when they reach Nepal. They meet three girls who change their lives forever. They are Pallabi (Srabanti Chatterjee), Rai (Mimi Chakraborty) and Kanchi (Roja Dey). Pallabi is Pablo's ex-girlfriend who dumped him for another guy. Rai is Sunny's childhood friend who has a crush on him. Kanchi is a Nepali girl who works as a guide and falls in love with Sidhu.

      -

      The three friends get into trouble when they unknowingly get involved in a smuggling racket run by Minakshi (Malobika Banerjee) and her henchmen. They have to face many dangers and challenges as they try to escape from the villains and also find love in the process.

      -

      The Performance

      -

      The performance of the actors is one of the highlights of Katmundu. The three lead actors, Soham, Abir and Rudranil, have done a commendable job in portraying their characters. They have a great chemistry and camaraderie among themselves and also with their respective love interests. They have delivered some hilarious dialogues and expressions that will make you laugh out loud.

      -

      The three leading ladies, Srabanti, Mimi and Roja, have also given impressive performances. They have matched up to their male counterparts in terms of acting and glamour. They have added charm and grace to their roles and also shown their versatility in different emotions.

      -

      The supporting actors, especially Saswata Chatterjee, have also contributed to the comedy quotient of the movie. Saswata plays the role of Aiyoswami, who is a funny and quirky character who keeps making mistakes and creating confusion. He has some of the best scenes in the movie that will make you laugh till your stomach hurts.

      -

      The Direction and Music

      -

      The direction of Raj Chakraborty is another plus point of Katmundu. He has handled the script and the scenes with skill and finesse. He has balanced the comedy, romance, action and suspense elements well and maintained a smooth pace throughout. He has also extracted good performances from his actors and made use of his technical team effectively.

      -

      The music of Anupam Roy is another asset of Katmundu. He has composed and sung six songs for the movie that are catchy and melodious. The songs suit the mood and theme of the movie well and also enhance the visual appeal. Some of the popular songs are "Aami Raaji", "Eto Aalo", "Bhorer Tara" and "Mon Amaar". The lyrics are also meaningful and catchy.

      -

      The cinematography of Sirsha Ray is another commendable aspect of Katmundu. He has captured the beauty of Nepal and Kolkata in a splendid way. He has used different angles and shots to create an aesthetic appeal for the viewers. He has also shot some thrilling action sequences that will keep you hooked.

      -

      Conclusion

      -

      Katmundu is a movie that will not disappoint you if you are looking for a wholesome entertainment package. It has comedy, romance, action and suspense that will keep you engaged throughout. It has good performances, direction, music and cinematography that will make you appreciate its quality. It has a simple but engaging story that will make you relate to its characters.

      -

      I would give Katmundu a rating of 4 out of 5 stars and recommend it to anyone who wants to watch a fun-filled movie that will make them laugh and also thrill them at times. It is a movie that will make you forget your worries for two hours and enjoy yourself with your friends or family.

      -

      FAQs

      -

      When was Katmundu released?

      -

      Katmundu was released on 16 October 2015 in India.

      -

      Where can I watch Katmundu online?

      -

      You can watch Katmundu online on various streaming platforms like Hoichoi, Zee5, MX Player etc.

      -

      Is Katmundu based on a true story?

      -

      No, Katmundu is not based on a true story. It is a fictional story written by Padmanava Dasgupta.

      -

      Who is Roja Dey in Katmundu?

      -

      Roja Dey is an actress who debuted on the silver screen with Katmundu. She plays the role of Kanchi, a Nepali girl who works as a guide and falls in love with Sidhu.

      -

      What are some other movies by Raj Chakraborty?

      -

      Some other movies by Raj Chakraborty are Challenge (2009), Bojhena Shey Bojhena (2012), Parbona Ami Chartey Tokey (2015), Noor Jahaan (2018), Parineeta (2019) etc.

      0a6ba089eb
      -
      -
      \ No newline at end of file diff --git a/spaces/ticomspire/turkey-syria-earthquake-tweets/logs/Call of Duty Mobile - Garena APK for Huawei The Ultimate Guide.md b/spaces/ticomspire/turkey-syria-earthquake-tweets/logs/Call of Duty Mobile - Garena APK for Huawei The Ultimate Guide.md deleted file mode 100644 index 6462d6020032033b1d9e8f9fa9c02fbda68db510..0000000000000000000000000000000000000000 --- a/spaces/ticomspire/turkey-syria-earthquake-tweets/logs/Call of Duty Mobile - Garena APK for Huawei The Ultimate Guide.md +++ /dev/null @@ -1,127 +0,0 @@ - -

      Call of Duty Mobile - Garena APK for Huawei

      -

      If you are a fan of first-person shooter games and want to enjoy a thrilling and immersive experience on your mobile device, you should try Call of Duty Mobile - Garena. This game is a crossover of the popular Call of Duty franchise, featuring various modes, maps, weapons, and characters from the series. In this article, we will tell you what Call of Duty Mobile - Garena is, how to download and install it on your Huawei device, how to play it on PC, and some tips and tricks to help you win.

      -

      call of duty mobile - garena apk for huawei


      Download File »»» https://bltlly.com/2uOqat



      -

      What is Call of Duty Mobile - Garena?

      -

      Call of Duty Mobile - Garena is a free-to-play first-person shooter game developed by Activision in partnership with Tencent's Timi Studios and published by Garena in Southeast Asia. The game offers a variety of modes, such as multiplayer, battle royale, and zombie mode, where you can engage in head-to-head battles through fan-favorite maps like Nuketown, Crash, Killhouse, and Scrapyard. The game also features a gunsmith system that allows you to customize your weapons according to your playing style.

      -

      Features of Call of Duty Mobile - Garena

      -

      Some of the features that make Call of Duty Mobile - Garena stand out are:

      -
        -
      • New MP Map - Apocalypse: A new map set in a jungle village with multiple routes and vantage points.
        • -
      • New weapon FFAR 1: A new assault rifle with a high rate of fire and mobility.
        • -
      • New gameplay, Search & Rescue: A new mode where you have to plant or defuse bombs while reviving your allies.
        • -
      • New Battle Royale Knight's Covenant mode: A new mode where you have to collect resources to produce necessary supplies for survival.
        • -
      • MP Optimization: Improved performance and stability for multiplayer matches.
        • -
      • New MP Modes: New modes such as Gun Game Team Fight, Capture the Flag, One Shot One Kill, and more.
        • -
      • New Functional Weapon - ODEN: A new heavy-hitting assault rifle with high damage and accuracy.
        • -
      • New Ranked Series: A new season with new rewards and challenges.
        • -
      -

      Differences between Call of Duty Mobile - Garena and Global

      -

      Call of Duty Mobile - Garena is not the same as the global version published by Activision. Here are some of the differences between them:

      -
        -
      • Call of Duty Mobile - Garena is only available for players in Southeast Asia (except Vietnam), while the global version is available for players in all other regions (except Vietnam, Belgium, and China).
        • -
      • Call of Duty Mobile - Garena has different servers and matchmaking than the global version, so you cannot play with players from other regions.
        • -
      • Call of Duty Mobile - Garena has different events, updates, and content than the global version, so you may see some differences in the game features and items.
        • -
      -

      How to download and install Call of Duty Mobile - Garena APK for Huawei?

      -

      If you want to play Call of Duty Mobile - Garena on your Huawei device, you will need to download and install the APK file from a trusted source. Here are the steps to do so:

      -

      How to install call of duty mobile - garena apk on huawei devices
      -Call of duty mobile - garena apk download for huawei p40 pro
      -Best settings for call of duty mobile - garena apk on huawei phones
      -Call of duty mobile - garena apk latest version for huawei mate 40
      -Call of duty mobile - garena apk mod for huawei nova 7
      -Call of duty mobile - garena apk update for huawei y9s
      -Call of duty mobile - garena apk free download for huawei p30 lite
      -Call of duty mobile - garena apk offline for huawei enjoy 20
      -Call of duty mobile - garena apk hack for huawei honor 10
      -Call of duty mobile - garena apk obb for huawei mediapad m6
      -Call of duty mobile - garena apk size for huawei y7p
      -Call of duty mobile - garena apk gameplay on huawei p smart 2021
      -Call of duty mobile - garena apk review for huawei mate x2
      -Call of duty mobile - garena apk error on huawei nova 8
      -Call of duty mobile - garena apk features for huawei y6p
      -Call of duty mobile - garena apk tips and tricks for huawei users
      -Call of duty mobile - garena apk compatible with huawei appgallery
      -Call of duty mobile - garena apk graphics settings for huawei mate 30 pro
      -Call of duty mobile - garena apk controller support for huawei phones
      -Call of duty mobile - garena apk system requirements for huawei devices
      -Call of duty mobile - garena apk cheats for huawei honor 9x
      -Call of duty mobile - garena apk zombies mode for huawei p20 pro
      -Call of duty mobile - garena apk data for huawei y8p
      -Call of duty mobile - garena apk skins for huawei nova 5t
      -Call of duty mobile - garena apk weapons for huawei enjoy 10s
      -Call of duty mobile - garena apk maps for huawei matepad pro
      -Call of duty mobile - garena apk ranking system for huawei y9 prime 2019
      -Call of duty mobile - garena apk battle royale mode for huawei p smart z
      -Call of duty mobile - garena apk clans for huawei honor play 4t pro
      -Call of duty mobile - garena apk voice chat for huawei nova 7i
      -Call of duty mobile - garena apk season 7 for huawei mate 20 x
      -Call of duty mobile - garena apk patch notes for huawei y5p
      -Call of duty mobile - garena apk rewards for huawei enjoy z 5g
      -Call of duty mobile - garena apk events for huawei honor v30 pro
      -Call of duty mobile - garena apk codes for huawei p40 lite e
      -Call of duty mobile - garena apk login problem on huawei nova 6 se
      -Call of duty mobile - garena apk lag fix for huawei y6s
      -Call of duty mobile - garena apk sensitivity settings for huawei matepad t8
      -Call of duty mobile - garena apk crossplay with other platforms on huawei phones
      -Call of duty mobile - garena apk emulator for pc with huawei id account

      -

      Step 1: Download the APK file from a trusted source

      -

      You can download the latest version of Call of Duty Mobile - Garena APK from the official website or from other reliable sources like APKPure or APKMirror. Make sure you have enough storage space on your device before downloading the file.

      -

      Step 2: Enable unknown sources on your Huawei device

      -

      Before you can install the APK file, you need to enable unknown sources on your Huawei device. This will allow you to install apps from sources other than the Google Play Store. To do this, follow these steps:

      -
        -
      1. Go to Settings > Security & privacy > More settings.
        2. -
      2. Tap on Install unknown apps and select the browser or file manager that you used to download the APK file.
        3. -
      3. Toggle on Allow app installs and confirm your choice.
        4. -
      -

      Step 3: Install the APK file and launch the game

      -

      Once you have enabled unknown sources, you can install the APK file by following these steps:

      -
        -
      1. Locate the downloaded APK file on your device and tap on it.
        2. -
      2. Tap on Install and wait for the installation to complete.
        3. -
      3. Tap on Open and grant the necessary permissions to the game.
        4. -
      4. Log in with your Garena account or create a new one if you don't have one.
        5. -
      5. Enjoy playing Call of Duty Mobile - Garena on your Huawei device.
        6. -
      -

      How to play Call of Duty Mobile - Garena on PC?

      -

      If you prefer playing Call of Duty Mobile - Garena on a bigger screen and with better controls, you can also play it on your PC. There are two ways to do this:

      -

      Option 1: Use an emulator like LDPlayer

      -

      An emulator is a software that allows you to run Android apps on your PC. One of the best emulators for Call of Duty Mobile - Garena is LDPlayer, which offers smooth performance, high compatibility, and customizable controls. To use LDPlayer, follow these steps:

      -
        -
      1. Download and install LDPlayer from its official website.
        2. -
      2. Launch LDPlayer and search for Call of Duty Mobile - Garena in the LD Store or Google Play Store.
        3. -
      3. Download and install Call of Duty Mobile - Garena on LDPlayer.
        4. -
      4. Log in with your Garena account or create a new one if you don't have one.
        5. -
      5. Enjoy playing Call of Duty Mobile - Garena on PC with LDPlayer.
        6. -
      -

      Option 2: Use a mirroring app like ApowerMirror

      -

      A mirroring app is a software that allows you to mirror your mobile screen to your PC. One of the best mirroring apps for Call of Duty Mobile - Garena is ApowerMirror, which offers high-quality display, easy connection, and keyboard and mouse support. To use ApowerMirror, follow these steps:

      -
        -
      1. Download and install ApowerMirror on your PC and mobile device from its official website.
        2. -
      2. Connect your mobile device and PC to the same Wi-Fi network.
        3. -
      3. Launch ApowerMirror on both devices and tap on Mirror on your mobile device.
        4. -
      4. Select your PC name from the list of available devices and tap on Start Now.
        5. -
      5. Your mobile screen will be mirrored to your PC. You can use your keyboard and mouse to control the game.
        6. -
      6. Enjoy playing Call of Duty Mobile - Garena on PC with ApowerMirror.
        7. -
      -

      Tips and tricks for Call of Duty Mobile - Garena

      -

      To help you improve your skills and win more matches in Call of Duty Mobile - Garena, here are some tips and tricks that you should know:

      -

      Customize your controls and settings

      -

      One of the most important things to do before playing Call of Duty Mobile - Garena is to customize your controls and settings according to your preference. You can adjust the sensitivity, layout, graphics, sound, and other options in the game settings. You can also choose between simple mode, which automatically fires when aiming at an enemy, or advanced mode, which gives you more control over firing and aiming. Experiment with different settings until you find the ones that suit you best.

      -

      Use the best weapons and loadouts for each mode

      -

      Different modes in Call of Duty Mobile - Garena require different strategies and weapons. For example, in multiplayer mode, you may want to use a fast-firing weapon like an SMG or a shotgun for close-range combat, while in battle royale mode, you may want to use a long-range weapon like a sniper rifle or a marksman rifle for taking out enemies from afar. You can also use the gunsmith system to modify your weapons with different attachments, perks, and skins. You can create different loadouts for different modes and situations, and switch between them during the game. Experiment with different weapons and loadouts until you find the ones that suit your playstyle.

      -

      Communicate and cooperate with your team

      -

      Another key factor for winning in Call of Duty Mobile - Garena is communication and cooperation with your team. Whether you are playing with your friends or random players, you should always communicate with your team using the voice chat or text chat feature. You can also use the quick chat option to send predefined messages to your team. Communication can help you coordinate your attacks, share information, request support, and warn your teammates of danger. Cooperation can help you work together as a team, cover each other, revive each other, and share resources. Communication and cooperation can make the difference between victory and defeat.

      -

      Conclusion

      -

      Call of Duty Mobile - Garena is a fun and exciting game that offers a variety of modes, maps, weapons, and characters from the Call of Duty franchise. You can play it on your Huawei device by downloading and installing the APK file from a trusted source, or you can play it on your PC by using an emulator or a mirroring app. You can also improve your skills and win more matches by customizing your controls and settings, using the best weapons and loadouts for each mode, and communicating and cooperating with your team. If you are looking for a first-person shooter game that will keep you entertained and challenged, you should give Call of Duty Mobile - Garena a try.

      -

      FAQs

      -

      Here are some of the frequently asked questions about Call of Duty Mobile - Garena:

      -
        -
      1. Q: Is Call of Duty Mobile - Garena free to play?
        A: Yes, Call of Duty Mobile - Garena is free to play, but it also offers in-game purchases for cosmetic items, weapons, and other features.
        2. -
      2. Q: Can I play Call of Duty Mobile - Garena offline?
        A: No, Call of Duty Mobile - Garena requires an internet connection to play.
        3. -
      3. Q: Can I transfer my progress from the global version to the Garena version?
        A: No, Call of Duty Mobile - Garena and the global version are separate games with separate servers and accounts. You cannot transfer your progress from one version to another.
        4. -
      4. Q: How can I get more CP (COD Points) in Call of Duty Mobile - Garena?
        A: You can get more CP by purchasing them with real money or by completing certain tasks and events in the game.
        5. -
      5. Q: How can I report hackers or cheaters in Call of Duty Mobile - Garena?
        A: You can report hackers or cheaters by tapping on their name in the match results screen or in the lobby, and then tapping on Report. You can also contact the customer service team through the game settings or the official website.
        6. -

      197e85843d
      -
      -
      \ No newline at end of file diff --git a/spaces/timqian/like-history/src/App.js b/spaces/timqian/like-history/src/App.js deleted file mode 100644 index 8229f9916a6522e9028a577e61a64a5e54b10e63..0000000000000000000000000000000000000000 --- a/spaces/timqian/like-history/src/App.js +++ /dev/null @@ -1,55 +0,0 @@ -import { useState } from "react"; - -const projectTypes = ["model", "dataset", "space"]; - -/** - * 1. User click enter key - * 2. Get model/dataset/space name - * 3. Get data from API - * 4. Format data(to 20 points at most) - * 5. Draw line chart - */ -function App() { - const [projectType, setProjectType] = useState("model"); - const [projectName, setProjectName] = useState("meta-llama/Llama-2-7b"); - - return ( -
      -
      -

      - View the like history of a project on huggingface 🤗 -

      -
      -
      -
      - - -
      - -
      -
      - - -
      -
      - ); -} - -export default App; diff --git a/spaces/tioseFevbu/cartoon-converter/Singh-Saab-The-Great-Full-LINK-Movie-In-Hd-1080p.md b/spaces/tioseFevbu/cartoon-converter/Singh-Saab-The-Great-Full-LINK-Movie-In-Hd-1080p.md deleted file mode 100644 index 6c84657ba389783c0d30183aada2dbff87ebd8a5..0000000000000000000000000000000000000000 --- a/spaces/tioseFevbu/cartoon-converter/Singh-Saab-The-Great-Full-LINK-Movie-In-Hd-1080p.md +++ /dev/null @@ -1,67 +0,0 @@ -## Singh Saab The Great Full Movie In Hd 1080p - - - -**Download File › [https://vercupalo.blogspot.com/?d=2tvYnJ](https://vercupalo.blogspot.com/?d=2tvYnJ)** - - - -# How to Watch Singh Saab The Great Full Movie in HD 1080p Online - - - -Singh Saab The Great is a 2013 Hindi action movie starring Sunny Deol, Amrita Rao and Urvashi Rautela. The movie is directed by Anil Sharma and tells the story of a government employee who becomes a crusader against corruption and a champion of the poor and weak. The movie was praised for its patriotic theme, action sequences and Sunny Deol's performance. - - - -If you want to watch Singh Saab The Great full movie in HD 1080p online, you have a few options. Here are some of them: - - - -- **JioCinema**: JioCinema is a streaming service that offers a wide range of movies, TV shows and web series. You can watch Singh Saab The Great full movie in HD 1080p on JioCinema if you have a Jio SIM card or a JioFiber connection. You can access JioCinema on your smartphone, tablet, laptop or smart TV. To watch Singh Saab The Great on JioCinema, go to [^1^] or [^2^] and click on the play button. - -- **Tealfeed**: Tealfeed is a website that provides free download links for movies, TV shows and web series. You can download Singh Saab The Great full movie in HD 1080p from Tealfeed if you have a good internet connection and enough storage space on your device. To download Singh Saab The Great from Tealfeed, go to [^3^] and click on the download button. - - - -Disclaimer: This article is for informational purposes only and does not endorse or promote any illegal activity. Please respect the copyrights of the content creators and watch movies only from legal sources. - - - -If you have watched Singh Saab The Great full movie in HD 1080p online, you might be interested in some trivia and facts about the movie. Here are some of them: - - - -- The movie was inspired by the life and work of Anna Hazare, a social activist who led several anti-corruption movements in India. - -- The movie was shot in various locations in India, such as Bhopal, Indore, Mumbai and Hyderabad. Some scenes were also shot in Dubai and Australia. - -- The movie features a cameo appearance by Dharmendra, Sunny Deol's father and a veteran actor. He plays the role of a judge who sentences Sunny Deol's character to jail. - -- The movie was a moderate success at the box office, earning about 30 crore rupees on a budget of 18 crore rupees. It received mixed reviews from critics and audiences. - - - -Do you have any questions or feedback about the movie or the article? Let me know in the comments section below. - - - -If you enjoyed Singh Saab The Great full movie in HD 1080p online, you might also like some other movies that feature Sunny Deol in a similar role. Here are some of them: - - - -- **Gadar: Ek Prem Katha**: This is a 2001 historical drama movie that stars Sunny Deol and Ameesha Patel. The movie is set during the partition of India and Pakistan in 1947 and tells the story of a Sikh truck driver who falls in love with a Muslim girl and rescues her from the riots. - -- **Ghayal**: This is a 1990 action movie that stars Sunny Deol and Meenakshi Seshadri. The movie is about a boxer who seeks revenge against a corrupt businessman who framed him for the murder of his brother. - -- **Damini**: This is a 1993 social drama movie that stars Sunny Deol and Meenakshi Seshadri. The movie is about a woman who witnesses her brother-in-law raping their maid and fights for justice with the help of a lawyer. - - - -You can watch these movies online on various streaming platforms or download them from legal sources. Please do not support piracy and respect the hard work of the filmmakers and actors. - - - -Thank you for reading this article. I hope you found it informative and entertaining. If you did, please share it with your friends and family who might also be interested in watching Singh Saab The Great full movie in HD 1080p online. You can also follow me on my blog or social media for more articles like this one. Stay tuned for more updates and happy watching! - - 1b8d091108 \ No newline at end of file diff --git a/spaces/tioseFevbu/cartoon-converter/scripts/Apples Vertical Integration Spree Continues [EXCLUSIVE].md b/spaces/tioseFevbu/cartoon-converter/scripts/Apples Vertical Integration Spree Continues [EXCLUSIVE].md deleted file mode 100644 index eeeac610dd51420937f34fd4863460e14eab2f06..0000000000000000000000000000000000000000 --- a/spaces/tioseFevbu/cartoon-converter/scripts/Apples Vertical Integration Spree Continues [EXCLUSIVE].md +++ /dev/null @@ -1,21 +0,0 @@ - -

      Apple’s vertical integration spree continues with Dialog deal

      -

      Apple (NASDAQ: AAPL) has been steadily increasing its control over the components and technologies that go into its products. The latest example of this strategy is a licensing agreement with Dialog Semiconductor (NASDAQOTH: DLGNF), a company that has supplied power management chips to Apple for years.

      -

      According to a press release from Dialog, Apple will pay $300 million in cash for the license of certain power management integrated circuit (PMIC) technologies and the transfer of certain PMIC assets and employees. Apple will also prepay $300 million for products to be delivered over the next three years.

      -

      Apple’s vertical integration spree continues


      Download ⚙⚙⚙ https://urlcod.com/2uHwz5



      -

      The deal will result in over 300 Dialog employees, or 16% of its global workforce, joining Apple. Apple will also take over certain Dialog facilities in Italy, UK, Germany and China.

      -

      Dialog CEO Jalal Bagherli said that the agreement “reinforces our long-standing relationship with Apple, and demonstrates the value of the strong business and technologies we have built at Dialog.”

      -

      However, the deal also means that Dialog will lose its main PMIC spots in future iPhone, iPad and Apple Watch devices. Dialog said that it expects no new revenue contribution from main PMICs for 2019 iPhone models and for 2020 iPad or Watch models.

      -

      Dialog has been relying heavily on sales to Apple, which accounted for about 77% of its revenue in 2017. The company showed in a slide deck accompanying this announcement that while roughly 75% of its revenue in 2018 came from Apple, it expects that by 2022, sales to Apple will make up between 35% and 40% of its revenue.

      -

      Dialog said that it will continue to ship current and future generations of sub-PMICs for all platforms to Apple. It also said that it has been awarded a broad range of new contracts by Apple, which include the development and supply of power management, audio subsystem, charging and other mixed-signal integrated circuits for high-volume applications.

      -

      The deal is another example of Apple’s vertical integration spree, which aims to reduce its dependence on external suppliers and gain more control over the performance, quality and cost of its products. Apple has been developing its own processors, graphics chips, modems, sensors, displays and software for its devices.

      -

      Apple’s vertical integration spree could have implications for its competitors and customers, as well as for its suppliers. By owning more of the technologies that go into its products, Apple could gain an edge in innovation, differentiation and profitability. However, it could also face challenges in managing the complexity and risks of developing and manufacturing its own components.

      - -

      Apple’s vertical integration spree has some clear benefits for the company. By owning more of the technologies that go into its products, Apple can reduce its reliance on external suppliers, lower its costs, improve its quality and performance, and protect its intellectual property. Apple can also create a more seamless and consistent user experience across its hardware, software and services, which enhances its brand loyalty and differentiation.

      -

      -

      For example, by designing its own processors for the iPhone and iPad, Apple can optimize them for its own operating system and applications, resulting in faster and more efficient devices. By developing its own display technology, Apple can ensure that its products have the best color accuracy and brightness. By creating its own subscription services, such as Apple Music and Apple TV+, Apple can offer exclusive content and features to its customers.

      -

      However, Apple’s vertical integration spree also poses some challenges and risks for the company. By taking on more functions and activities, Apple increases its complexity and operational demands, which could strain its resources and capabilities. Apple also faces the challenge of maintaining its innovation edge in a rapidly changing and competitive industry, where it has to constantly anticipate and meet customer needs and preferences.

      -

      For instance, by designing its own modems for future iPhones, Apple will have to compete with established players like Qualcomm and Huawei, who have years of experience and expertise in this field. By entering the streaming market, Apple will have to contend with rivals like Netflix and Disney+, who have larger and more diverse content libraries. By expanding its services portfolio, Apple will have to balance its hardware-centric culture with a software-centric one.

      -

      Apple’s vertical integration spree is not a guarantee of success. It requires careful planning, execution and coordination across different functions and units. It also requires a culture of collaboration, experimentation and learning that fosters innovation. Apple has shown that it can master these challenges in the past, but it will have to continue to do so in the future.

      cec2833e83
      -
      -
      \ No newline at end of file diff --git a/spaces/tioseFevbu/cartoon-converter/scripts/Free Download Film Digimon Movie Subtitle Indonesia PATCHED.md b/spaces/tioseFevbu/cartoon-converter/scripts/Free Download Film Digimon Movie Subtitle Indonesia PATCHED.md deleted file mode 100644 index eb70d16d7ec83c34b354848b5d0ff173681a4c19..0000000000000000000000000000000000000000 --- a/spaces/tioseFevbu/cartoon-converter/scripts/Free Download Film Digimon Movie Subtitle Indonesia PATCHED.md +++ /dev/null @@ -1,23 +0,0 @@ - -

      Free Download Film Digimon Movie Subtitle Indonesia

      -

      If you are a fan of the Digimon franchise, you might be interested in watching the Digimon movies that were released in Japan. However, finding them online with Indonesian subtitles can be challenging. That's why we have compiled a list of websites where you can free download film Digimon movie subtitle Indonesia and enjoy them on your device.

      -

      free download film digimon movie subtitle indonesia


      Download File ✶✶✶ https://urlcod.com/2uHySa



      -

      The Digimon movies are animated films based on the popular anime and video game series that feature digital monsters called Digimon. The movies explore various aspects of the Digimon world, such as the origin of the Digimon, the relationship between humans and Digimon, and the threats posed by evil Digimon. The movies also feature different characters and Digimon from different seasons of the anime.

      -

      Here are some of the websites where you can free download film Digimon movie subtitle Indonesia:

      -
        -
      • Layarkaca21: This website offers a large collection of anime movies, including the Digimon movies. You can choose from different quality options and download them with Indonesian subtitles.
        • -
      • Samehadaku: This website is dedicated to anime fans and provides various anime content, such as episodes, movies, and specials. You can find the Digimon movies here and download them with Indonesian subtitles.
        • -
      • Anoboy: This website is another source of anime content, where you can watch and download the Digimon movies with Indonesian subtitles. You can also stream them online if you prefer.
        • -
      -

      We hope this article helps you find and enjoy the Digimon movies with Indonesian subtitles. If you have any questions or suggestions, feel free to leave a comment below.

      -

      - -

      If you are wondering which Digimon movies to watch first, here are some recommendations based on the popularity and ratings of the movies:

      -
        -
      1. Digimon Adventure: Last Evolution Kizuna: This movie is the latest and final installment of the Digimon Adventure series, which follows the original DigiDestined as they face their last adventure with their Digimon partners. The movie is a nostalgic and emotional farewell to the characters and fans who grew up with the series.
        2. -
      2. Digimon Adventure tri. 6: Bokura no Mirai: This movie is the sixth and final part of the Digimon Adventure tri. series, which is a sequel to the first two seasons of the anime. The movie concludes the story of the DigiDestined and their Digimon as they face a mysterious threat that puts both worlds in danger.
        3. -
      3. Digimon Adventure: Our War Game: This movie is the second Digimon movie and the first one to be released theatrically. The movie features the DigiDestined and their Digimon as they try to stop a rogue Digimon named Diaboromon from launching a nuclear missile at Japan.
        4. -
      -

      These are just some of the Digimon movies that you can free download film Digimon movie subtitle Indonesia from the websites we mentioned above. There are many more movies to choose from, so feel free to explore and discover your favorite ones.

      7b8c122e87
      -
      -
      \ No newline at end of file diff --git a/spaces/tjburns/ask_marcus_aurelius/.venv/lib/python3.10/site-packages/pip/_internal/operations/build/build_tracker.py b/spaces/tjburns/ask_marcus_aurelius/.venv/lib/python3.10/site-packages/pip/_internal/operations/build/build_tracker.py deleted file mode 100644 index 6621549b8449130d2d01ebac0a3649d8b70c4f91..0000000000000000000000000000000000000000 --- a/spaces/tjburns/ask_marcus_aurelius/.venv/lib/python3.10/site-packages/pip/_internal/operations/build/build_tracker.py +++ /dev/null @@ -1,124 +0,0 @@ -import contextlib -import hashlib -import logging -import os -from types import TracebackType -from typing import Dict, Generator, Optional, Set, Type, Union - -from pip._internal.models.link import Link -from pip._internal.req.req_install import InstallRequirement -from pip._internal.utils.temp_dir import TempDirectory - -logger = logging.getLogger(__name__) - - -@contextlib.contextmanager -def update_env_context_manager(**changes: str) -> Generator[None, None, None]: - target = os.environ - - # Save values from the target and change them. - non_existent_marker = object() - saved_values: Dict[str, Union[object, str]] = {} - for name, new_value in changes.items(): - try: - saved_values[name] = target[name] - except KeyError: - saved_values[name] = non_existent_marker - target[name] = new_value - - try: - yield - finally: - # Restore original values in the target. - for name, original_value in saved_values.items(): - if original_value is non_existent_marker: - del target[name] - else: - assert isinstance(original_value, str) # for mypy - target[name] = original_value - - -@contextlib.contextmanager -def get_build_tracker() -> Generator["BuildTracker", None, None]: - root = os.environ.get("PIP_BUILD_TRACKER") - with contextlib.ExitStack() as ctx: - if root is None: - root = ctx.enter_context(TempDirectory(kind="build-tracker")).path - ctx.enter_context(update_env_context_manager(PIP_BUILD_TRACKER=root)) - logger.debug("Initialized build tracking at %s", root) - - with BuildTracker(root) as tracker: - yield tracker - - -class BuildTracker: - def __init__(self, root: str) -> None: - self._root = root - self._entries: Set[InstallRequirement] = set() - logger.debug("Created build tracker: %s", self._root) - - def __enter__(self) -> "BuildTracker": - logger.debug("Entered build tracker: %s", self._root) - return self - - def __exit__( - self, - exc_type: Optional[Type[BaseException]], - exc_val: Optional[BaseException], - exc_tb: Optional[TracebackType], - ) -> None: - self.cleanup() - - def _entry_path(self, link: Link) -> str: - hashed = hashlib.sha224(link.url_without_fragment.encode()).hexdigest() - return os.path.join(self._root, hashed) - - def add(self, req: InstallRequirement) -> None: - """Add an InstallRequirement to build tracking.""" - - assert req.link - # Get the file to write information about this requirement. - entry_path = self._entry_path(req.link) - - # Try reading from the file. If it exists and can be read from, a build - # is already in progress, so a LookupError is raised. - try: - with open(entry_path) as fp: - contents = fp.read() - except FileNotFoundError: - pass - else: - message = "{} is already being built: {}".format(req.link, contents) - raise LookupError(message) - - # If we're here, req should really not be building already. - assert req not in self._entries - - # Start tracking this requirement. - with open(entry_path, "w", encoding="utf-8") as fp: - fp.write(str(req)) - self._entries.add(req) - - logger.debug("Added %s to build tracker %r", req, self._root) - - def remove(self, req: InstallRequirement) -> None: - """Remove an InstallRequirement from build tracking.""" - - assert req.link - # Delete the created file and the corresponding entries. - os.unlink(self._entry_path(req.link)) - self._entries.remove(req) - - logger.debug("Removed %s from build tracker %r", req, self._root) - - def cleanup(self) -> None: - for req in set(self._entries): - self.remove(req) - - logger.debug("Removed build tracker: %r", self._root) - - @contextlib.contextmanager - def track(self, req: InstallRequirement) -> Generator[None, None, None]: - self.add(req) - yield - self.remove(req) diff --git a/spaces/tjburns/ask_marcus_aurelius/.venv/lib/python3.10/site-packages/pip/_internal/utils/datetime.py b/spaces/tjburns/ask_marcus_aurelius/.venv/lib/python3.10/site-packages/pip/_internal/utils/datetime.py deleted file mode 100644 index 8668b3b0ec1deec2aeb7ff6bd94265d6705e05bf..0000000000000000000000000000000000000000 --- a/spaces/tjburns/ask_marcus_aurelius/.venv/lib/python3.10/site-packages/pip/_internal/utils/datetime.py +++ /dev/null @@ -1,11 +0,0 @@ -"""For when pip wants to check the date or time. -""" - -import datetime - - -def today_is_later_than(year: int, month: int, day: int) -> bool: - today = datetime.date.today() - given = datetime.date(year, month, day) - - return today > given diff --git a/spaces/tomofi/NDLOCR/src/ndl_layout/mmdetection/configs/cascade_rcnn/cascade_mask_rcnn_r50_fpn_1x_coco.py b/spaces/tomofi/NDLOCR/src/ndl_layout/mmdetection/configs/cascade_rcnn/cascade_mask_rcnn_r50_fpn_1x_coco.py deleted file mode 100644 index 49ab539aa4cdf7c396b6f109efe2dc7a6d596a2a..0000000000000000000000000000000000000000 --- a/spaces/tomofi/NDLOCR/src/ndl_layout/mmdetection/configs/cascade_rcnn/cascade_mask_rcnn_r50_fpn_1x_coco.py +++ /dev/null @@ -1,5 +0,0 @@ -_base_ = [ - '../_base_/models/cascade_mask_rcnn_r50_fpn.py', - '../_base_/datasets/coco_instance.py', - '../_base_/schedules/schedule_1x.py', '../_base_/default_runtime.py' -] diff --git a/spaces/tomofi/NDLOCR/src/ndl_layout/mmdetection/configs/gcnet/cascade_mask_rcnn_x101_32x4d_fpn_syncbn-backbone_dconv_c3-c5_r16_gcb_c3-c5_1x_coco.py b/spaces/tomofi/NDLOCR/src/ndl_layout/mmdetection/configs/gcnet/cascade_mask_rcnn_x101_32x4d_fpn_syncbn-backbone_dconv_c3-c5_r16_gcb_c3-c5_1x_coco.py deleted file mode 100644 index fa4b6f12f36be74c6e1f7182db110893f9f4f0c4..0000000000000000000000000000000000000000 --- a/spaces/tomofi/NDLOCR/src/ndl_layout/mmdetection/configs/gcnet/cascade_mask_rcnn_x101_32x4d_fpn_syncbn-backbone_dconv_c3-c5_r16_gcb_c3-c5_1x_coco.py +++ /dev/null @@ -1,11 +0,0 @@ -_base_ = '../dcn/cascade_rcnn_r50_fpn_dconv_c3-c5_1x_coco.py' -model = dict( - backbone=dict( - norm_cfg=dict(type='SyncBN', requires_grad=True), - norm_eval=False, - plugins=[ - dict( - cfg=dict(type='ContextBlock', ratio=1. / 16), - stages=(False, True, True, True), - position='after_conv3') - ])) diff --git a/spaces/tomofi/NDLOCR/src/ndl_layout/mmdetection/configs/vfnet/vfnet_x101_64x4d_fpn_mstrain_2x_coco.py b/spaces/tomofi/NDLOCR/src/ndl_layout/mmdetection/configs/vfnet/vfnet_x101_64x4d_fpn_mstrain_2x_coco.py deleted file mode 100644 index 4329b34bee03d219cdd94b600055eb5d5a7cc8ef..0000000000000000000000000000000000000000 --- a/spaces/tomofi/NDLOCR/src/ndl_layout/mmdetection/configs/vfnet/vfnet_x101_64x4d_fpn_mstrain_2x_coco.py +++ /dev/null @@ -1,14 +0,0 @@ -_base_ = './vfnet_r50_fpn_mstrain_2x_coco.py' -model = dict( - pretrained='open-mmlab://resnext101_64x4d', - backbone=dict( - type='ResNeXt', - depth=101, - groups=64, - base_width=4, - num_stages=4, - out_indices=(0, 1, 2, 3), - frozen_stages=1, - norm_cfg=dict(type='BN', requires_grad=True), - norm_eval=True, - style='pytorch')) diff --git a/spaces/tomofi/NDLOCR/src/ndl_layout/mmdetection/mmdet/core/bbox/samplers/__init__.py b/spaces/tomofi/NDLOCR/src/ndl_layout/mmdetection/mmdet/core/bbox/samplers/__init__.py deleted file mode 100644 index 0b06303fe1000e11c5486c40c70606a34a5208e3..0000000000000000000000000000000000000000 --- a/spaces/tomofi/NDLOCR/src/ndl_layout/mmdetection/mmdet/core/bbox/samplers/__init__.py +++ /dev/null @@ -1,15 +0,0 @@ -from .base_sampler import BaseSampler -from .combined_sampler import CombinedSampler -from .instance_balanced_pos_sampler import InstanceBalancedPosSampler -from .iou_balanced_neg_sampler import IoUBalancedNegSampler -from .ohem_sampler import OHEMSampler -from .pseudo_sampler import PseudoSampler -from .random_sampler import RandomSampler -from .sampling_result import SamplingResult -from .score_hlr_sampler import ScoreHLRSampler - -__all__ = [ - 'BaseSampler', 'PseudoSampler', 'RandomSampler', - 'InstanceBalancedPosSampler', 'IoUBalancedNegSampler', 'CombinedSampler', - 'OHEMSampler', 'SamplingResult', 'ScoreHLRSampler' -] diff --git a/spaces/tomofi/NDLOCR/src/ndl_layout/mmdetection/mmdet/models/losses/focal_loss.py b/spaces/tomofi/NDLOCR/src/ndl_layout/mmdetection/mmdet/models/losses/focal_loss.py deleted file mode 100644 index 493907c6984d532175e0351daf2eafe4b9ff0256..0000000000000000000000000000000000000000 --- a/spaces/tomofi/NDLOCR/src/ndl_layout/mmdetection/mmdet/models/losses/focal_loss.py +++ /dev/null @@ -1,181 +0,0 @@ -import torch -import torch.nn as nn -import torch.nn.functional as F -from mmcv.ops import sigmoid_focal_loss as _sigmoid_focal_loss - -from ..builder import LOSSES -from .utils import weight_reduce_loss - - -# This method is only for debugging -def py_sigmoid_focal_loss(pred, - target, - weight=None, - gamma=2.0, - alpha=0.25, - reduction='mean', - avg_factor=None): - """PyTorch version of `Focal Loss `_. - - Args: - pred (torch.Tensor): The prediction with shape (N, C), C is the - number of classes - target (torch.Tensor): The learning label of the prediction. - weight (torch.Tensor, optional): Sample-wise loss weight. - gamma (float, optional): The gamma for calculating the modulating - factor. Defaults to 2.0. - alpha (float, optional): A balanced form for Focal Loss. - Defaults to 0.25. - reduction (str, optional): The method used to reduce the loss into - a scalar. Defaults to 'mean'. - avg_factor (int, optional): Average factor that is used to average - the loss. Defaults to None. - """ - pred_sigmoid = pred.sigmoid() - target = target.type_as(pred) - pt = (1 - pred_sigmoid) * target + pred_sigmoid * (1 - target) - focal_weight = (alpha * target + (1 - alpha) * - (1 - target)) * pt.pow(gamma) - loss = F.binary_cross_entropy_with_logits( - pred, target, reduction='none') * focal_weight - if weight is not None: - if weight.shape != loss.shape: - if weight.size(0) == loss.size(0): - # For most cases, weight is of shape (num_priors, ), - # which means it does not have the second axis num_class - weight = weight.view(-1, 1) - else: - # Sometimes, weight per anchor per class is also needed. e.g. - # in FSAF. But it may be flattened of shape - # (num_priors x num_class, ), while loss is still of shape - # (num_priors, num_class). - assert weight.numel() == loss.numel() - weight = weight.view(loss.size(0), -1) - assert weight.ndim == loss.ndim - loss = weight_reduce_loss(loss, weight, reduction, avg_factor) - return loss - - -def sigmoid_focal_loss(pred, - target, - weight=None, - gamma=2.0, - alpha=0.25, - reduction='mean', - avg_factor=None): - r"""A warpper of cuda version `Focal Loss - `_. - - Args: - pred (torch.Tensor): The prediction with shape (N, C), C is the number - of classes. - target (torch.Tensor): The learning label of the prediction. - weight (torch.Tensor, optional): Sample-wise loss weight. - gamma (float, optional): The gamma for calculating the modulating - factor. Defaults to 2.0. - alpha (float, optional): A balanced form for Focal Loss. - Defaults to 0.25. - reduction (str, optional): The method used to reduce the loss into - a scalar. Defaults to 'mean'. Options are "none", "mean" and "sum". - avg_factor (int, optional): Average factor that is used to average - the loss. Defaults to None. - """ - # Function.apply does not accept keyword arguments, so the decorator - # "weighted_loss" is not applicable - loss = _sigmoid_focal_loss(pred.contiguous(), target, gamma, alpha, None, - 'none') - if weight is not None: - if weight.shape != loss.shape: - if weight.size(0) == loss.size(0): - # For most cases, weight is of shape (num_priors, ), - # which means it does not have the second axis num_class - weight = weight.view(-1, 1) - else: - # Sometimes, weight per anchor per class is also needed. e.g. - # in FSAF. But it may be flattened of shape - # (num_priors x num_class, ), while loss is still of shape - # (num_priors, num_class). - assert weight.numel() == loss.numel() - weight = weight.view(loss.size(0), -1) - assert weight.ndim == loss.ndim - loss = weight_reduce_loss(loss, weight, reduction, avg_factor) - return loss - - -@LOSSES.register_module() -class FocalLoss(nn.Module): - - def __init__(self, - use_sigmoid=True, - gamma=2.0, - alpha=0.25, - reduction='mean', - loss_weight=1.0): - """`Focal Loss `_ - - Args: - use_sigmoid (bool, optional): Whether to the prediction is - used for sigmoid or softmax. Defaults to True. - gamma (float, optional): The gamma for calculating the modulating - factor. Defaults to 2.0. - alpha (float, optional): A balanced form for Focal Loss. - Defaults to 0.25. - reduction (str, optional): The method used to reduce the loss into - a scalar. Defaults to 'mean'. Options are "none", "mean" and - "sum". - loss_weight (float, optional): Weight of loss. Defaults to 1.0. - """ - super(FocalLoss, self).__init__() - assert use_sigmoid is True, 'Only sigmoid focal loss supported now.' - self.use_sigmoid = use_sigmoid - self.gamma = gamma - self.alpha = alpha - self.reduction = reduction - self.loss_weight = loss_weight - - def forward(self, - pred, - target, - weight=None, - avg_factor=None, - reduction_override=None): - """Forward function. - - Args: - pred (torch.Tensor): The prediction. - target (torch.Tensor): The learning label of the prediction. - weight (torch.Tensor, optional): The weight of loss for each - prediction. Defaults to None. - avg_factor (int, optional): Average factor that is used to average - the loss. Defaults to None. - reduction_override (str, optional): The reduction method used to - override the original reduction method of the loss. - Options are "none", "mean" and "sum". - - Returns: - torch.Tensor: The calculated loss - """ - assert reduction_override in (None, 'none', 'mean', 'sum') - reduction = ( - reduction_override if reduction_override else self.reduction) - if self.use_sigmoid: - if torch.cuda.is_available() and pred.is_cuda: - calculate_loss_func = sigmoid_focal_loss - else: - num_classes = pred.size(1) - target = F.one_hot(target, num_classes=num_classes + 1) - target = target[:, :num_classes] - calculate_loss_func = py_sigmoid_focal_loss - - loss_cls = self.loss_weight * calculate_loss_func( - pred, - target, - weight, - gamma=self.gamma, - alpha=self.alpha, - reduction=reduction, - avg_factor=avg_factor) - - else: - raise NotImplementedError - return loss_cls diff --git a/spaces/tomofi/NDLOCR/src/ndl_layout/mmdetection/tests/test_models/test_roi_heads/utils.py b/spaces/tomofi/NDLOCR/src/ndl_layout/mmdetection/tests/test_models/test_roi_heads/utils.py deleted file mode 100644 index e5c6d58fcb1ce3e1d6def9070b61680670b39d58..0000000000000000000000000000000000000000 --- a/spaces/tomofi/NDLOCR/src/ndl_layout/mmdetection/tests/test_models/test_roi_heads/utils.py +++ /dev/null @@ -1,37 +0,0 @@ -import torch - -from mmdet.core import build_assigner, build_sampler - - -def _dummy_bbox_sampling(proposal_list, gt_bboxes, gt_labels): - """Create sample results that can be passed to BBoxHead.get_targets.""" - num_imgs = 1 - feat = torch.rand(1, 1, 3, 3) - assign_config = dict( - type='MaxIoUAssigner', - pos_iou_thr=0.5, - neg_iou_thr=0.5, - min_pos_iou=0.5, - ignore_iof_thr=-1) - sampler_config = dict( - type='RandomSampler', - num=512, - pos_fraction=0.25, - neg_pos_ub=-1, - add_gt_as_proposals=True) - bbox_assigner = build_assigner(assign_config) - bbox_sampler = build_sampler(sampler_config) - gt_bboxes_ignore = [None for _ in range(num_imgs)] - sampling_results = [] - for i in range(num_imgs): - assign_result = bbox_assigner.assign(proposal_list[i], gt_bboxes[i], - gt_bboxes_ignore[i], gt_labels[i]) - sampling_result = bbox_sampler.sample( - assign_result, - proposal_list[i], - gt_bboxes[i], - gt_labels[i], - feats=feat) - sampling_results.append(sampling_result) - - return sampling_results diff --git a/spaces/tomofi/NDLOCR/src/ndl_layout/mmdetection/tests/test_onnx/test_neck.py b/spaces/tomofi/NDLOCR/src/ndl_layout/mmdetection/tests/test_onnx/test_neck.py deleted file mode 100644 index f16a3dcc8597bbd09c5bb4656a93531438b83eb0..0000000000000000000000000000000000000000 --- a/spaces/tomofi/NDLOCR/src/ndl_layout/mmdetection/tests/test_onnx/test_neck.py +++ /dev/null @@ -1,162 +0,0 @@ -import os.path as osp - -import mmcv -import pytest -import torch - -from mmdet import digit_version -from mmdet.models.necks import FPN, YOLOV3Neck -from .utils import ort_validate - -if digit_version(torch.__version__) <= digit_version('1.5.0'): - pytest.skip( - 'ort backend does not support version below 1.5.0', - allow_module_level=True) - -# Control the returned model of fpn_neck_config() -fpn_test_step_names = { - 'fpn_normal': 0, - 'fpn_wo_extra_convs': 1, - 'fpn_lateral_bns': 2, - 'fpn_bilinear_upsample': 3, - 'fpn_scale_factor': 4, - 'fpn_extra_convs_inputs': 5, - 'fpn_extra_convs_laterals': 6, - 'fpn_extra_convs_outputs': 7, -} - -# Control the returned model of yolo_neck_config() -yolo_test_step_names = {'yolo_normal': 0} - -data_path = osp.join(osp.dirname(__file__), 'data') - - -def fpn_neck_config(test_step_name): - """Return the class containing the corresponding attributes according to - the fpn_test_step_names.""" - s = 64 - in_channels = [8, 16, 32, 64] - feat_sizes = [s // 2**i for i in range(4)] # [64, 32, 16, 8] - out_channels = 8 - - feats = [ - torch.rand(1, in_channels[i], feat_sizes[i], feat_sizes[i]) - for i in range(len(in_channels)) - ] - - if (fpn_test_step_names[test_step_name] == 0): - fpn_model = FPN( - in_channels=in_channels, - out_channels=out_channels, - add_extra_convs=True, - num_outs=5) - elif (fpn_test_step_names[test_step_name] == 1): - fpn_model = FPN( - in_channels=in_channels, - out_channels=out_channels, - add_extra_convs=False, - num_outs=5) - elif (fpn_test_step_names[test_step_name] == 2): - fpn_model = FPN( - in_channels=in_channels, - out_channels=out_channels, - add_extra_convs=True, - no_norm_on_lateral=False, - norm_cfg=dict(type='BN', requires_grad=True), - num_outs=5) - elif (fpn_test_step_names[test_step_name] == 3): - fpn_model = FPN( - in_channels=in_channels, - out_channels=out_channels, - add_extra_convs=True, - upsample_cfg=dict(mode='bilinear', align_corners=True), - num_outs=5) - elif (fpn_test_step_names[test_step_name] == 4): - fpn_model = FPN( - in_channels=in_channels, - out_channels=out_channels, - add_extra_convs=True, - upsample_cfg=dict(scale_factor=2), - num_outs=5) - elif (fpn_test_step_names[test_step_name] == 5): - fpn_model = FPN( - in_channels=in_channels, - out_channels=out_channels, - add_extra_convs='on_input', - num_outs=5) - elif (fpn_test_step_names[test_step_name] == 6): - fpn_model = FPN( - in_channels=in_channels, - out_channels=out_channels, - add_extra_convs='on_lateral', - num_outs=5) - elif (fpn_test_step_names[test_step_name] == 7): - fpn_model = FPN( - in_channels=in_channels, - out_channels=out_channels, - add_extra_convs='on_output', - num_outs=5) - return fpn_model, feats - - -def yolo_neck_config(test_step_name): - """Config yolov3 Neck.""" - in_channels = [16, 8, 4] - out_channels = [8, 4, 2] - - # The data of yolov3_neck.pkl contains a list of - # torch.Tensor, where each torch.Tensor is generated by - # torch.rand and each tensor size is: - # (1, 4, 64, 64), (1, 8, 32, 32), (1, 16, 16, 16). - yolov3_neck_data = 'yolov3_neck.pkl' - feats = mmcv.load(osp.join(data_path, yolov3_neck_data)) - - if (yolo_test_step_names[test_step_name] == 0): - yolo_model = YOLOV3Neck( - in_channels=in_channels, out_channels=out_channels, num_scales=3) - return yolo_model, feats - - -def test_fpn_normal(): - outs = fpn_neck_config('fpn_normal') - ort_validate(*outs) - - -def test_fpn_wo_extra_convs(): - outs = fpn_neck_config('fpn_wo_extra_convs') - ort_validate(*outs) - - -def test_fpn_lateral_bns(): - outs = fpn_neck_config('fpn_lateral_bns') - ort_validate(*outs) - - -def test_fpn_bilinear_upsample(): - outs = fpn_neck_config('fpn_bilinear_upsample') - ort_validate(*outs) - - -def test_fpn_scale_factor(): - outs = fpn_neck_config('fpn_scale_factor') - ort_validate(*outs) - - -def test_fpn_extra_convs_inputs(): - outs = fpn_neck_config('fpn_extra_convs_inputs') - ort_validate(*outs) - - -def test_fpn_extra_convs_laterals(): - outs = fpn_neck_config('fpn_extra_convs_laterals') - ort_validate(*outs) - - -def test_fpn_extra_convs_outputs(): - outs = fpn_neck_config('fpn_extra_convs_outputs') - ort_validate(*outs) - - -def test_yolo_normal(): - outs = yolo_neck_config('yolo_normal') - ort_validate(*outs) diff --git a/spaces/tracinginsights/api/README.md b/spaces/tracinginsights/api/README.md deleted file mode 100644 index cbaa3b106102218cdf2733db2d44454fde916c0b..0000000000000000000000000000000000000000 --- a/spaces/tracinginsights/api/README.md +++ /dev/null @@ -1,10 +0,0 @@ ---- -title: Api -emoji: 👁 -colorFrom: purple -colorTo: green -sdk: docker -pinned: false ---- - -Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference diff --git a/spaces/unday/bing/Dockerfile b/spaces/unday/bing/Dockerfile deleted file mode 100644 index 3698c7cb7938e025afc53b18a571ae2961fbdffe..0000000000000000000000000000000000000000 --- a/spaces/unday/bing/Dockerfile +++ /dev/null @@ -1,34 +0,0 @@ -# Build Stage -# 使用 golang:alpine 作为构建阶段的基础镜像 -FROM golang:alpine AS builder - -# 添加 git，以便之后能从GitHub克隆项目 -RUN apk --no-cache add git - -# 从 GitHub 克隆 go-proxy-bingai 项目到 /workspace/app 目录下 -RUN git clone https://github.com/Harry-zklcdc/go-proxy-bingai.git /workspace/app - -# 设置工作目录为之前克隆的项目目录 -WORKDIR /workspace/app - -# 编译 go 项目。-ldflags="-s -w" 是为了减少编译后的二进制大小 -RUN go build -ldflags="-s -w" -tags netgo -trimpath -o go-proxy-bingai main.go - -# Runtime Stage -# 使用轻量级的 alpine 镜像作为运行时的基础镜像 -FROM alpine - -# 设置工作目录 -WORKDIR /workspace/app - -# 从构建阶段复制编译后的二进制文件到运行时镜像中 -COPY --from=builder /workspace/app/go-proxy-bingai . - -# 设置环境变量，此处为随机字符 -ENV Go_Proxy_BingAI_USER_TOKEN_1="kJs8hD92ncMzLaoQWYtX5rG6bE3fZ4iO" - -# 暴露8080端口 -EXPOSE 8080 - -# 容器启动时运行的命令 -CMD ["/workspace/app/go-proxy-bingai"] \ No newline at end of file diff --git a/spaces/usbethFlerru/sovits-modelsV2/example/Baaghi 2 Movie Full In Tamil Hd 1080p A Spectacular Show of Stunts Chases and Explosions.md b/spaces/usbethFlerru/sovits-modelsV2/example/Baaghi 2 Movie Full In Tamil Hd 1080p A Spectacular Show of Stunts Chases and Explosions.md deleted file mode 100644 index d03af1d348713500f37457f377a01a637646ba13..0000000000000000000000000000000000000000 --- a/spaces/usbethFlerru/sovits-modelsV2/example/Baaghi 2 Movie Full In Tamil Hd 1080p A Spectacular Show of Stunts Chases and Explosions.md +++ /dev/null @@ -1,6 +0,0 @@ -

      Baaghi 2 Movie Full In Tamil Hd 1080p


      DOWNLOAD ————— https://urlcod.com/2uyXsm



      -
      - aaccfb2cb3
      -
      -
      -

      diff --git a/spaces/usbethFlerru/sovits-modelsV2/example/Becker Z201 Software Downloaden.md b/spaces/usbethFlerru/sovits-modelsV2/example/Becker Z201 Software Downloaden.md deleted file mode 100644 index e989c02520bafb96786f6722daffc8d45f005470..0000000000000000000000000000000000000000 --- a/spaces/usbethFlerru/sovits-modelsV2/example/Becker Z201 Software Downloaden.md +++ /dev/null @@ -1,6 +0,0 @@ -

      Becker Z201 Software Downloaden


      DOWNLOAD ○○○ https://urlcod.com/2uyWti



      - - 4d29de3e1b
      -
      -
      -

      diff --git a/spaces/user238921933/stable-diffusion-webui/extensions/deforum/scripts/deforum_helpers/src/clipseg/datasets/pfe_dataset.py b/spaces/user238921933/stable-diffusion-webui/extensions/deforum/scripts/deforum_helpers/src/clipseg/datasets/pfe_dataset.py deleted file mode 100644 index 83988dea963a2c4226010a336573de94bf06c55e..0000000000000000000000000000000000000000 --- a/spaces/user238921933/stable-diffusion-webui/extensions/deforum/scripts/deforum_helpers/src/clipseg/datasets/pfe_dataset.py +++ /dev/null @@ -1,129 +0,0 @@ -from os.path import expanduser -import torch -import json -from general_utils import get_from_repository -from datasets.lvis_oneshot3 import blend_image_segmentation -from general_utils import log - -PASCAL_CLASSES = {a['id']: a['synonyms'] for a in json.load(open('datasets/pascal_classes.json'))} - - -class PFEPascalWrapper(object): - - def __init__(self, mode, split, mask='separate', image_size=473, label_support=None, size=None, p_negative=0, aug=None): - import sys - # sys.path.append(expanduser('~/projects/new_one_shot')) - from third_party.PFENet.util.dataset import SemData - - get_from_repository('PascalVOC2012', ['Pascal5i.tar']) - - self.p_negative = p_negative - self.size = size - self.mode = mode - self.image_size = image_size - - if label_support in {True, False}: - log.warning('label_support argument is deprecated. Use mask instead.') - #raise ValueError() - - self.mask = mask - - value_scale = 255 - mean = [0.485, 0.456, 0.406] - mean = [item * value_scale for item in mean] - std = [0.229, 0.224, 0.225] - std = [item * value_scale for item in std] - - import third_party.PFENet.util.transform as transform - - if mode == 'val': - data_list = expanduser('~/projects/old_one_shot/PFENet/lists/pascal/val.txt') - - data_transform = [transform.test_Resize(size=image_size)] if image_size != 'original' else [] - data_transform += [ - transform.ToTensor(), - transform.Normalize(mean=mean, std=std) - ] - - - elif mode == 'train': - data_list = expanduser('~/projects/old_one_shot/PFENet/lists/pascal/voc_sbd_merge_noduplicate.txt') - - assert image_size != 'original' - - data_transform = [ - transform.RandScale([0.9, 1.1]), - transform.RandRotate([-10, 10], padding=mean, ignore_label=255), - transform.RandomGaussianBlur(), - transform.RandomHorizontalFlip(), - transform.Crop((image_size, image_size), crop_type='rand', padding=mean, ignore_label=255), - transform.ToTensor(), - transform.Normalize(mean=mean, std=std) - ] - - data_transform = transform.Compose(data_transform) - - self.dataset = SemData(split=split, mode=mode, data_root=expanduser('~/datasets/PascalVOC2012/VOC2012'), - data_list=data_list, shot=1, transform=data_transform, use_coco=False, use_split_coco=False) - - self.class_list = self.dataset.sub_val_list if mode == 'val' else self.dataset.sub_list - - # verify that subcls_list always has length 1 - # assert len(set([len(d[4]) for d in self.dataset])) == 1 - - print('actual length', len(self.dataset.data_list)) - - def __len__(self): - if self.mode == 'val': - return len(self.dataset.data_list) - else: - return len(self.dataset.data_list) - - def __getitem__(self, index): - if self.dataset.mode == 'train': - image, label, s_x, s_y, subcls_list = self.dataset[index % len(self.dataset.data_list)] - elif self.dataset.mode == 'val': - image, label, s_x, s_y, subcls_list, ori_label = self.dataset[index % len(self.dataset.data_list)] - ori_label = torch.from_numpy(ori_label).unsqueeze(0) - - if self.image_size != 'original': - longerside = max(ori_label.size(1), ori_label.size(2)) - backmask = torch.ones(ori_label.size(0), longerside, longerside).cuda()*255 - backmask[0, :ori_label.size(1), :ori_label.size(2)] = ori_label - label = backmask.clone().long() - else: - label = label.unsqueeze(0) - - # assert label.shape == (473, 473) - - if self.p_negative > 0: - if torch.rand(1).item() < self.p_negative: - while True: - idx = torch.randint(0, len(self.dataset.data_list), (1,)).item() - _, _, s_x, s_y, subcls_list_tmp, _ = self.dataset[idx] - if subcls_list[0] != subcls_list_tmp[0]: - break - - s_x = s_x[0] - s_y = (s_y == 1)[0] - label_fg = (label == 1).float() - val_mask = (label != 255).float() - - class_id = self.class_list[subcls_list[0]] - - label_name = PASCAL_CLASSES[class_id][0] - label_add = () - mask = self.mask - - if mask == 'text': - support = ('a photo of a ' + label_name + '.',) - elif mask == 'separate': - support = (s_x, s_y) - else: - if mask.startswith('text_and_'): - label_add = (label_name,) - mask = mask[9:] - - support = (blend_image_segmentation(s_x, s_y.float(), mask)[0],) - - return (image,) + label_add + support, (label_fg.unsqueeze(0), val_mask.unsqueeze(0), subcls_list[0]) diff --git a/spaces/vaishanthr/Simultaneous-Segmented-Depth-Prediction/yolov8/docs/reference/vit/sam/autosize.md b/spaces/vaishanthr/Simultaneous-Segmented-Depth-Prediction/yolov8/docs/reference/vit/sam/autosize.md deleted file mode 100644 index cbb0ca7c055fa680ffc9080a0c4d4db650134327..0000000000000000000000000000000000000000 --- a/spaces/vaishanthr/Simultaneous-Segmented-Depth-Prediction/yolov8/docs/reference/vit/sam/autosize.md +++ /dev/null @@ -1,9 +0,0 @@ ---- -description: Learn how to use the ResizeLongestSide module in Ultralytics YOLO for automatic image resizing. Resize your images with ease. -keywords: ResizeLongestSide, Ultralytics YOLO, automatic image resizing, image resizing ---- - -## ResizeLongestSide ---- -### ::: ultralytics.vit.sam.autosize.ResizeLongestSide -

      \ No newline at end of file diff --git a/spaces/vinay123/panoptic-segment-anything/GroundingDINO/groundingdino/models/GroundingDINO/utils.py b/spaces/vinay123/panoptic-segment-anything/GroundingDINO/groundingdino/models/GroundingDINO/utils.py deleted file mode 100644 index 5bd18f70225e12b2e27fdb4eabcde91d959f8e31..0000000000000000000000000000000000000000 --- a/spaces/vinay123/panoptic-segment-anything/GroundingDINO/groundingdino/models/GroundingDINO/utils.py +++ /dev/null @@ -1,268 +0,0 @@ -# ------------------------------------------------------------------------ -# Grounding DINO -# url: https://github.com/IDEA-Research/GroundingDINO -# Copyright (c) 2023 IDEA. All Rights Reserved. -# Licensed under the Apache License, Version 2.0 [see LICENSE for details] -# ------------------------------------------------------------------------ - -import copy -import math - -import torch -import torch.nn.functional as F -from torch import Tensor, nn - - -def _get_clones(module, N, layer_share=False): - # import ipdb; ipdb.set_trace() - if layer_share: - return nn.ModuleList([module for i in range(N)]) - else: - return nn.ModuleList([copy.deepcopy(module) for i in range(N)]) - - -def get_sine_pos_embed( - pos_tensor: torch.Tensor, - num_pos_feats: int = 128, - temperature: int = 10000, - exchange_xy: bool = True, -): - """generate sine position embedding from a position tensor - Args: - pos_tensor (torch.Tensor): shape: [..., n]. - num_pos_feats (int): projected shape for each float in the tensor. - temperature (int): temperature in the sine/cosine function. - exchange_xy (bool, optional): exchange pos x and pos y. \ - For example, input tensor is [x,y], the results will be [pos(y), pos(x)]. Defaults to True. - Returns: - pos_embed (torch.Tensor): shape: [..., n*num_pos_feats]. - """ - scale = 2 * math.pi - dim_t = torch.arange(num_pos_feats, dtype=torch.float32, device=pos_tensor.device) - dim_t = temperature ** (2 * torch.div(dim_t, 2, rounding_mode="floor") / num_pos_feats) - - def sine_func(x: torch.Tensor): - sin_x = x * scale / dim_t - sin_x = torch.stack((sin_x[..., 0::2].sin(), sin_x[..., 1::2].cos()), dim=3).flatten(2) - return sin_x - - pos_res = [sine_func(x) for x in pos_tensor.split([1] * pos_tensor.shape[-1], dim=-1)] - if exchange_xy: - pos_res[0], pos_res[1] = pos_res[1], pos_res[0] - pos_res = torch.cat(pos_res, dim=-1) - return pos_res - - -def gen_encoder_output_proposals( - memory: Tensor, memory_padding_mask: Tensor, spatial_shapes: Tensor, learnedwh=None -): - """ - Input: - - memory: bs, \sum{hw}, d_model - - memory_padding_mask: bs, \sum{hw} - - spatial_shapes: nlevel, 2 - - learnedwh: 2 - Output: - - output_memory: bs, \sum{hw}, d_model - - output_proposals: bs, \sum{hw}, 4 - """ - N_, S_, C_ = memory.shape - proposals = [] - _cur = 0 - for lvl, (H_, W_) in enumerate(spatial_shapes): - mask_flatten_ = memory_padding_mask[:, _cur : (_cur + H_ * W_)].view(N_, H_, W_, 1) - valid_H = torch.sum(~mask_flatten_[:, :, 0, 0], 1) - valid_W = torch.sum(~mask_flatten_[:, 0, :, 0], 1) - - # import ipdb; ipdb.set_trace() - - grid_y, grid_x = torch.meshgrid( - torch.linspace(0, H_ - 1, H_, dtype=torch.float32, device=memory.device), - torch.linspace(0, W_ - 1, W_, dtype=torch.float32, device=memory.device), - ) - grid = torch.cat([grid_x.unsqueeze(-1), grid_y.unsqueeze(-1)], -1) # H_, W_, 2 - - scale = torch.cat([valid_W.unsqueeze(-1), valid_H.unsqueeze(-1)], 1).view(N_, 1, 1, 2) - grid = (grid.unsqueeze(0).expand(N_, -1, -1, -1) + 0.5) / scale - - if learnedwh is not None: - # import ipdb; ipdb.set_trace() - wh = torch.ones_like(grid) * learnedwh.sigmoid() * (2.0**lvl) - else: - wh = torch.ones_like(grid) * 0.05 * (2.0**lvl) - - # scale = torch.cat([W_[None].unsqueeze(-1), H_[None].unsqueeze(-1)], 1).view(1, 1, 1, 2).repeat(N_, 1, 1, 1) - # grid = (grid.unsqueeze(0).expand(N_, -1, -1, -1) + 0.5) / scale - # wh = torch.ones_like(grid) / scale - proposal = torch.cat((grid, wh), -1).view(N_, -1, 4) - proposals.append(proposal) - _cur += H_ * W_ - # import ipdb; ipdb.set_trace() - output_proposals = torch.cat(proposals, 1) - output_proposals_valid = ((output_proposals > 0.01) & (output_proposals < 0.99)).all( - -1, keepdim=True - ) - output_proposals = torch.log(output_proposals / (1 - output_proposals)) # unsigmoid - output_proposals = output_proposals.masked_fill(memory_padding_mask.unsqueeze(-1), float("inf")) - output_proposals = output_proposals.masked_fill(~output_proposals_valid, float("inf")) - - output_memory = memory - output_memory = output_memory.masked_fill(memory_padding_mask.unsqueeze(-1), float(0)) - output_memory = output_memory.masked_fill(~output_proposals_valid, float(0)) - - # output_memory = output_memory.masked_fill(memory_padding_mask.unsqueeze(-1), float('inf')) - # output_memory = output_memory.masked_fill(~output_proposals_valid, float('inf')) - - return output_memory, output_proposals - - -class RandomBoxPerturber: - def __init__( - self, x_noise_scale=0.2, y_noise_scale=0.2, w_noise_scale=0.2, h_noise_scale=0.2 - ) -> None: - self.noise_scale = torch.Tensor( - [x_noise_scale, y_noise_scale, w_noise_scale, h_noise_scale] - ) - - def __call__(self, refanchors: Tensor) -> Tensor: - nq, bs, query_dim = refanchors.shape - device = refanchors.device - - noise_raw = torch.rand_like(refanchors) - noise_scale = self.noise_scale.to(device)[:query_dim] - - new_refanchors = refanchors * (1 + (noise_raw - 0.5) * noise_scale) - return new_refanchors.clamp_(0, 1) - - -def sigmoid_focal_loss( - inputs, targets, num_boxes, alpha: float = 0.25, gamma: float = 2, no_reduction=False -): - """ - Loss used in RetinaNet for dense detection: https://arxiv.org/abs/1708.02002. - Args: - inputs: A float tensor of arbitrary shape. - The predictions for each example. - targets: A float tensor with the same shape as inputs. Stores the binary - classification label for each element in inputs - (0 for the negative class and 1 for the positive class). - alpha: (optional) Weighting factor in range (0,1) to balance - positive vs negative examples. Default = -1 (no weighting). - gamma: Exponent of the modulating factor (1 - p_t) to - balance easy vs hard examples. - Returns: - Loss tensor - """ - prob = inputs.sigmoid() - ce_loss = F.binary_cross_entropy_with_logits(inputs, targets, reduction="none") - p_t = prob * targets + (1 - prob) * (1 - targets) - loss = ce_loss * ((1 - p_t) ** gamma) - - if alpha >= 0: - alpha_t = alpha * targets + (1 - alpha) * (1 - targets) - loss = alpha_t * loss - - if no_reduction: - return loss - - return loss.mean(1).sum() / num_boxes - - -class MLP(nn.Module): - """Very simple multi-layer perceptron (also called FFN)""" - - def __init__(self, input_dim, hidden_dim, output_dim, num_layers): - super().__init__() - self.num_layers = num_layers - h = [hidden_dim] * (num_layers - 1) - self.layers = nn.ModuleList( - nn.Linear(n, k) for n, k in zip([input_dim] + h, h + [output_dim]) - ) - - def forward(self, x): - for i, layer in enumerate(self.layers): - x = F.relu(layer(x)) if i < self.num_layers - 1 else layer(x) - return x - - -def _get_activation_fn(activation, d_model=256, batch_dim=0): - """Return an activation function given a string""" - if activation == "relu": - return F.relu - if activation == "gelu": - return F.gelu - if activation == "glu": - return F.glu - if activation == "prelu": - return nn.PReLU() - if activation == "selu": - return F.selu - - raise RuntimeError(f"activation should be relu/gelu, not {activation}.") - - -def gen_sineembed_for_position(pos_tensor): - # n_query, bs, _ = pos_tensor.size() - # sineembed_tensor = torch.zeros(n_query, bs, 256) - scale = 2 * math.pi - dim_t = torch.arange(128, dtype=torch.float32, device=pos_tensor.device) - dim_t = 10000 ** (2 * (torch.div(dim_t, 2, rounding_mode='floor')) / 128) - x_embed = pos_tensor[:, :, 0] * scale - y_embed = pos_tensor[:, :, 1] * scale - pos_x = x_embed[:, :, None] / dim_t - pos_y = y_embed[:, :, None] / dim_t - pos_x = torch.stack((pos_x[:, :, 0::2].sin(), pos_x[:, :, 1::2].cos()), dim=3).flatten(2) - pos_y = torch.stack((pos_y[:, :, 0::2].sin(), pos_y[:, :, 1::2].cos()), dim=3).flatten(2) - if pos_tensor.size(-1) == 2: - pos = torch.cat((pos_y, pos_x), dim=2) - elif pos_tensor.size(-1) == 4: - w_embed = pos_tensor[:, :, 2] * scale - pos_w = w_embed[:, :, None] / dim_t - pos_w = torch.stack((pos_w[:, :, 0::2].sin(), pos_w[:, :, 1::2].cos()), dim=3).flatten(2) - - h_embed = pos_tensor[:, :, 3] * scale - pos_h = h_embed[:, :, None] / dim_t - pos_h = torch.stack((pos_h[:, :, 0::2].sin(), pos_h[:, :, 1::2].cos()), dim=3).flatten(2) - - pos = torch.cat((pos_y, pos_x, pos_w, pos_h), dim=2) - else: - raise ValueError("Unknown pos_tensor shape(-1):{}".format(pos_tensor.size(-1))) - return pos - - -class ContrastiveEmbed(nn.Module): - def __init__(self, max_text_len=256): - """ - Args: - max_text_len: max length of text. - """ - super().__init__() - self.max_text_len = max_text_len - - def forward(self, x, text_dict): - """_summary_ - - Args: - x (_type_): _description_ - text_dict (_type_): _description_ - { - 'encoded_text': encoded_text, # bs, 195, d_model - 'text_token_mask': text_token_mask, # bs, 195 - # True for used tokens. False for padding tokens - } - Returns: - _type_: _description_ - """ - assert isinstance(text_dict, dict) - - y = text_dict["encoded_text"] - text_token_mask = text_dict["text_token_mask"] - - res = x @ y.transpose(-1, -2) - res.masked_fill_(~text_token_mask[:, None, :], float("-inf")) - - # padding to max_text_len - new_res = torch.full((*res.shape[:-1], self.max_text_len), float("-inf"), device=res.device) - new_res[..., : res.shape[-1]] = res - - return new_res diff --git a/spaces/vonbarnekowa/stable-diffusion/ldm/models/diffusion/dpm_solver/sampler.py b/spaces/vonbarnekowa/stable-diffusion/ldm/models/diffusion/dpm_solver/sampler.py deleted file mode 100644 index 7d137b8cf36718c1c58faa09f9dd919e5fb2977b..0000000000000000000000000000000000000000 --- a/spaces/vonbarnekowa/stable-diffusion/ldm/models/diffusion/dpm_solver/sampler.py +++ /dev/null @@ -1,87 +0,0 @@ -"""SAMPLING ONLY.""" -import torch - -from .dpm_solver import NoiseScheduleVP, model_wrapper, DPM_Solver - - -MODEL_TYPES = { - "eps": "noise", - "v": "v" -} - - -class DPMSolverSampler(object): - def __init__(self, model, **kwargs): - super().__init__() - self.model = model - to_torch = lambda x: x.clone().detach().to(torch.float32).to(model.device) - self.register_buffer('alphas_cumprod', to_torch(model.alphas_cumprod)) - - def register_buffer(self, name, attr): - if type(attr) == torch.Tensor: - if attr.device != torch.device("cuda"): - attr = attr.to(torch.device("cuda")) - setattr(self, name, attr) - - @torch.no_grad() - def sample(self, - S, - batch_size, - shape, - conditioning=None, - callback=None, - normals_sequence=None, - img_callback=None, - quantize_x0=False, - eta=0., - mask=None, - x0=None, - temperature=1., - noise_dropout=0., - score_corrector=None, - corrector_kwargs=None, - verbose=True, - x_T=None, - log_every_t=100, - unconditional_guidance_scale=1., - unconditional_conditioning=None, - # this has to come in the same format as the conditioning, # e.g. as encoded tokens, ... - **kwargs - ): - if conditioning is not None: - if isinstance(conditioning, dict): - cbs = conditioning[list(conditioning.keys())[0]].shape[0] - if cbs != batch_size: - print(f"Warning: Got {cbs} conditionings but batch-size is {batch_size}") - else: - if conditioning.shape[0] != batch_size: - print(f"Warning: Got {conditioning.shape[0]} conditionings but batch-size is {batch_size}") - - # sampling - C, H, W = shape - size = (batch_size, C, H, W) - - print(f'Data shape for DPM-Solver sampling is {size}, sampling steps {S}') - - device = self.model.betas.device - if x_T is None: - img = torch.randn(size, device=device) - else: - img = x_T - - ns = NoiseScheduleVP('discrete', alphas_cumprod=self.alphas_cumprod) - - model_fn = model_wrapper( - lambda x, t, c: self.model.apply_model(x, t, c), - ns, - model_type=MODEL_TYPES[self.model.parameterization], - guidance_type="classifier-free", - condition=conditioning, - unconditional_condition=unconditional_conditioning, - guidance_scale=unconditional_guidance_scale, - ) - - dpm_solver = DPM_Solver(model_fn, ns, predict_x0=True, thresholding=False) - x = dpm_solver.sample(img, steps=S, skip_type="time_uniform", method="multistep", order=2, lower_order_final=True) - - return x.to(device), None \ No newline at end of file diff --git a/spaces/vorstcavry/vits-models-1/inference_main.py b/spaces/vorstcavry/vits-models-1/inference_main.py deleted file mode 100644 index 3b2c32ac9e29e6b016e656e937fede5d2c23e7e6..0000000000000000000000000000000000000000 --- a/spaces/vorstcavry/vits-models-1/inference_main.py +++ /dev/null @@ -1,130 +0,0 @@ -import io -import logging -import time -from pathlib import Path - -import librosa -import matplotlib.pyplot as plt -import numpy as np -import soundfile - -from inference import infer_tool -from inference import slicer -from inference.infer_tool import Svc - -logging.getLogger('numba').setLevel(logging.WARNING) -chunks_dict = infer_tool.read_temp("inference/chunks_temp.json") - - - -def main(): - import argparse - - parser = argparse.ArgumentParser(description='sovits4 inference') - - # 一定要设置的部分 - parser.add_argument('-m', '--model_path', type=str, default="logs/44k/G_0.pth", help='模型路径') - parser.add_argument('-c', '--config_path', type=str, default="configs/config.json", help='配置文件路径') - parser.add_argument('-cl', '--clip', type=float, default=0, help='音频强制切片，默认0为自动切片，单位为秒/s') - parser.add_argument('-n', '--clean_names', type=str, nargs='+', default=["君の知らない物語-src.wav"], help='wav文件名列表，放在raw文件夹下') - parser.add_argument('-t', '--trans', type=int, nargs='+', default=[0], help='音高调整，支持正负（半音）') - parser.add_argument('-s', '--spk_list', type=str, nargs='+', default=['nen'], help='合成目标说话人名称') - - # 可选项部分 - parser.add_argument('-a', '--auto_predict_f0', action='store_true', default=False,help='语音转换自动预测音高，转换歌声时不要打开这个会严重跑调') - parser.add_argument('-cm', '--cluster_model_path', type=str, default="logs/44k/kmeans_10000.pt", help='聚类模型路径，如果没有训练聚类则随便填') - parser.add_argument('-cr', '--cluster_infer_ratio', type=float, default=0, help='聚类方案占比，范围0-1，若没有训练聚类模型则默认0即可') - parser.add_argument('-lg', '--linear_gradient', type=float, default=0, help='两段音频切片的交叉淡入长度，如果强制切片后出现人声不连贯可调整该数值，如果连贯建议采用默认值0，单位为秒') - parser.add_argument('-fmp', '--f0_mean_pooling', type=bool, default=False, help='是否对F0使用均值滤波器(池化)，对部分哑音有改善。注意，启动该选项会导致推理速度下降，默认关闭') - - # 不用动的部分 - parser.add_argument('-sd', '--slice_db', type=int, default=-40, help='默认-40，嘈杂的音频可以-30，干声保留呼吸可以-50') - parser.add_argument('-d', '--device', type=str, default=None, help='推理设备，None则为自动选择cpu和gpu') - parser.add_argument('-ns', '--noice_scale', type=float, default=0.4, help='噪音级别，会影响咬字和音质，较为玄学') - parser.add_argument('-p', '--pad_seconds', type=float, default=0.5, help='推理音频pad秒数，由于未知原因开头结尾会有异响，pad一小段静音段后就不会出现') - parser.add_argument('-wf', '--wav_format', type=str, default='flac', help='音频输出格式') - parser.add_argument('-lgr', '--linear_gradient_retain', type=float, default=0.75, help='自动音频切片后，需要舍弃每段切片的头尾。该参数设置交叉长度保留的比例，范围0-1,左开右闭') - - args = parser.parse_args() - - svc_model = Svc(args.model_path, args.config_path, args.device, args.cluster_model_path) - infer_tool.mkdir(["raw", "results"]) - clean_names = args.clean_names - trans = args.trans - spk_list = args.spk_list - slice_db = args.slice_db - wav_format = args.wav_format - auto_predict_f0 = args.auto_predict_f0 - cluster_infer_ratio = args.cluster_infer_ratio - noice_scale = args.noice_scale - pad_seconds = args.pad_seconds - clip = args.clip - lg = args.linear_gradient - lgr = args.linear_gradient_retain - F0_mean_pooling = args.f0_mean_pooling - - infer_tool.fill_a_to_b(trans, clean_names) - for clean_name, tran in zip(clean_names, trans): - raw_audio_path = f"raw/{clean_name}" - if "." not in raw_audio_path: - raw_audio_path += ".wav" - infer_tool.format_wav(raw_audio_path) - wav_path = Path(raw_audio_path).with_suffix('.wav') - chunks = slicer.cut(wav_path, db_thresh=slice_db) - audio_data, audio_sr = slicer.chunks2audio(wav_path, chunks) - per_size = int(clip*audio_sr) - lg_size = int(lg*audio_sr) - lg_size_r = int(lg_size*lgr) - lg_size_c_l = (lg_size-lg_size_r)//2 - lg_size_c_r = lg_size-lg_size_r-lg_size_c_l - lg = np.linspace(0,1,lg_size_r) if lg_size!=0 else 0 - - for spk in spk_list: - audio = [] - for (slice_tag, data) in audio_data: - print(f'#=====segment start, {round(len(data) / audio_sr, 3)}s======') - - length = int(np.ceil(len(data) / audio_sr * svc_model.target_sample)) - if slice_tag: - print('jump empty segment') - _audio = np.zeros(length) - audio.extend(list(infer_tool.pad_array(_audio, length))) - continue - if per_size != 0: - datas = infer_tool.split_list_by_n(data, per_size,lg_size) - else: - datas = [data] - for k,dat in enumerate(datas): - per_length = int(np.ceil(len(dat) / audio_sr * svc_model.target_sample)) if clip!=0 else length - if clip!=0: print(f'###=====segment clip start, {round(len(dat) / audio_sr, 3)}s======') - # padd - pad_len = int(audio_sr * pad_seconds) - dat = np.concatenate([np.zeros([pad_len]), dat, np.zeros([pad_len])]) - raw_path = io.BytesIO() - soundfile.write(raw_path, dat, audio_sr, format="wav") - raw_path.seek(0) - out_audio, out_sr = svc_model.infer(spk, tran, raw_path, - cluster_infer_ratio=cluster_infer_ratio, - auto_predict_f0=auto_predict_f0, - noice_scale=noice_scale, - F0_mean_pooling = F0_mean_pooling - ) - _audio = out_audio.cpu().numpy() - pad_len = int(svc_model.target_sample * pad_seconds) - _audio = _audio[pad_len:-pad_len] - _audio = infer_tool.pad_array(_audio, per_length) - if lg_size!=0 and k!=0: - lg1 = audio[-(lg_size_r+lg_size_c_r):-lg_size_c_r] if lgr != 1 else audio[-lg_size:] - lg2 = _audio[lg_size_c_l:lg_size_c_l+lg_size_r] if lgr != 1 else _audio[0:lg_size] - lg_pre = lg1*(1-lg)+lg2*lg - audio = audio[0:-(lg_size_r+lg_size_c_r)] if lgr != 1 else audio[0:-lg_size] - audio.extend(lg_pre) - _audio = _audio[lg_size_c_l+lg_size_r:] if lgr != 1 else _audio[lg_size:] - audio.extend(list(_audio)) - key = "auto" if auto_predict_f0 else f"{tran}key" - cluster_name = "" if cluster_infer_ratio == 0 else f"_{cluster_infer_ratio}" - res_path = f'./results/{clean_name}_{key}_{spk}{cluster_name}.{wav_format}' - soundfile.write(res_path, audio, svc_model.target_sample, format=wav_format) - -if __name__ == '__main__': - main() diff --git a/spaces/vumichien/canvas_controlnet/annotator/uniformer/configs/_base_/datasets/pascal_voc12_aug.py b/spaces/vumichien/canvas_controlnet/annotator/uniformer/configs/_base_/datasets/pascal_voc12_aug.py deleted file mode 100644 index 3f23b6717d53ad29f02dd15046802a2631a5076b..0000000000000000000000000000000000000000 --- a/spaces/vumichien/canvas_controlnet/annotator/uniformer/configs/_base_/datasets/pascal_voc12_aug.py +++ /dev/null @@ -1,9 +0,0 @@ -_base_ = './pascal_voc12.py' -# dataset settings -data = dict( - train=dict( - ann_dir=['SegmentationClass', 'SegmentationClassAug'], - split=[ - 'ImageSets/Segmentation/train.txt', - 'ImageSets/Segmentation/aug.txt' - ])) diff --git a/spaces/vumichien/canvas_controlnet/annotator/uniformer/mmseg/datasets/stare.py b/spaces/vumichien/canvas_controlnet/annotator/uniformer/mmseg/datasets/stare.py deleted file mode 100644 index cbd14e0920e7f6a73baff1432e5a32ccfdb0dfae..0000000000000000000000000000000000000000 --- a/spaces/vumichien/canvas_controlnet/annotator/uniformer/mmseg/datasets/stare.py +++ /dev/null @@ -1,27 +0,0 @@ -import os.path as osp - -from .builder import DATASETS -from .custom import CustomDataset - - -@DATASETS.register_module() -class STAREDataset(CustomDataset): - """STARE dataset. - - In segmentation map annotation for STARE, 0 stands for background, which is - included in 2 categories. ``reduce_zero_label`` is fixed to False. The - ``img_suffix`` is fixed to '.png' and ``seg_map_suffix`` is fixed to - '.ah.png'. - """ - - CLASSES = ('background', 'vessel') - - PALETTE = [[120, 120, 120], [6, 230, 230]] - - def __init__(self, **kwargs): - super(STAREDataset, self).__init__( - img_suffix='.png', - seg_map_suffix='.ah.png', - reduce_zero_label=False, - **kwargs) - assert osp.exists(self.img_dir) diff --git a/spaces/weanalyze/analyze_url/README.md b/spaces/weanalyze/analyze_url/README.md deleted file mode 100644 index d27582317c51ef850708dc5f9ce4997d349aabbe..0000000000000000000000000000000000000000 --- a/spaces/weanalyze/analyze_url/README.md +++ /dev/null @@ -1,10 +0,0 @@ ---- -title: Analyze Url -emoji: 🚀 -colorFrom: green -colorTo: pink -sdk: docker -pinned: false ---- - -Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference diff --git a/spaces/weibinke/vits-simple-api/static/css/bootstrap.min.css b/spaces/weibinke/vits-simple-api/static/css/bootstrap.min.css deleted file mode 100644 index 83a71b1f50721c12da8e13b8d476cad8ec471e92..0000000000000000000000000000000000000000 --- a/spaces/weibinke/vits-simple-api/static/css/bootstrap.min.css +++ /dev/null @@ -1,7 +0,0 @@ -/*! - * Bootstrap v4.6.2 (https://getbootstrap.com/) - * Copyright 2011-2022 The Bootstrap Authors - * Copyright 2011-2022 Twitter, Inc. - * Licensed under MIT (https://github.com/twbs/bootstrap/blob/main/LICENSE) - */:root{--blue:#007bff;--indigo:#6610f2;--purple:#6f42c1;--pink:#e83e8c;--red:#dc3545;--orange:#fd7e14;--yellow:#ffc107;--green:#28a745;--teal:#20c997;--cyan:#17a2b8;--white:#fff;--gray:#6c757d;--gray-dark:#343a40;--primary:#007bff;--secondary:#6c757d;--success:#28a745;--info:#17a2b8;--warning:#ffc107;--danger:#dc3545;--light:#f8f9fa;--dark:#343a40;--breakpoint-xs:0;--breakpoint-sm:576px;--breakpoint-md:768px;--breakpoint-lg:992px;--breakpoint-xl:1200px;--font-family-sans-serif:-apple-system,BlinkMacSystemFont,"Segoe UI",Roboto,"Helvetica Neue",Arial,"Noto Sans","Liberation Sans",sans-serif,"Apple Color Emoji","Segoe UI Emoji","Segoe UI Symbol","Noto Color Emoji";--font-family-monospace:SFMono-Regular,Menlo,Monaco,Consolas,"Liberation Mono","Courier New",monospace}*,::after,::before{box-sizing:border-box}html{font-family:sans-serif;line-height:1.15;-webkit-text-size-adjust:100%;-webkit-tap-highlight-color:transparent}article,aside,figcaption,figure,footer,header,hgroup,main,nav,section{display:block}body{margin:0;font-family:-apple-system,BlinkMacSystemFont,"Segoe UI",Roboto,"Helvetica Neue",Arial,"Noto Sans","Liberation Sans",sans-serif,"Apple Color Emoji","Segoe UI Emoji","Segoe UI Symbol","Noto Color Emoji";font-size:1rem;font-weight:400;line-height:1.5;color:#212529;text-align:left;background-color:#fff}[tabindex="-1"]:focus:not(:focus-visible){outline:0!important}hr{box-sizing:content-box;height:0;overflow:visible}h1,h2,h3,h4,h5,h6{margin-top:0;margin-bottom:.5rem}p{margin-top:0;margin-bottom:1rem}abbr[data-original-title],abbr[title]{text-decoration:underline;-webkit-text-decoration:underline dotted;text-decoration:underline dotted;cursor:help;border-bottom:0;-webkit-text-decoration-skip-ink:none;text-decoration-skip-ink:none}address{margin-bottom:1rem;font-style:normal;line-height:inherit}dl,ol,ul{margin-top:0;margin-bottom:1rem}ol ol,ol ul,ul ol,ul ul{margin-bottom:0}dt{font-weight:700}dd{margin-bottom:.5rem;margin-left:0}blockquote{margin:0 0 1rem}b,strong{font-weight:bolder}small{font-size:80%}sub,sup{position:relative;font-size:75%;line-height:0;vertical-align:baseline}sub{bottom:-.25em}sup{top:-.5em}a{color:#007bff;text-decoration:none;background-color:transparent}a:hover{color:#0056b3;text-decoration:underline}a:not([href]):not([class]){color:inherit;text-decoration:none}a:not([href]):not([class]):hover{color:inherit;text-decoration:none}code,kbd,pre,samp{font-family:SFMono-Regular,Menlo,Monaco,Consolas,"Liberation Mono","Courier New",monospace;font-size:1em}pre{margin-top:0;margin-bottom:1rem;overflow:auto;-ms-overflow-style:scrollbar}figure{margin:0 0 1rem}img{vertical-align:middle;border-style:none}svg{overflow:hidden;vertical-align:middle}table{border-collapse:collapse}caption{padding-top:.75rem;padding-bottom:.75rem;color:#6c757d;text-align:left;caption-side:bottom}th{text-align:inherit;text-align:-webkit-match-parent}label{display:inline-block;margin-bottom:.5rem}button{border-radius:0}button:focus:not(:focus-visible){outline:0}button,input,optgroup,select,textarea{margin:0;font-family:inherit;font-size:inherit;line-height:inherit}button,input{overflow:visible}button,select{text-transform:none}[role=button]{cursor:pointer}select{word-wrap:normal}[type=button],[type=reset],[type=submit],button{-webkit-appearance:button}[type=button]:not(:disabled),[type=reset]:not(:disabled),[type=submit]:not(:disabled),button:not(:disabled){cursor:pointer}[type=button]::-moz-focus-inner,[type=reset]::-moz-focus-inner,[type=submit]::-moz-focus-inner,button::-moz-focus-inner{padding:0;border-style:none}input[type=checkbox],input[type=radio]{box-sizing:border-box;padding:0}textarea{overflow:auto;resize:vertical}fieldset{min-width:0;padding:0;margin:0;border:0}legend{display:block;width:100%;max-width:100%;padding:0;margin-bottom:.5rem;font-size:1.5rem;line-height:inherit;color:inherit;white-space:normal}progress{vertical-align:baseline}[type=number]::-webkit-inner-spin-button,[type=number]::-webkit-outer-spin-button{height:auto}[type=search]{outline-offset:-2px;-webkit-appearance:none}[type=search]::-webkit-search-decoration{-webkit-appearance:none}::-webkit-file-upload-button{font:inherit;-webkit-appearance:button}output{display:inline-block}summary{display:list-item;cursor:pointer}template{display:none}[hidden]{display:none!important}.h1,.h2,.h3,.h4,.h5,.h6,h1,h2,h3,h4,h5,h6{margin-bottom:.5rem;font-weight:500;line-height:1.2}.h1,h1{font-size:2.5rem}.h2,h2{font-size:2rem}.h3,h3{font-size:1.75rem}.h4,h4{font-size:1.5rem}.h5,h5{font-size:1.25rem}.h6,h6{font-size:1rem}.lead{font-size:1.25rem;font-weight:300}.display-1{font-size:6rem;font-weight:300;line-height:1.2}.display-2{font-size:5.5rem;font-weight:300;line-height:1.2}.display-3{font-size:4.5rem;font-weight:300;line-height:1.2}.display-4{font-size:3.5rem;font-weight:300;line-height:1.2}hr{margin-top:1rem;margin-bottom:1rem;border:0;border-top:1px solid rgba(0,0,0,.1)}.small,small{font-size:.875em;font-weight:400}.mark,mark{padding:.2em;background-color:#fcf8e3}.list-unstyled{padding-left:0;list-style:none}.list-inline{padding-left:0;list-style:none}.list-inline-item{display:inline-block}.list-inline-item:not(:last-child){margin-right:.5rem}.initialism{font-size:90%;text-transform:uppercase}.blockquote{margin-bottom:1rem;font-size:1.25rem}.blockquote-footer{display:block;font-size:.875em;color:#6c757d}.blockquote-footer::before{content:"\2014\00A0"}.img-fluid{max-width:100%;height:auto}.img-thumbnail{padding:.25rem;background-color:#fff;border:1px solid #dee2e6;border-radius:.25rem;max-width:100%;height:auto}.figure{display:inline-block}.figure-img{margin-bottom:.5rem;line-height:1}.figure-caption{font-size:90%;color:#6c757d}code{font-size:87.5%;color:#e83e8c;word-wrap:break-word}a>code{color:inherit}kbd{padding:.2rem .4rem;font-size:87.5%;color:#fff;background-color:#212529;border-radius:.2rem}kbd kbd{padding:0;font-size:100%;font-weight:700}pre{display:block;font-size:87.5%;color:#212529}pre code{font-size:inherit;color:inherit;word-break:normal}.pre-scrollable{max-height:340px;overflow-y:scroll}.container,.container-fluid,.container-lg,.container-md,.container-sm,.container-xl{width:100%;padding-right:15px;padding-left:15px;margin-right:auto;margin-left:auto}@media (min-width:576px){.container,.container-sm{max-width:540px}}@media (min-width:768px){.container,.container-md,.container-sm{max-width:720px}}@media (min-width:992px){.container,.container-lg,.container-md,.container-sm{max-width:960px}}@media (min-width:1200px){.container,.container-lg,.container-md,.container-sm,.container-xl{max-width:1140px}}.row{display:-ms-flexbox;display:flex;-ms-flex-wrap:wrap;flex-wrap:wrap;margin-right:-15px;margin-left:-15px}.no-gutters{margin-right:0;margin-left:0}.no-gutters>.col,.no-gutters>[class*=col-]{padding-right:0;padding-left:0}.col,.col-1,.col-10,.col-11,.col-12,.col-2,.col-3,.col-4,.col-5,.col-6,.col-7,.col-8,.col-9,.col-auto,.col-lg,.col-lg-1,.col-lg-10,.col-lg-11,.col-lg-12,.col-lg-2,.col-lg-3,.col-lg-4,.col-lg-5,.col-lg-6,.col-lg-7,.col-lg-8,.col-lg-9,.col-lg-auto,.col-md,.col-md-1,.col-md-10,.col-md-11,.col-md-12,.col-md-2,.col-md-3,.col-md-4,.col-md-5,.col-md-6,.col-md-7,.col-md-8,.col-md-9,.col-md-auto,.col-sm,.col-sm-1,.col-sm-10,.col-sm-11,.col-sm-12,.col-sm-2,.col-sm-3,.col-sm-4,.col-sm-5,.col-sm-6,.col-sm-7,.col-sm-8,.col-sm-9,.col-sm-auto,.col-xl,.col-xl-1,.col-xl-10,.col-xl-11,.col-xl-12,.col-xl-2,.col-xl-3,.col-xl-4,.col-xl-5,.col-xl-6,.col-xl-7,.col-xl-8,.col-xl-9,.col-xl-auto{position:relative;width:100%;padding-right:15px;padding-left:15px}.col{-ms-flex-preferred-size:0;flex-basis:0;-ms-flex-positive:1;flex-grow:1;max-width:100%}.row-cols-1>*{-ms-flex:0 0 100%;flex:0 0 100%;max-width:100%}.row-cols-2>*{-ms-flex:0 0 50%;flex:0 0 50%;max-width:50%}.row-cols-3>*{-ms-flex:0 0 33.333333%;flex:0 0 33.333333%;max-width:33.333333%}.row-cols-4>*{-ms-flex:0 0 25%;flex:0 0 25%;max-width:25%}.row-cols-5>*{-ms-flex:0 0 20%;flex:0 0 20%;max-width:20%}.row-cols-6>*{-ms-flex:0 0 16.666667%;flex:0 0 16.666667%;max-width:16.666667%}.col-auto{-ms-flex:0 0 auto;flex:0 0 auto;width:auto;max-width:100%}.col-1{-ms-flex:0 0 8.333333%;flex:0 0 8.333333%;max-width:8.333333%}.col-2{-ms-flex:0 0 16.666667%;flex:0 0 16.666667%;max-width:16.666667%}.col-3{-ms-flex:0 0 25%;flex:0 0 25%;max-width:25%}.col-4{-ms-flex:0 0 33.333333%;flex:0 0 33.333333%;max-width:33.333333%}.col-5{-ms-flex:0 0 41.666667%;flex:0 0 41.666667%;max-width:41.666667%}.col-6{-ms-flex:0 0 50%;flex:0 0 50%;max-width:50%}.col-7{-ms-flex:0 0 58.333333%;flex:0 0 58.333333%;max-width:58.333333%}.col-8{-ms-flex:0 0 66.666667%;flex:0 0 66.666667%;max-width:66.666667%}.col-9{-ms-flex:0 0 75%;flex:0 0 75%;max-width:75%}.col-10{-ms-flex:0 0 83.333333%;flex:0 0 83.333333%;max-width:83.333333%}.col-11{-ms-flex:0 0 91.666667%;flex:0 0 91.666667%;max-width:91.666667%}.col-12{-ms-flex:0 0 100%;flex:0 0 100%;max-width:100%}.order-first{-ms-flex-order:-1;order:-1}.order-last{-ms-flex-order:13;order:13}.order-0{-ms-flex-order:0;order:0}.order-1{-ms-flex-order:1;order:1}.order-2{-ms-flex-order:2;order:2}.order-3{-ms-flex-order:3;order:3}.order-4{-ms-flex-order:4;order:4}.order-5{-ms-flex-order:5;order:5}.order-6{-ms-flex-order:6;order:6}.order-7{-ms-flex-order:7;order:7}.order-8{-ms-flex-order:8;order:8}.order-9{-ms-flex-order:9;order:9}.order-10{-ms-flex-order:10;order:10}.order-11{-ms-flex-order:11;order:11}.order-12{-ms-flex-order:12;order:12}.offset-1{margin-left:8.333333%}.offset-2{margin-left:16.666667%}.offset-3{margin-left:25%}.offset-4{margin-left:33.333333%}.offset-5{margin-left:41.666667%}.offset-6{margin-left:50%}.offset-7{margin-left:58.333333%}.offset-8{margin-left:66.666667%}.offset-9{margin-left:75%}.offset-10{margin-left:83.333333%}.offset-11{margin-left:91.666667%}@media (min-width:576px){.col-sm{-ms-flex-preferred-size:0;flex-basis:0;-ms-flex-positive:1;flex-grow:1;max-width:100%}.row-cols-sm-1>*{-ms-flex:0 0 100%;flex:0 0 100%;max-width:100%}.row-cols-sm-2>*{-ms-flex:0 0 50%;flex:0 0 50%;max-width:50%}.row-cols-sm-3>*{-ms-flex:0 0 33.333333%;flex:0 0 33.333333%;max-width:33.333333%}.row-cols-sm-4>*{-ms-flex:0 0 25%;flex:0 0 25%;max-width:25%}.row-cols-sm-5>*{-ms-flex:0 0 20%;flex:0 0 20%;max-width:20%}.row-cols-sm-6>*{-ms-flex:0 0 16.666667%;flex:0 0 16.666667%;max-width:16.666667%}.col-sm-auto{-ms-flex:0 0 auto;flex:0 0 auto;width:auto;max-width:100%}.col-sm-1{-ms-flex:0 0 8.333333%;flex:0 0 8.333333%;max-width:8.333333%}.col-sm-2{-ms-flex:0 0 16.666667%;flex:0 0 16.666667%;max-width:16.666667%}.col-sm-3{-ms-flex:0 0 25%;flex:0 0 25%;max-width:25%}.col-sm-4{-ms-flex:0 0 33.333333%;flex:0 0 33.333333%;max-width:33.333333%}.col-sm-5{-ms-flex:0 0 41.666667%;flex:0 0 41.666667%;max-width:41.666667%}.col-sm-6{-ms-flex:0 0 50%;flex:0 0 50%;max-width:50%}.col-sm-7{-ms-flex:0 0 58.333333%;flex:0 0 58.333333%;max-width:58.333333%}.col-sm-8{-ms-flex:0 0 66.666667%;flex:0 0 66.666667%;max-width:66.666667%}.col-sm-9{-ms-flex:0 0 75%;flex:0 0 75%;max-width:75%}.col-sm-10{-ms-flex:0 0 83.333333%;flex:0 0 83.333333%;max-width:83.333333%}.col-sm-11{-ms-flex:0 0 91.666667%;flex:0 0 91.666667%;max-width:91.666667%}.col-sm-12{-ms-flex:0 0 100%;flex:0 0 100%;max-width:100%}.order-sm-first{-ms-flex-order:-1;order:-1}.order-sm-last{-ms-flex-order:13;order:13}.order-sm-0{-ms-flex-order:0;order:0}.order-sm-1{-ms-flex-order:1;order:1}.order-sm-2{-ms-flex-order:2;order:2}.order-sm-3{-ms-flex-order:3;order:3}.order-sm-4{-ms-flex-order:4;order:4}.order-sm-5{-ms-flex-order:5;order:5}.order-sm-6{-ms-flex-order:6;order:6}.order-sm-7{-ms-flex-order:7;order:7}.order-sm-8{-ms-flex-order:8;order:8}.order-sm-9{-ms-flex-order:9;order:9}.order-sm-10{-ms-flex-order:10;order:10}.order-sm-11{-ms-flex-order:11;order:11}.order-sm-12{-ms-flex-order:12;order:12}.offset-sm-0{margin-left:0}.offset-sm-1{margin-left:8.333333%}.offset-sm-2{margin-left:16.666667%}.offset-sm-3{margin-left:25%}.offset-sm-4{margin-left:33.333333%}.offset-sm-5{margin-left:41.666667%}.offset-sm-6{margin-left:50%}.offset-sm-7{margin-left:58.333333%}.offset-sm-8{margin-left:66.666667%}.offset-sm-9{margin-left:75%}.offset-sm-10{margin-left:83.333333%}.offset-sm-11{margin-left:91.666667%}}@media (min-width:768px){.col-md{-ms-flex-preferred-size:0;flex-basis:0;-ms-flex-positive:1;flex-grow:1;max-width:100%}.row-cols-md-1>*{-ms-flex:0 0 100%;flex:0 0 100%;max-width:100%}.row-cols-md-2>*{-ms-flex:0 0 50%;flex:0 0 50%;max-width:50%}.row-cols-md-3>*{-ms-flex:0 0 33.333333%;flex:0 0 33.333333%;max-width:33.333333%}.row-cols-md-4>*{-ms-flex:0 0 25%;flex:0 0 25%;max-width:25%}.row-cols-md-5>*{-ms-flex:0 0 20%;flex:0 0 20%;max-width:20%}.row-cols-md-6>*{-ms-flex:0 0 16.666667%;flex:0 0 16.666667%;max-width:16.666667%}.col-md-auto{-ms-flex:0 0 auto;flex:0 0 auto;width:auto;max-width:100%}.col-md-1{-ms-flex:0 0 8.333333%;flex:0 0 8.333333%;max-width:8.333333%}.col-md-2{-ms-flex:0 0 16.666667%;flex:0 0 16.666667%;max-width:16.666667%}.col-md-3{-ms-flex:0 0 25%;flex:0 0 25%;max-width:25%}.col-md-4{-ms-flex:0 0 33.333333%;flex:0 0 33.333333%;max-width:33.333333%}.col-md-5{-ms-flex:0 0 41.666667%;flex:0 0 41.666667%;max-width:41.666667%}.col-md-6{-ms-flex:0 0 50%;flex:0 0 50%;max-width:50%}.col-md-7{-ms-flex:0 0 58.333333%;flex:0 0 58.333333%;max-width:58.333333%}.col-md-8{-ms-flex:0 0 66.666667%;flex:0 0 66.666667%;max-width:66.666667%}.col-md-9{-ms-flex:0 0 75%;flex:0 0 75%;max-width:75%}.col-md-10{-ms-flex:0 0 83.333333%;flex:0 0 83.333333%;max-width:83.333333%}.col-md-11{-ms-flex:0 0 91.666667%;flex:0 0 91.666667%;max-width:91.666667%}.col-md-12{-ms-flex:0 0 100%;flex:0 0 100%;max-width:100%}.order-md-first{-ms-flex-order:-1;order:-1}.order-md-last{-ms-flex-order:13;order:13}.order-md-0{-ms-flex-order:0;order:0}.order-md-1{-ms-flex-order:1;order:1}.order-md-2{-ms-flex-order:2;order:2}.order-md-3{-ms-flex-order:3;order:3}.order-md-4{-ms-flex-order:4;order:4}.order-md-5{-ms-flex-order:5;order:5}.order-md-6{-ms-flex-order:6;order:6}.order-md-7{-ms-flex-order:7;order:7}.order-md-8{-ms-flex-order:8;order:8}.order-md-9{-ms-flex-order:9;order:9}.order-md-10{-ms-flex-order:10;order:10}.order-md-11{-ms-flex-order:11;order:11}.order-md-12{-ms-flex-order:12;order:12}.offset-md-0{margin-left:0}.offset-md-1{margin-left:8.333333%}.offset-md-2{margin-left:16.666667%}.offset-md-3{margin-left:25%}.offset-md-4{margin-left:33.333333%}.offset-md-5{margin-left:41.666667%}.offset-md-6{margin-left:50%}.offset-md-7{margin-left:58.333333%}.offset-md-8{margin-left:66.666667%}.offset-md-9{margin-left:75%}.offset-md-10{margin-left:83.333333%}.offset-md-11{margin-left:91.666667%}}@media (min-width:992px){.col-lg{-ms-flex-preferred-size:0;flex-basis:0;-ms-flex-positive:1;flex-grow:1;max-width:100%}.row-cols-lg-1>*{-ms-flex:0 0 100%;flex:0 0 100%;max-width:100%}.row-cols-lg-2>*{-ms-flex:0 0 50%;flex:0 0 50%;max-width:50%}.row-cols-lg-3>*{-ms-flex:0 0 33.333333%;flex:0 0 33.333333%;max-width:33.333333%}.row-cols-lg-4>*{-ms-flex:0 0 25%;flex:0 0 25%;max-width:25%}.row-cols-lg-5>*{-ms-flex:0 0 20%;flex:0 0 20%;max-width:20%}.row-cols-lg-6>*{-ms-flex:0 0 16.666667%;flex:0 0 16.666667%;max-width:16.666667%}.col-lg-auto{-ms-flex:0 0 auto;flex:0 0 auto;width:auto;max-width:100%}.col-lg-1{-ms-flex:0 0 8.333333%;flex:0 0 8.333333%;max-width:8.333333%}.col-lg-2{-ms-flex:0 0 16.666667%;flex:0 0 16.666667%;max-width:16.666667%}.col-lg-3{-ms-flex:0 0 25%;flex:0 0 25%;max-width:25%}.col-lg-4{-ms-flex:0 0 33.333333%;flex:0 0 33.333333%;max-width:33.333333%}.col-lg-5{-ms-flex:0 0 41.666667%;flex:0 0 41.666667%;max-width:41.666667%}.col-lg-6{-ms-flex:0 0 50%;flex:0 0 50%;max-width:50%}.col-lg-7{-ms-flex:0 0 58.333333%;flex:0 0 58.333333%;max-width:58.333333%}.col-lg-8{-ms-flex:0 0 66.666667%;flex:0 0 66.666667%;max-width:66.666667%}.col-lg-9{-ms-flex:0 0 75%;flex:0 0 75%;max-width:75%}.col-lg-10{-ms-flex:0 0 83.333333%;flex:0 0 83.333333%;max-width:83.333333%}.col-lg-11{-ms-flex:0 0 91.666667%;flex:0 0 91.666667%;max-width:91.666667%}.col-lg-12{-ms-flex:0 0 100%;flex:0 0 100%;max-width:100%}.order-lg-first{-ms-flex-order:-1;order:-1}.order-lg-last{-ms-flex-order:13;order:13}.order-lg-0{-ms-flex-order:0;order:0}.order-lg-1{-ms-flex-order:1;order:1}.order-lg-2{-ms-flex-order:2;order:2}.order-lg-3{-ms-flex-order:3;order:3}.order-lg-4{-ms-flex-order:4;order:4}.order-lg-5{-ms-flex-order:5;order:5}.order-lg-6{-ms-flex-order:6;order:6}.order-lg-7{-ms-flex-order:7;order:7}.order-lg-8{-ms-flex-order:8;order:8}.order-lg-9{-ms-flex-order:9;order:9}.order-lg-10{-ms-flex-order:10;order:10}.order-lg-11{-ms-flex-order:11;order:11}.order-lg-12{-ms-flex-order:12;order:12}.offset-lg-0{margin-left:0}.offset-lg-1{margin-left:8.333333%}.offset-lg-2{margin-left:16.666667%}.offset-lg-3{margin-left:25%}.offset-lg-4{margin-left:33.333333%}.offset-lg-5{margin-left:41.666667%}.offset-lg-6{margin-left:50%}.offset-lg-7{margin-left:58.333333%}.offset-lg-8{margin-left:66.666667%}.offset-lg-9{margin-left:75%}.offset-lg-10{margin-left:83.333333%}.offset-lg-11{margin-left:91.666667%}}@media (min-width:1200px){.col-xl{-ms-flex-preferred-size:0;flex-basis:0;-ms-flex-positive:1;flex-grow:1;max-width:100%}.row-cols-xl-1>*{-ms-flex:0 0 100%;flex:0 0 100%;max-width:100%}.row-cols-xl-2>*{-ms-flex:0 0 50%;flex:0 0 50%;max-width:50%}.row-cols-xl-3>*{-ms-flex:0 0 33.333333%;flex:0 0 33.333333%;max-width:33.333333%}.row-cols-xl-4>*{-ms-flex:0 0 25%;flex:0 0 25%;max-width:25%}.row-cols-xl-5>*{-ms-flex:0 0 20%;flex:0 0 20%;max-width:20%}.row-cols-xl-6>*{-ms-flex:0 0 16.666667%;flex:0 0 16.666667%;max-width:16.666667%}.col-xl-auto{-ms-flex:0 0 auto;flex:0 0 auto;width:auto;max-width:100%}.col-xl-1{-ms-flex:0 0 8.333333%;flex:0 0 8.333333%;max-width:8.333333%}.col-xl-2{-ms-flex:0 0 16.666667%;flex:0 0 16.666667%;max-width:16.666667%}.col-xl-3{-ms-flex:0 0 25%;flex:0 0 25%;max-width:25%}.col-xl-4{-ms-flex:0 0 33.333333%;flex:0 0 33.333333%;max-width:33.333333%}.col-xl-5{-ms-flex:0 0 41.666667%;flex:0 0 41.666667%;max-width:41.666667%}.col-xl-6{-ms-flex:0 0 50%;flex:0 0 50%;max-width:50%}.col-xl-7{-ms-flex:0 0 58.333333%;flex:0 0 58.333333%;max-width:58.333333%}.col-xl-8{-ms-flex:0 0 66.666667%;flex:0 0 66.666667%;max-width:66.666667%}.col-xl-9{-ms-flex:0 0 75%;flex:0 0 75%;max-width:75%}.col-xl-10{-ms-flex:0 0 83.333333%;flex:0 0 83.333333%;max-width:83.333333%}.col-xl-11{-ms-flex:0 0 91.666667%;flex:0 0 91.666667%;max-width:91.666667%}.col-xl-12{-ms-flex:0 0 100%;flex:0 0 100%;max-width:100%}.order-xl-first{-ms-flex-order:-1;order:-1}.order-xl-last{-ms-flex-order:13;order:13}.order-xl-0{-ms-flex-order:0;order:0}.order-xl-1{-ms-flex-order:1;order:1}.order-xl-2{-ms-flex-order:2;order:2}.order-xl-3{-ms-flex-order:3;order:3}.order-xl-4{-ms-flex-order:4;order:4}.order-xl-5{-ms-flex-order:5;order:5}.order-xl-6{-ms-flex-order:6;order:6}.order-xl-7{-ms-flex-order:7;order:7}.order-xl-8{-ms-flex-order:8;order:8}.order-xl-9{-ms-flex-order:9;order:9}.order-xl-10{-ms-flex-order:10;order:10}.order-xl-11{-ms-flex-order:11;order:11}.order-xl-12{-ms-flex-order:12;order:12}.offset-xl-0{margin-left:0}.offset-xl-1{margin-left:8.333333%}.offset-xl-2{margin-left:16.666667%}.offset-xl-3{margin-left:25%}.offset-xl-4{margin-left:33.333333%}.offset-xl-5{margin-left:41.666667%}.offset-xl-6{margin-left:50%}.offset-xl-7{margin-left:58.333333%}.offset-xl-8{margin-left:66.666667%}.offset-xl-9{margin-left:75%}.offset-xl-10{margin-left:83.333333%}.offset-xl-11{margin-left:91.666667%}}.table{width:100%;margin-bottom:1rem;color:#212529}.table td,.table th{padding:.75rem;vertical-align:top;border-top:1px solid #dee2e6}.table thead th{vertical-align:bottom;border-bottom:2px solid #dee2e6}.table tbody+tbody{border-top:2px solid #dee2e6}.table-sm td,.table-sm th{padding:.3rem}.table-bordered{border:1px solid #dee2e6}.table-bordered td,.table-bordered th{border:1px solid #dee2e6}.table-bordered thead td,.table-bordered thead th{border-bottom-width:2px}.table-borderless tbody+tbody,.table-borderless td,.table-borderless th,.table-borderless thead th{border:0}.table-striped tbody tr:nth-of-type(odd){background-color:rgba(0,0,0,.05)}.table-hover tbody tr:hover{color:#212529;background-color:rgba(0,0,0,.075)}.table-primary,.table-primary>td,.table-primary>th{background-color:#b8daff}.table-primary tbody+tbody,.table-primary td,.table-primary th,.table-primary thead th{border-color:#7abaff}.table-hover .table-primary:hover{background-color:#9fcdff}.table-hover .table-primary:hover>td,.table-hover .table-primary:hover>th{background-color:#9fcdff}.table-secondary,.table-secondary>td,.table-secondary>th{background-color:#d6d8db}.table-secondary tbody+tbody,.table-secondary td,.table-secondary th,.table-secondary thead th{border-color:#b3b7bb}.table-hover .table-secondary:hover{background-color:#c8cbcf}.table-hover .table-secondary:hover>td,.table-hover .table-secondary:hover>th{background-color:#c8cbcf}.table-success,.table-success>td,.table-success>th{background-color:#c3e6cb}.table-success tbody+tbody,.table-success td,.table-success th,.table-success thead th{border-color:#8fd19e}.table-hover .table-success:hover{background-color:#b1dfbb}.table-hover .table-success:hover>td,.table-hover .table-success:hover>th{background-color:#b1dfbb}.table-info,.table-info>td,.table-info>th{background-color:#bee5eb}.table-info tbody+tbody,.table-info td,.table-info th,.table-info thead th{border-color:#86cfda}.table-hover .table-info:hover{background-color:#abdde5}.table-hover .table-info:hover>td,.table-hover .table-info:hover>th{background-color:#abdde5}.table-warning,.table-warning>td,.table-warning>th{background-color:#ffeeba}.table-warning tbody+tbody,.table-warning td,.table-warning th,.table-warning thead th{border-color:#ffdf7e}.table-hover .table-warning:hover{background-color:#ffe8a1}.table-hover .table-warning:hover>td,.table-hover .table-warning:hover>th{background-color:#ffe8a1}.table-danger,.table-danger>td,.table-danger>th{background-color:#f5c6cb}.table-danger tbody+tbody,.table-danger td,.table-danger th,.table-danger thead th{border-color:#ed969e}.table-hover .table-danger:hover{background-color:#f1b0b7}.table-hover .table-danger:hover>td,.table-hover .table-danger:hover>th{background-color:#f1b0b7}.table-light,.table-light>td,.table-light>th{background-color:#fdfdfe}.table-light tbody+tbody,.table-light td,.table-light th,.table-light thead th{border-color:#fbfcfc}.table-hover .table-light:hover{background-color:#ececf6}.table-hover .table-light:hover>td,.table-hover .table-light:hover>th{background-color:#ececf6}.table-dark,.table-dark>td,.table-dark>th{background-color:#c6c8ca}.table-dark tbody+tbody,.table-dark td,.table-dark th,.table-dark thead th{border-color:#95999c}.table-hover .table-dark:hover{background-color:#b9bbbe}.table-hover .table-dark:hover>td,.table-hover .table-dark:hover>th{background-color:#b9bbbe}.table-active,.table-active>td,.table-active>th{background-color:rgba(0,0,0,.075)}.table-hover .table-active:hover{background-color:rgba(0,0,0,.075)}.table-hover .table-active:hover>td,.table-hover .table-active:hover>th{background-color:rgba(0,0,0,.075)}.table .thead-dark th{color:#fff;background-color:#343a40;border-color:#454d55}.table .thead-light th{color:#495057;background-color:#e9ecef;border-color:#dee2e6}.table-dark{color:#fff;background-color:#343a40}.table-dark td,.table-dark th,.table-dark thead th{border-color:#454d55}.table-dark.table-bordered{border:0}.table-dark.table-striped tbody tr:nth-of-type(odd){background-color:rgba(255,255,255,.05)}.table-dark.table-hover tbody tr:hover{color:#fff;background-color:rgba(255,255,255,.075)}@media (max-width:575.98px){.table-responsive-sm{display:block;width:100%;overflow-x:auto;-webkit-overflow-scrolling:touch}.table-responsive-sm>.table-bordered{border:0}}@media (max-width:767.98px){.table-responsive-md{display:block;width:100%;overflow-x:auto;-webkit-overflow-scrolling:touch}.table-responsive-md>.table-bordered{border:0}}@media (max-width:991.98px){.table-responsive-lg{display:block;width:100%;overflow-x:auto;-webkit-overflow-scrolling:touch}.table-responsive-lg>.table-bordered{border:0}}@media (max-width:1199.98px){.table-responsive-xl{display:block;width:100%;overflow-x:auto;-webkit-overflow-scrolling:touch}.table-responsive-xl>.table-bordered{border:0}}.table-responsive{display:block;width:100%;overflow-x:auto;-webkit-overflow-scrolling:touch}.table-responsive>.table-bordered{border:0}.form-control{display:block;width:100%;height:calc(1.5em + .75rem + 2px);padding:.375rem .75rem;font-size:1rem;font-weight:400;line-height:1.5;color:#495057;background-color:#fff;background-clip:padding-box;border:1px solid #ced4da;border-radius:.25rem;transition:border-color .15s ease-in-out,box-shadow .15s ease-in-out}@media (prefers-reduced-motion:reduce){.form-control{transition:none}}.form-control::-ms-expand{background-color:transparent;border:0}.form-control:focus{color:#495057;background-color:#fff;border-color:#80bdff;outline:0;box-shadow:0 0 0 .2rem rgba(0,123,255,.25)}.form-control::-webkit-input-placeholder{color:#6c757d;opacity:1}.form-control::-moz-placeholder{color:#6c757d;opacity:1}.form-control:-ms-input-placeholder{color:#6c757d;opacity:1}.form-control::-ms-input-placeholder{color:#6c757d;opacity:1}.form-control::placeholder{color:#6c757d;opacity:1}.form-control:disabled,.form-control[readonly]{background-color:#e9ecef;opacity:1}input[type=date].form-control,input[type=datetime-local].form-control,input[type=month].form-control,input[type=time].form-control{-webkit-appearance:none;-moz-appearance:none;appearance:none}select.form-control:-moz-focusring{color:transparent;text-shadow:0 0 0 #495057}select.form-control:focus::-ms-value{color:#495057;background-color:#fff}.form-control-file,.form-control-range{display:block;width:100%}.col-form-label{padding-top:calc(.375rem + 1px);padding-bottom:calc(.375rem + 1px);margin-bottom:0;font-size:inherit;line-height:1.5}.col-form-label-lg{padding-top:calc(.5rem + 1px);padding-bottom:calc(.5rem + 1px);font-size:1.25rem;line-height:1.5}.col-form-label-sm{padding-top:calc(.25rem + 1px);padding-bottom:calc(.25rem + 1px);font-size:.875rem;line-height:1.5}.form-control-plaintext{display:block;width:100%;padding:.375rem 0;margin-bottom:0;font-size:1rem;line-height:1.5;color:#212529;background-color:transparent;border:solid transparent;border-width:1px 0}.form-control-plaintext.form-control-lg,.form-control-plaintext.form-control-sm{padding-right:0;padding-left:0}.form-control-sm{height:calc(1.5em + .5rem + 2px);padding:.25rem .5rem;font-size:.875rem;line-height:1.5;border-radius:.2rem}.form-control-lg{height:calc(1.5em + 1rem + 2px);padding:.5rem 1rem;font-size:1.25rem;line-height:1.5;border-radius:.3rem}select.form-control[multiple],select.form-control[size]{height:auto}textarea.form-control{height:auto}.form-group{margin-bottom:1rem}.form-text{display:block;margin-top:.25rem}.form-row{display:-ms-flexbox;display:flex;-ms-flex-wrap:wrap;flex-wrap:wrap;margin-right:-5px;margin-left:-5px}.form-row>.col,.form-row>[class*=col-]{padding-right:5px;padding-left:5px}.form-check{position:relative;display:block;padding-left:1.25rem}.form-check-input{position:absolute;margin-top:.3rem;margin-left:-1.25rem}.form-check-input:disabled~.form-check-label,.form-check-input[disabled]~.form-check-label{color:#6c757d}.form-check-label{margin-bottom:0}.form-check-inline{display:-ms-inline-flexbox;display:inline-flex;-ms-flex-align:center;align-items:center;padding-left:0;margin-right:.75rem}.form-check-inline .form-check-input{position:static;margin-top:0;margin-right:.3125rem;margin-left:0}.valid-feedback{display:none;width:100%;margin-top:.25rem;font-size:.875em;color:#28a745}.valid-tooltip{position:absolute;top:100%;left:0;z-index:5;display:none;max-width:100%;padding:.25rem .5rem;margin-top:.1rem;font-size:.875rem;line-height:1.5;color:#fff;background-color:rgba(40,167,69,.9);border-radius:.25rem}.form-row>.col>.valid-tooltip,.form-row>[class*=col-]>.valid-tooltip{left:5px}.is-valid~.valid-feedback,.is-valid~.valid-tooltip,.was-validated :valid~.valid-feedback,.was-validated :valid~.valid-tooltip{display:block}.form-control.is-valid,.was-validated .form-control:valid{border-color:#28a745;padding-right:calc(1.5em + .75rem)!important;background-image:url("data:image/svg+xml,%3csvg xmlns='http://www.w3.org/2000/svg' width='8' height='8' viewBox='0 0 8 8'%3e%3cpath fill='%2328a745' d='M2.3 6.73L.6 4.53c-.4-1.04.46-1.4 1.1-.8l1.1 1.4 3.4-3.8c.6-.63 1.6-.27 1.2.7l-4 4.6c-.43.5-.8.4-1.1.1z'/%3e%3c/svg%3e");background-repeat:no-repeat;background-position:right calc(.375em + .1875rem) center;background-size:calc(.75em + .375rem) calc(.75em + .375rem)}.form-control.is-valid:focus,.was-validated .form-control:valid:focus{border-color:#28a745;box-shadow:0 0 0 .2rem rgba(40,167,69,.25)}.was-validated select.form-control:valid,select.form-control.is-valid{padding-right:3rem!important;background-position:right 1.5rem center}.was-validated textarea.form-control:valid,textarea.form-control.is-valid{padding-right:calc(1.5em + .75rem);background-position:top calc(.375em + .1875rem) right calc(.375em + .1875rem)}.custom-select.is-valid,.was-validated .custom-select:valid{border-color:#28a745;padding-right:calc(.75em + 2.3125rem)!important;background:url("data:image/svg+xml,%3csvg xmlns='http://www.w3.org/2000/svg' width='4' height='5' viewBox='0 0 4 5'%3e%3cpath fill='%23343a40' d='M2 0L0 2h4zm0 5L0 3h4z'/%3e%3c/svg%3e") right .75rem center/8px 10px no-repeat,#fff url("data:image/svg+xml,%3csvg xmlns='http://www.w3.org/2000/svg' width='8' height='8' viewBox='0 0 8 8'%3e%3cpath fill='%2328a745' d='M2.3 6.73L.6 4.53c-.4-1.04.46-1.4 1.1-.8l1.1 1.4 3.4-3.8c.6-.63 1.6-.27 1.2.7l-4 4.6c-.43.5-.8.4-1.1.1z'/%3e%3c/svg%3e") center right 1.75rem/calc(.75em + .375rem) calc(.75em + .375rem) no-repeat}.custom-select.is-valid:focus,.was-validated .custom-select:valid:focus{border-color:#28a745;box-shadow:0 0 0 .2rem rgba(40,167,69,.25)}.form-check-input.is-valid~.form-check-label,.was-validated .form-check-input:valid~.form-check-label{color:#28a745}.form-check-input.is-valid~.valid-feedback,.form-check-input.is-valid~.valid-tooltip,.was-validated .form-check-input:valid~.valid-feedback,.was-validated .form-check-input:valid~.valid-tooltip{display:block}.custom-control-input.is-valid~.custom-control-label,.was-validated .custom-control-input:valid~.custom-control-label{color:#28a745}.custom-control-input.is-valid~.custom-control-label::before,.was-validated .custom-control-input:valid~.custom-control-label::before{border-color:#28a745}.custom-control-input.is-valid:checked~.custom-control-label::before,.was-validated .custom-control-input:valid:checked~.custom-control-label::before{border-color:#34ce57;background-color:#34ce57}.custom-control-input.is-valid:focus~.custom-control-label::before,.was-validated .custom-control-input:valid:focus~.custom-control-label::before{box-shadow:0 0 0 .2rem rgba(40,167,69,.25)}.custom-control-input.is-valid:focus:not(:checked)~.custom-control-label::before,.was-validated .custom-control-input:valid:focus:not(:checked)~.custom-control-label::before{border-color:#28a745}.custom-file-input.is-valid~.custom-file-label,.was-validated .custom-file-input:valid~.custom-file-label{border-color:#28a745}.custom-file-input.is-valid:focus~.custom-file-label,.was-validated .custom-file-input:valid:focus~.custom-file-label{border-color:#28a745;box-shadow:0 0 0 .2rem rgba(40,167,69,.25)}.invalid-feedback{display:none;width:100%;margin-top:.25rem;font-size:.875em;color:#dc3545}.invalid-tooltip{position:absolute;top:100%;left:0;z-index:5;display:none;max-width:100%;padding:.25rem .5rem;margin-top:.1rem;font-size:.875rem;line-height:1.5;color:#fff;background-color:rgba(220,53,69,.9);border-radius:.25rem}.form-row>.col>.invalid-tooltip,.form-row>[class*=col-]>.invalid-tooltip{left:5px}.is-invalid~.invalid-feedback,.is-invalid~.invalid-tooltip,.was-validated :invalid~.invalid-feedback,.was-validated :invalid~.invalid-tooltip{display:block}.form-control.is-invalid,.was-validated .form-control:invalid{border-color:#dc3545;padding-right:calc(1.5em + .75rem)!important;background-image:url("data:image/svg+xml,%3csvg xmlns='http://www.w3.org/2000/svg' width='12' height='12' fill='none' stroke='%23dc3545' viewBox='0 0 12 12'%3e%3ccircle cx='6' cy='6' r='4.5'/%3e%3cpath stroke-linejoin='round' d='M5.8 3.6h.4L6 6.5z'/%3e%3ccircle cx='6' cy='8.2' r='.6' fill='%23dc3545' stroke='none'/%3e%3c/svg%3e");background-repeat:no-repeat;background-position:right calc(.375em + .1875rem) center;background-size:calc(.75em + .375rem) calc(.75em + .375rem)}.form-control.is-invalid:focus,.was-validated .form-control:invalid:focus{border-color:#dc3545;box-shadow:0 0 0 .2rem rgba(220,53,69,.25)}.was-validated select.form-control:invalid,select.form-control.is-invalid{padding-right:3rem!important;background-position:right 1.5rem center}.was-validated textarea.form-control:invalid,textarea.form-control.is-invalid{padding-right:calc(1.5em + .75rem);background-position:top calc(.375em + .1875rem) right calc(.375em + .1875rem)}.custom-select.is-invalid,.was-validated .custom-select:invalid{border-color:#dc3545;padding-right:calc(.75em + 2.3125rem)!important;background:url("data:image/svg+xml,%3csvg xmlns='http://www.w3.org/2000/svg' width='4' height='5' viewBox='0 0 4 5'%3e%3cpath fill='%23343a40' d='M2 0L0 2h4zm0 5L0 3h4z'/%3e%3c/svg%3e") right .75rem center/8px 10px no-repeat,#fff url("data:image/svg+xml,%3csvg xmlns='http://www.w3.org/2000/svg' width='12' height='12' fill='none' stroke='%23dc3545' viewBox='0 0 12 12'%3e%3ccircle cx='6' cy='6' r='4.5'/%3e%3cpath stroke-linejoin='round' d='M5.8 3.6h.4L6 6.5z'/%3e%3ccircle cx='6' cy='8.2' r='.6' fill='%23dc3545' stroke='none'/%3e%3c/svg%3e") center right 1.75rem/calc(.75em + .375rem) calc(.75em + .375rem) no-repeat}.custom-select.is-invalid:focus,.was-validated .custom-select:invalid:focus{border-color:#dc3545;box-shadow:0 0 0 .2rem rgba(220,53,69,.25)}.form-check-input.is-invalid~.form-check-label,.was-validated .form-check-input:invalid~.form-check-label{color:#dc3545}.form-check-input.is-invalid~.invalid-feedback,.form-check-input.is-invalid~.invalid-tooltip,.was-validated .form-check-input:invalid~.invalid-feedback,.was-validated .form-check-input:invalid~.invalid-tooltip{display:block}.custom-control-input.is-invalid~.custom-control-label,.was-validated .custom-control-input:invalid~.custom-control-label{color:#dc3545}.custom-control-input.is-invalid~.custom-control-label::before,.was-validated .custom-control-input:invalid~.custom-control-label::before{border-color:#dc3545}.custom-control-input.is-invalid:checked~.custom-control-label::before,.was-validated .custom-control-input:invalid:checked~.custom-control-label::before{border-color:#e4606d;background-color:#e4606d}.custom-control-input.is-invalid:focus~.custom-control-label::before,.was-validated .custom-control-input:invalid:focus~.custom-control-label::before{box-shadow:0 0 0 .2rem rgba(220,53,69,.25)}.custom-control-input.is-invalid:focus:not(:checked)~.custom-control-label::before,.was-validated .custom-control-input:invalid:focus:not(:checked)~.custom-control-label::before{border-color:#dc3545}.custom-file-input.is-invalid~.custom-file-label,.was-validated .custom-file-input:invalid~.custom-file-label{border-color:#dc3545}.custom-file-input.is-invalid:focus~.custom-file-label,.was-validated .custom-file-input:invalid:focus~.custom-file-label{border-color:#dc3545;box-shadow:0 0 0 .2rem rgba(220,53,69,.25)}.form-inline{display:-ms-flexbox;display:flex;-ms-flex-flow:row wrap;flex-flow:row wrap;-ms-flex-align:center;align-items:center}.form-inline .form-check{width:100%}@media (min-width:576px){.form-inline label{display:-ms-flexbox;display:flex;-ms-flex-align:center;align-items:center;-ms-flex-pack:center;justify-content:center;margin-bottom:0}.form-inline .form-group{display:-ms-flexbox;display:flex;-ms-flex:0 0 auto;flex:0 0 auto;-ms-flex-flow:row wrap;flex-flow:row wrap;-ms-flex-align:center;align-items:center;margin-bottom:0}.form-inline .form-control{display:inline-block;width:auto;vertical-align:middle}.form-inline .form-control-plaintext{display:inline-block}.form-inline .custom-select,.form-inline .input-group{width:auto}.form-inline .form-check{display:-ms-flexbox;display:flex;-ms-flex-align:center;align-items:center;-ms-flex-pack:center;justify-content:center;width:auto;padding-left:0}.form-inline .form-check-input{position:relative;-ms-flex-negative:0;flex-shrink:0;margin-top:0;margin-right:.25rem;margin-left:0}.form-inline .custom-control{-ms-flex-align:center;align-items:center;-ms-flex-pack:center;justify-content:center}.form-inline .custom-control-label{margin-bottom:0}}.btn{display:inline-block;font-weight:400;color:#212529;text-align:center;vertical-align:middle;-webkit-user-select:none;-moz-user-select:none;-ms-user-select:none;user-select:none;background-color:transparent;border:1px solid transparent;padding:.375rem .75rem;font-size:1rem;line-height:1.5;border-radius:.25rem;transition:color .15s ease-in-out,background-color .15s ease-in-out,border-color .15s ease-in-out,box-shadow .15s ease-in-out}@media (prefers-reduced-motion:reduce){.btn{transition:none}}.btn:hover{color:#212529;text-decoration:none}.btn.focus,.btn:focus{outline:0;box-shadow:0 0 0 .2rem rgba(0,123,255,.25)}.btn.disabled,.btn:disabled{opacity:.65}.btn:not(:disabled):not(.disabled){cursor:pointer}a.btn.disabled,fieldset:disabled a.btn{pointer-events:none}.btn-primary{color:#fff;background-color:#007bff;border-color:#007bff}.btn-primary:hover{color:#fff;background-color:#0069d9;border-color:#0062cc}.btn-primary.focus,.btn-primary:focus{color:#fff;background-color:#0069d9;border-color:#0062cc;box-shadow:0 0 0 .2rem rgba(38,143,255,.5)}.btn-primary.disabled,.btn-primary:disabled{color:#fff;background-color:#007bff;border-color:#007bff}.btn-primary:not(:disabled):not(.disabled).active,.btn-primary:not(:disabled):not(.disabled):active,.show>.btn-primary.dropdown-toggle{color:#fff;background-color:#0062cc;border-color:#005cbf}.btn-primary:not(:disabled):not(.disabled).active:focus,.btn-primary:not(:disabled):not(.disabled):active:focus,.show>.btn-primary.dropdown-toggle:focus{box-shadow:0 0 0 .2rem rgba(38,143,255,.5)}.btn-secondary{color:#fff;background-color:#6c757d;border-color:#6c757d}.btn-secondary:hover{color:#fff;background-color:#5a6268;border-color:#545b62}.btn-secondary.focus,.btn-secondary:focus{color:#fff;background-color:#5a6268;border-color:#545b62;box-shadow:0 0 0 .2rem rgba(130,138,145,.5)}.btn-secondary.disabled,.btn-secondary:disabled{color:#fff;background-color:#6c757d;border-color:#6c757d}.btn-secondary:not(:disabled):not(.disabled).active,.btn-secondary:not(:disabled):not(.disabled):active,.show>.btn-secondary.dropdown-toggle{color:#fff;background-color:#545b62;border-color:#4e555b}.btn-secondary:not(:disabled):not(.disabled).active:focus,.btn-secondary:not(:disabled):not(.disabled):active:focus,.show>.btn-secondary.dropdown-toggle:focus{box-shadow:0 0 0 .2rem rgba(130,138,145,.5)}.btn-success{color:#fff;background-color:#28a745;border-color:#28a745}.btn-success:hover{color:#fff;background-color:#218838;border-color:#1e7e34}.btn-success.focus,.btn-success:focus{color:#fff;background-color:#218838;border-color:#1e7e34;box-shadow:0 0 0 .2rem rgba(72,180,97,.5)}.btn-success.disabled,.btn-success:disabled{color:#fff;background-color:#28a745;border-color:#28a745}.btn-success:not(:disabled):not(.disabled).active,.btn-success:not(:disabled):not(.disabled):active,.show>.btn-success.dropdown-toggle{color:#fff;background-color:#1e7e34;border-color:#1c7430}.btn-success:not(:disabled):not(.disabled).active:focus,.btn-success:not(:disabled):not(.disabled):active:focus,.show>.btn-success.dropdown-toggle:focus{box-shadow:0 0 0 .2rem rgba(72,180,97,.5)}.btn-info{color:#fff;background-color:#17a2b8;border-color:#17a2b8}.btn-info:hover{color:#fff;background-color:#138496;border-color:#117a8b}.btn-info.focus,.btn-info:focus{color:#fff;background-color:#138496;border-color:#117a8b;box-shadow:0 0 0 .2rem rgba(58,176,195,.5)}.btn-info.disabled,.btn-info:disabled{color:#fff;background-color:#17a2b8;border-color:#17a2b8}.btn-info:not(:disabled):not(.disabled).active,.btn-info:not(:disabled):not(.disabled):active,.show>.btn-info.dropdown-toggle{color:#fff;background-color:#117a8b;border-color:#10707f}.btn-info:not(:disabled):not(.disabled).active:focus,.btn-info:not(:disabled):not(.disabled):active:focus,.show>.btn-info.dropdown-toggle:focus{box-shadow:0 0 0 .2rem rgba(58,176,195,.5)}.btn-warning{color:#212529;background-color:#ffc107;border-color:#ffc107}.btn-warning:hover{color:#212529;background-color:#e0a800;border-color:#d39e00}.btn-warning.focus,.btn-warning:focus{color:#212529;background-color:#e0a800;border-color:#d39e00;box-shadow:0 0 0 .2rem rgba(222,170,12,.5)}.btn-warning.disabled,.btn-warning:disabled{color:#212529;background-color:#ffc107;border-color:#ffc107}.btn-warning:not(:disabled):not(.disabled).active,.btn-warning:not(:disabled):not(.disabled):active,.show>.btn-warning.dropdown-toggle{color:#212529;background-color:#d39e00;border-color:#c69500}.btn-warning:not(:disabled):not(.disabled).active:focus,.btn-warning:not(:disabled):not(.disabled):active:focus,.show>.btn-warning.dropdown-toggle:focus{box-shadow:0 0 0 .2rem rgba(222,170,12,.5)}.btn-danger{color:#fff;background-color:#dc3545;border-color:#dc3545}.btn-danger:hover{color:#fff;background-color:#c82333;border-color:#bd2130}.btn-danger.focus,.btn-danger:focus{color:#fff;background-color:#c82333;border-color:#bd2130;box-shadow:0 0 0 .2rem rgba(225,83,97,.5)}.btn-danger.disabled,.btn-danger:disabled{color:#fff;background-color:#dc3545;border-color:#dc3545}.btn-danger:not(:disabled):not(.disabled).active,.btn-danger:not(:disabled):not(.disabled):active,.show>.btn-danger.dropdown-toggle{color:#fff;background-color:#bd2130;border-color:#b21f2d}.btn-danger:not(:disabled):not(.disabled).active:focus,.btn-danger:not(:disabled):not(.disabled):active:focus,.show>.btn-danger.dropdown-toggle:focus{box-shadow:0 0 0 .2rem rgba(225,83,97,.5)}.btn-light{color:#212529;background-color:#f8f9fa;border-color:#f8f9fa}.btn-light:hover{color:#212529;background-color:#e2e6ea;border-color:#dae0e5}.btn-light.focus,.btn-light:focus{color:#212529;background-color:#e2e6ea;border-color:#dae0e5;box-shadow:0 0 0 .2rem rgba(216,217,219,.5)}.btn-light.disabled,.btn-light:disabled{color:#212529;background-color:#f8f9fa;border-color:#f8f9fa}.btn-light:not(:disabled):not(.disabled).active,.btn-light:not(:disabled):not(.disabled):active,.show>.btn-light.dropdown-toggle{color:#212529;background-color:#dae0e5;border-color:#d3d9df}.btn-light:not(:disabled):not(.disabled).active:focus,.btn-light:not(:disabled):not(.disabled):active:focus,.show>.btn-light.dropdown-toggle:focus{box-shadow:0 0 0 .2rem rgba(216,217,219,.5)}.btn-dark{color:#fff;background-color:#343a40;border-color:#343a40}.btn-dark:hover{color:#fff;background-color:#23272b;border-color:#1d2124}.btn-dark.focus,.btn-dark:focus{color:#fff;background-color:#23272b;border-color:#1d2124;box-shadow:0 0 0 .2rem rgba(82,88,93,.5)}.btn-dark.disabled,.btn-dark:disabled{color:#fff;background-color:#343a40;border-color:#343a40}.btn-dark:not(:disabled):not(.disabled).active,.btn-dark:not(:disabled):not(.disabled):active,.show>.btn-dark.dropdown-toggle{color:#fff;background-color:#1d2124;border-color:#171a1d}.btn-dark:not(:disabled):not(.disabled).active:focus,.btn-dark:not(:disabled):not(.disabled):active:focus,.show>.btn-dark.dropdown-toggle:focus{box-shadow:0 0 0 .2rem rgba(82,88,93,.5)}.btn-outline-primary{color:#007bff;border-color:#007bff}.btn-outline-primary:hover{color:#fff;background-color:#007bff;border-color:#007bff}.btn-outline-primary.focus,.btn-outline-primary:focus{box-shadow:0 0 0 .2rem rgba(0,123,255,.5)}.btn-outline-primary.disabled,.btn-outline-primary:disabled{color:#007bff;background-color:transparent}.btn-outline-primary:not(:disabled):not(.disabled).active,.btn-outline-primary:not(:disabled):not(.disabled):active,.show>.btn-outline-primary.dropdown-toggle{color:#fff;background-color:#007bff;border-color:#007bff}.btn-outline-primary:not(:disabled):not(.disabled).active:focus,.btn-outline-primary:not(:disabled):not(.disabled):active:focus,.show>.btn-outline-primary.dropdown-toggle:focus{box-shadow:0 0 0 .2rem rgba(0,123,255,.5)}.btn-outline-secondary{color:#6c757d;border-color:#6c757d}.btn-outline-secondary:hover{color:#fff;background-color:#6c757d;border-color:#6c757d}.btn-outline-secondary.focus,.btn-outline-secondary:focus{box-shadow:0 0 0 .2rem rgba(108,117,125,.5)}.btn-outline-secondary.disabled,.btn-outline-secondary:disabled{color:#6c757d;background-color:transparent}.btn-outline-secondary:not(:disabled):not(.disabled).active,.btn-outline-secondary:not(:disabled):not(.disabled):active,.show>.btn-outline-secondary.dropdown-toggle{color:#fff;background-color:#6c757d;border-color:#6c757d}.btn-outline-secondary:not(:disabled):not(.disabled).active:focus,.btn-outline-secondary:not(:disabled):not(.disabled):active:focus,.show>.btn-outline-secondary.dropdown-toggle:focus{box-shadow:0 0 0 .2rem rgba(108,117,125,.5)}.btn-outline-success{color:#28a745;border-color:#28a745}.btn-outline-success:hover{color:#fff;background-color:#28a745;border-color:#28a745}.btn-outline-success.focus,.btn-outline-success:focus{box-shadow:0 0 0 .2rem rgba(40,167,69,.5)}.btn-outline-success.disabled,.btn-outline-success:disabled{color:#28a745;background-color:transparent}.btn-outline-success:not(:disabled):not(.disabled).active,.btn-outline-success:not(:disabled):not(.disabled):active,.show>.btn-outline-success.dropdown-toggle{color:#fff;background-color:#28a745;border-color:#28a745}.btn-outline-success:not(:disabled):not(.disabled).active:focus,.btn-outline-success:not(:disabled):not(.disabled):active:focus,.show>.btn-outline-success.dropdown-toggle:focus{box-shadow:0 0 0 .2rem rgba(40,167,69,.5)}.btn-outline-info{color:#17a2b8;border-color:#17a2b8}.btn-outline-info:hover{color:#fff;background-color:#17a2b8;border-color:#17a2b8}.btn-outline-info.focus,.btn-outline-info:focus{box-shadow:0 0 0 .2rem rgba(23,162,184,.5)}.btn-outline-info.disabled,.btn-outline-info:disabled{color:#17a2b8;background-color:transparent}.btn-outline-info:not(:disabled):not(.disabled).active,.btn-outline-info:not(:disabled):not(.disabled):active,.show>.btn-outline-info.dropdown-toggle{color:#fff;background-color:#17a2b8;border-color:#17a2b8}.btn-outline-info:not(:disabled):not(.disabled).active:focus,.btn-outline-info:not(:disabled):not(.disabled):active:focus,.show>.btn-outline-info.dropdown-toggle:focus{box-shadow:0 0 0 .2rem rgba(23,162,184,.5)}.btn-outline-warning{color:#ffc107;border-color:#ffc107}.btn-outline-warning:hover{color:#212529;background-color:#ffc107;border-color:#ffc107}.btn-outline-warning.focus,.btn-outline-warning:focus{box-shadow:0 0 0 .2rem rgba(255,193,7,.5)}.btn-outline-warning.disabled,.btn-outline-warning:disabled{color:#ffc107;background-color:transparent}.btn-outline-warning:not(:disabled):not(.disabled).active,.btn-outline-warning:not(:disabled):not(.disabled):active,.show>.btn-outline-warning.dropdown-toggle{color:#212529;background-color:#ffc107;border-color:#ffc107}.btn-outline-warning:not(:disabled):not(.disabled).active:focus,.btn-outline-warning:not(:disabled):not(.disabled):active:focus,.show>.btn-outline-warning.dropdown-toggle:focus{box-shadow:0 0 0 .2rem rgba(255,193,7,.5)}.btn-outline-danger{color:#dc3545;border-color:#dc3545}.btn-outline-danger:hover{color:#fff;background-color:#dc3545;border-color:#dc3545}.btn-outline-danger.focus,.btn-outline-danger:focus{box-shadow:0 0 0 .2rem rgba(220,53,69,.5)}.btn-outline-danger.disabled,.btn-outline-danger:disabled{color:#dc3545;background-color:transparent}.btn-outline-danger:not(:disabled):not(.disabled).active,.btn-outline-danger:not(:disabled):not(.disabled):active,.show>.btn-outline-danger.dropdown-toggle{color:#fff;background-color:#dc3545;border-color:#dc3545}.btn-outline-danger:not(:disabled):not(.disabled).active:focus,.btn-outline-danger:not(:disabled):not(.disabled):active:focus,.show>.btn-outline-danger.dropdown-toggle:focus{box-shadow:0 0 0 .2rem rgba(220,53,69,.5)}.btn-outline-light{color:#f8f9fa;border-color:#f8f9fa}.btn-outline-light:hover{color:#212529;background-color:#f8f9fa;border-color:#f8f9fa}.btn-outline-light.focus,.btn-outline-light:focus{box-shadow:0 0 0 .2rem rgba(248,249,250,.5)}.btn-outline-light.disabled,.btn-outline-light:disabled{color:#f8f9fa;background-color:transparent}.btn-outline-light:not(:disabled):not(.disabled).active,.btn-outline-light:not(:disabled):not(.disabled):active,.show>.btn-outline-light.dropdown-toggle{color:#212529;background-color:#f8f9fa;border-color:#f8f9fa}.btn-outline-light:not(:disabled):not(.disabled).active:focus,.btn-outline-light:not(:disabled):not(.disabled):active:focus,.show>.btn-outline-light.dropdown-toggle:focus{box-shadow:0 0 0 .2rem rgba(248,249,250,.5)}.btn-outline-dark{color:#343a40;border-color:#343a40}.btn-outline-dark:hover{color:#fff;background-color:#343a40;border-color:#343a40}.btn-outline-dark.focus,.btn-outline-dark:focus{box-shadow:0 0 0 .2rem rgba(52,58,64,.5)}.btn-outline-dark.disabled,.btn-outline-dark:disabled{color:#343a40;background-color:transparent}.btn-outline-dark:not(:disabled):not(.disabled).active,.btn-outline-dark:not(:disabled):not(.disabled):active,.show>.btn-outline-dark.dropdown-toggle{color:#fff;background-color:#343a40;border-color:#343a40}.btn-outline-dark:not(:disabled):not(.disabled).active:focus,.btn-outline-dark:not(:disabled):not(.disabled):active:focus,.show>.btn-outline-dark.dropdown-toggle:focus{box-shadow:0 0 0 .2rem rgba(52,58,64,.5)}.btn-link{font-weight:400;color:#007bff;text-decoration:none}.btn-link:hover{color:#0056b3;text-decoration:underline}.btn-link.focus,.btn-link:focus{text-decoration:underline}.btn-link.disabled,.btn-link:disabled{color:#6c757d;pointer-events:none}.btn-group-lg>.btn,.btn-lg{padding:.5rem 1rem;font-size:1.25rem;line-height:1.5;border-radius:.3rem}.btn-group-sm>.btn,.btn-sm{padding:.25rem .5rem;font-size:.875rem;line-height:1.5;border-radius:.2rem}.btn-block{display:block;width:100%}.btn-block+.btn-block{margin-top:.5rem}input[type=button].btn-block,input[type=reset].btn-block,input[type=submit].btn-block{width:100%}.fade{transition:opacity .15s linear}@media (prefers-reduced-motion:reduce){.fade{transition:none}}.fade:not(.show){opacity:0}.collapse:not(.show){display:none}.collapsing{position:relative;height:0;overflow:hidden;transition:height .35s ease}@media (prefers-reduced-motion:reduce){.collapsing{transition:none}}.collapsing.width{width:0;height:auto;transition:width .35s ease}@media (prefers-reduced-motion:reduce){.collapsing.width{transition:none}}.dropdown,.dropleft,.dropright,.dropup{position:relative}.dropdown-toggle{white-space:nowrap}.dropdown-toggle::after{display:inline-block;margin-left:.255em;vertical-align:.255em;content:"";border-top:.3em solid;border-right:.3em solid transparent;border-bottom:0;border-left:.3em solid transparent}.dropdown-toggle:empty::after{margin-left:0}.dropdown-menu{position:absolute;top:100%;left:0;z-index:1000;display:none;float:left;min-width:10rem;padding:.5rem 0;margin:.125rem 0 0;font-size:1rem;color:#212529;text-align:left;list-style:none;background-color:#fff;background-clip:padding-box;border:1px solid rgba(0,0,0,.15);border-radius:.25rem}.dropdown-menu-left{right:auto;left:0}.dropdown-menu-right{right:0;left:auto}@media (min-width:576px){.dropdown-menu-sm-left{right:auto;left:0}.dropdown-menu-sm-right{right:0;left:auto}}@media (min-width:768px){.dropdown-menu-md-left{right:auto;left:0}.dropdown-menu-md-right{right:0;left:auto}}@media (min-width:992px){.dropdown-menu-lg-left{right:auto;left:0}.dropdown-menu-lg-right{right:0;left:auto}}@media (min-width:1200px){.dropdown-menu-xl-left{right:auto;left:0}.dropdown-menu-xl-right{right:0;left:auto}}.dropup .dropdown-menu{top:auto;bottom:100%;margin-top:0;margin-bottom:.125rem}.dropup .dropdown-toggle::after{display:inline-block;margin-left:.255em;vertical-align:.255em;content:"";border-top:0;border-right:.3em solid transparent;border-bottom:.3em solid;border-left:.3em solid transparent}.dropup .dropdown-toggle:empty::after{margin-left:0}.dropright .dropdown-menu{top:0;right:auto;left:100%;margin-top:0;margin-left:.125rem}.dropright .dropdown-toggle::after{display:inline-block;margin-left:.255em;vertical-align:.255em;content:"";border-top:.3em solid transparent;border-right:0;border-bottom:.3em solid transparent;border-left:.3em solid}.dropright .dropdown-toggle:empty::after{margin-left:0}.dropright .dropdown-toggle::after{vertical-align:0}.dropleft .dropdown-menu{top:0;right:100%;left:auto;margin-top:0;margin-right:.125rem}.dropleft .dropdown-toggle::after{display:inline-block;margin-left:.255em;vertical-align:.255em;content:""}.dropleft .dropdown-toggle::after{display:none}.dropleft .dropdown-toggle::before{display:inline-block;margin-right:.255em;vertical-align:.255em;content:"";border-top:.3em solid transparent;border-right:.3em solid;border-bottom:.3em solid transparent}.dropleft .dropdown-toggle:empty::after{margin-left:0}.dropleft .dropdown-toggle::before{vertical-align:0}.dropdown-menu[x-placement^=bottom],.dropdown-menu[x-placement^=left],.dropdown-menu[x-placement^=right],.dropdown-menu[x-placement^=top]{right:auto;bottom:auto}.dropdown-divider{height:0;margin:.5rem 0;overflow:hidden;border-top:1px solid #e9ecef}.dropdown-item{display:block;width:100%;padding:.25rem 1.5rem;clear:both;font-weight:400;color:#212529;text-align:inherit;white-space:nowrap;background-color:transparent;border:0}.dropdown-item:focus,.dropdown-item:hover{color:#16181b;text-decoration:none;background-color:#e9ecef}.dropdown-item.active,.dropdown-item:active{color:#fff;text-decoration:none;background-color:#007bff}.dropdown-item.disabled,.dropdown-item:disabled{color:#adb5bd;pointer-events:none;background-color:transparent}.dropdown-menu.show{display:block}.dropdown-header{display:block;padding:.5rem 1.5rem;margin-bottom:0;font-size:.875rem;color:#6c757d;white-space:nowrap}.dropdown-item-text{display:block;padding:.25rem 1.5rem;color:#212529}.btn-group,.btn-group-vertical{position:relative;display:-ms-inline-flexbox;display:inline-flex;vertical-align:middle}.btn-group-vertical>.btn,.btn-group>.btn{position:relative;-ms-flex:1 1 auto;flex:1 1 auto}.btn-group-vertical>.btn:hover,.btn-group>.btn:hover{z-index:1}.btn-group-vertical>.btn.active,.btn-group-vertical>.btn:active,.btn-group-vertical>.btn:focus,.btn-group>.btn.active,.btn-group>.btn:active,.btn-group>.btn:focus{z-index:1}.btn-toolbar{display:-ms-flexbox;display:flex;-ms-flex-wrap:wrap;flex-wrap:wrap;-ms-flex-pack:start;justify-content:flex-start}.btn-toolbar .input-group{width:auto}.btn-group>.btn-group:not(:first-child),.btn-group>.btn:not(:first-child){margin-left:-1px}.btn-group>.btn-group:not(:last-child)>.btn,.btn-group>.btn:not(:last-child):not(.dropdown-toggle){border-top-right-radius:0;border-bottom-right-radius:0}.btn-group>.btn-group:not(:first-child)>.btn,.btn-group>.btn:not(:first-child){border-top-left-radius:0;border-bottom-left-radius:0}.dropdown-toggle-split{padding-right:.5625rem;padding-left:.5625rem}.dropdown-toggle-split::after,.dropright .dropdown-toggle-split::after,.dropup .dropdown-toggle-split::after{margin-left:0}.dropleft .dropdown-toggle-split::before{margin-right:0}.btn-group-sm>.btn+.dropdown-toggle-split,.btn-sm+.dropdown-toggle-split{padding-right:.375rem;padding-left:.375rem}.btn-group-lg>.btn+.dropdown-toggle-split,.btn-lg+.dropdown-toggle-split{padding-right:.75rem;padding-left:.75rem}.btn-group-vertical{-ms-flex-direction:column;flex-direction:column;-ms-flex-align:start;align-items:flex-start;-ms-flex-pack:center;justify-content:center}.btn-group-vertical>.btn,.btn-group-vertical>.btn-group{width:100%}.btn-group-vertical>.btn-group:not(:first-child),.btn-group-vertical>.btn:not(:first-child){margin-top:-1px}.btn-group-vertical>.btn-group:not(:last-child)>.btn,.btn-group-vertical>.btn:not(:last-child):not(.dropdown-toggle){border-bottom-right-radius:0;border-bottom-left-radius:0}.btn-group-vertical>.btn-group:not(:first-child)>.btn,.btn-group-vertical>.btn:not(:first-child){border-top-left-radius:0;border-top-right-radius:0}.btn-group-toggle>.btn,.btn-group-toggle>.btn-group>.btn{margin-bottom:0}.btn-group-toggle>.btn input[type=checkbox],.btn-group-toggle>.btn input[type=radio],.btn-group-toggle>.btn-group>.btn input[type=checkbox],.btn-group-toggle>.btn-group>.btn input[type=radio]{position:absolute;clip:rect(0,0,0,0);pointer-events:none}.input-group{position:relative;display:-ms-flexbox;display:flex;-ms-flex-wrap:wrap;flex-wrap:wrap;-ms-flex-align:stretch;align-items:stretch;width:100%}.input-group>.custom-file,.input-group>.custom-select,.input-group>.form-control,.input-group>.form-control-plaintext{position:relative;-ms-flex:1 1 auto;flex:1 1 auto;width:1%;min-width:0;margin-bottom:0}.input-group>.custom-file+.custom-file,.input-group>.custom-file+.custom-select,.input-group>.custom-file+.form-control,.input-group>.custom-select+.custom-file,.input-group>.custom-select+.custom-select,.input-group>.custom-select+.form-control,.input-group>.form-control+.custom-file,.input-group>.form-control+.custom-select,.input-group>.form-control+.form-control,.input-group>.form-control-plaintext+.custom-file,.input-group>.form-control-plaintext+.custom-select,.input-group>.form-control-plaintext+.form-control{margin-left:-1px}.input-group>.custom-file .custom-file-input:focus~.custom-file-label,.input-group>.custom-select:focus,.input-group>.form-control:focus{z-index:3}.input-group>.custom-file .custom-file-input:focus{z-index:4}.input-group>.custom-select:not(:first-child),.input-group>.form-control:not(:first-child){border-top-left-radius:0;border-bottom-left-radius:0}.input-group>.custom-file{display:-ms-flexbox;display:flex;-ms-flex-align:center;align-items:center}.input-group>.custom-file:not(:last-child) .custom-file-label,.input-group>.custom-file:not(:last-child) .custom-file-label::after{border-top-right-radius:0;border-bottom-right-radius:0}.input-group>.custom-file:not(:first-child) .custom-file-label{border-top-left-radius:0;border-bottom-left-radius:0}.input-group:not(.has-validation)>.custom-file:not(:last-child) .custom-file-label,.input-group:not(.has-validation)>.custom-file:not(:last-child) .custom-file-label::after,.input-group:not(.has-validation)>.custom-select:not(:last-child),.input-group:not(.has-validation)>.form-control:not(:last-child){border-top-right-radius:0;border-bottom-right-radius:0}.input-group.has-validation>.custom-file:nth-last-child(n+3) .custom-file-label,.input-group.has-validation>.custom-file:nth-last-child(n+3) .custom-file-label::after,.input-group.has-validation>.custom-select:nth-last-child(n+3),.input-group.has-validation>.form-control:nth-last-child(n+3){border-top-right-radius:0;border-bottom-right-radius:0}.input-group-append,.input-group-prepend{display:-ms-flexbox;display:flex}.input-group-append .btn,.input-group-prepend .btn{position:relative;z-index:2}.input-group-append .btn:focus,.input-group-prepend .btn:focus{z-index:3}.input-group-append .btn+.btn,.input-group-append .btn+.input-group-text,.input-group-append .input-group-text+.btn,.input-group-append .input-group-text+.input-group-text,.input-group-prepend .btn+.btn,.input-group-prepend .btn+.input-group-text,.input-group-prepend .input-group-text+.btn,.input-group-prepend .input-group-text+.input-group-text{margin-left:-1px}.input-group-prepend{margin-right:-1px}.input-group-append{margin-left:-1px}.input-group-text{display:-ms-flexbox;display:flex;-ms-flex-align:center;align-items:center;padding:.375rem .75rem;margin-bottom:0;font-size:1rem;font-weight:400;line-height:1.5;color:#495057;text-align:center;white-space:nowrap;background-color:#e9ecef;border:1px solid #ced4da;border-radius:.25rem}.input-group-text input[type=checkbox],.input-group-text input[type=radio]{margin-top:0}.input-group-lg>.custom-select,.input-group-lg>.form-control:not(textarea){height:calc(1.5em + 1rem + 2px)}.input-group-lg>.custom-select,.input-group-lg>.form-control,.input-group-lg>.input-group-append>.btn,.input-group-lg>.input-group-append>.input-group-text,.input-group-lg>.input-group-prepend>.btn,.input-group-lg>.input-group-prepend>.input-group-text{padding:.5rem 1rem;font-size:1.25rem;line-height:1.5;border-radius:.3rem}.input-group-sm>.custom-select,.input-group-sm>.form-control:not(textarea){height:calc(1.5em + .5rem + 2px)}.input-group-sm>.custom-select,.input-group-sm>.form-control,.input-group-sm>.input-group-append>.btn,.input-group-sm>.input-group-append>.input-group-text,.input-group-sm>.input-group-prepend>.btn,.input-group-sm>.input-group-prepend>.input-group-text{padding:.25rem .5rem;font-size:.875rem;line-height:1.5;border-radius:.2rem}.input-group-lg>.custom-select,.input-group-sm>.custom-select{padding-right:1.75rem}.input-group.has-validation>.input-group-append:nth-last-child(n+3)>.btn,.input-group.has-validation>.input-group-append:nth-last-child(n+3)>.input-group-text,.input-group:not(.has-validation)>.input-group-append:not(:last-child)>.btn,.input-group:not(.has-validation)>.input-group-append:not(:last-child)>.input-group-text,.input-group>.input-group-append:last-child>.btn:not(:last-child):not(.dropdown-toggle),.input-group>.input-group-append:last-child>.input-group-text:not(:last-child),.input-group>.input-group-prepend>.btn,.input-group>.input-group-prepend>.input-group-text{border-top-right-radius:0;border-bottom-right-radius:0}.input-group>.input-group-append>.btn,.input-group>.input-group-append>.input-group-text,.input-group>.input-group-prepend:first-child>.btn:not(:first-child),.input-group>.input-group-prepend:first-child>.input-group-text:not(:first-child),.input-group>.input-group-prepend:not(:first-child)>.btn,.input-group>.input-group-prepend:not(:first-child)>.input-group-text{border-top-left-radius:0;border-bottom-left-radius:0}.custom-control{position:relative;z-index:1;display:block;min-height:1.5rem;padding-left:1.5rem;-webkit-print-color-adjust:exact;color-adjust:exact;print-color-adjust:exact}.custom-control-inline{display:-ms-inline-flexbox;display:inline-flex;margin-right:1rem}.custom-control-input{position:absolute;left:0;z-index:-1;width:1rem;height:1.25rem;opacity:0}.custom-control-input:checked~.custom-control-label::before{color:#fff;border-color:#007bff;background-color:#007bff}.custom-control-input:focus~.custom-control-label::before{box-shadow:0 0 0 .2rem rgba(0,123,255,.25)}.custom-control-input:focus:not(:checked)~.custom-control-label::before{border-color:#80bdff}.custom-control-input:not(:disabled):active~.custom-control-label::before{color:#fff;background-color:#b3d7ff;border-color:#b3d7ff}.custom-control-input:disabled~.custom-control-label,.custom-control-input[disabled]~.custom-control-label{color:#6c757d}.custom-control-input:disabled~.custom-control-label::before,.custom-control-input[disabled]~.custom-control-label::before{background-color:#e9ecef}.custom-control-label{position:relative;margin-bottom:0;vertical-align:top}.custom-control-label::before{position:absolute;top:.25rem;left:-1.5rem;display:block;width:1rem;height:1rem;pointer-events:none;content:"";background-color:#fff;border:1px solid #adb5bd}.custom-control-label::after{position:absolute;top:.25rem;left:-1.5rem;display:block;width:1rem;height:1rem;content:"";background:50%/50% 50% no-repeat}.custom-checkbox .custom-control-label::before{border-radius:.25rem}.custom-checkbox .custom-control-input:checked~.custom-control-label::after{background-image:url("data:image/svg+xml,%3csvg xmlns='http://www.w3.org/2000/svg' width='8' height='8' viewBox='0 0 8 8'%3e%3cpath fill='%23fff' d='M6.564.75l-3.59 3.612-1.538-1.55L0 4.26l2.974 2.99L8 2.193z'/%3e%3c/svg%3e")}.custom-checkbox .custom-control-input:indeterminate~.custom-control-label::before{border-color:#007bff;background-color:#007bff}.custom-checkbox .custom-control-input:indeterminate~.custom-control-label::after{background-image:url("data:image/svg+xml,%3csvg xmlns='http://www.w3.org/2000/svg' width='4' height='4' viewBox='0 0 4 4'%3e%3cpath stroke='%23fff' d='M0 2h4'/%3e%3c/svg%3e")}.custom-checkbox .custom-control-input:disabled:checked~.custom-control-label::before{background-color:rgba(0,123,255,.5)}.custom-checkbox .custom-control-input:disabled:indeterminate~.custom-control-label::before{background-color:rgba(0,123,255,.5)}.custom-radio .custom-control-label::before{border-radius:50%}.custom-radio .custom-control-input:checked~.custom-control-label::after{background-image:url("data:image/svg+xml,%3csvg xmlns='http://www.w3.org/2000/svg' width='12' height='12' viewBox='-4 -4 8 8'%3e%3ccircle r='3' fill='%23fff'/%3e%3c/svg%3e")}.custom-radio .custom-control-input:disabled:checked~.custom-control-label::before{background-color:rgba(0,123,255,.5)}.custom-switch{padding-left:2.25rem}.custom-switch .custom-control-label::before{left:-2.25rem;width:1.75rem;pointer-events:all;border-radius:.5rem}.custom-switch .custom-control-label::after{top:calc(.25rem + 2px);left:calc(-2.25rem + 2px);width:calc(1rem - 4px);height:calc(1rem - 4px);background-color:#adb5bd;border-radius:.5rem;transition:background-color .15s ease-in-out,border-color .15s ease-in-out,box-shadow .15s ease-in-out,-webkit-transform .15s ease-in-out;transition:transform .15s ease-in-out,background-color .15s ease-in-out,border-color .15s ease-in-out,box-shadow .15s ease-in-out;transition:transform .15s ease-in-out,background-color .15s ease-in-out,border-color .15s ease-in-out,box-shadow .15s ease-in-out,-webkit-transform .15s ease-in-out}@media (prefers-reduced-motion:reduce){.custom-switch .custom-control-label::after{transition:none}}.custom-switch .custom-control-input:checked~.custom-control-label::after{background-color:#fff;-webkit-transform:translateX(.75rem);transform:translateX(.75rem)}.custom-switch .custom-control-input:disabled:checked~.custom-control-label::before{background-color:rgba(0,123,255,.5)}.custom-select{display:inline-block;width:100%;height:calc(1.5em + .75rem + 2px);padding:.375rem 1.75rem .375rem .75rem;font-size:1rem;font-weight:400;line-height:1.5;color:#495057;vertical-align:middle;background:#fff url("data:image/svg+xml,%3csvg xmlns='http://www.w3.org/2000/svg' width='4' height='5' viewBox='0 0 4 5'%3e%3cpath fill='%23343a40' d='M2 0L0 2h4zm0 5L0 3h4z'/%3e%3c/svg%3e") right .75rem center/8px 10px no-repeat;border:1px solid #ced4da;border-radius:.25rem;-webkit-appearance:none;-moz-appearance:none;appearance:none}.custom-select:focus{border-color:#80bdff;outline:0;box-shadow:0 0 0 .2rem rgba(0,123,255,.25)}.custom-select:focus::-ms-value{color:#495057;background-color:#fff}.custom-select[multiple],.custom-select[size]:not([size="1"]){height:auto;padding-right:.75rem;background-image:none}.custom-select:disabled{color:#6c757d;background-color:#e9ecef}.custom-select::-ms-expand{display:none}.custom-select:-moz-focusring{color:transparent;text-shadow:0 0 0 #495057}.custom-select-sm{height:calc(1.5em + .5rem + 2px);padding-top:.25rem;padding-bottom:.25rem;padding-left:.5rem;font-size:.875rem}.custom-select-lg{height:calc(1.5em + 1rem + 2px);padding-top:.5rem;padding-bottom:.5rem;padding-left:1rem;font-size:1.25rem}.custom-file{position:relative;display:inline-block;width:100%;height:calc(1.5em + .75rem + 2px);margin-bottom:0}.custom-file-input{position:relative;z-index:2;width:100%;height:calc(1.5em + .75rem + 2px);margin:0;overflow:hidden;opacity:0}.custom-file-input:focus~.custom-file-label{border-color:#80bdff;box-shadow:0 0 0 .2rem rgba(0,123,255,.25)}.custom-file-input:disabled~.custom-file-label,.custom-file-input[disabled]~.custom-file-label{background-color:#e9ecef}.custom-file-input:lang(en)~.custom-file-label::after{content:"Browse"}.custom-file-input~.custom-file-label[data-browse]::after{content:attr(data-browse)}.custom-file-label{position:absolute;top:0;right:0;left:0;z-index:1;height:calc(1.5em + .75rem + 2px);padding:.375rem .75rem;overflow:hidden;font-weight:400;line-height:1.5;color:#495057;background-color:#fff;border:1px solid #ced4da;border-radius:.25rem}.custom-file-label::after{position:absolute;top:0;right:0;bottom:0;z-index:3;display:block;height:calc(1.5em + .75rem);padding:.375rem .75rem;line-height:1.5;color:#495057;content:"Browse";background-color:#e9ecef;border-left:inherit;border-radius:0 .25rem .25rem 0}.custom-range{width:100%;height:1.4rem;padding:0;background-color:transparent;-webkit-appearance:none;-moz-appearance:none;appearance:none}.custom-range:focus{outline:0}.custom-range:focus::-webkit-slider-thumb{box-shadow:0 0 0 1px #fff,0 0 0 .2rem rgba(0,123,255,.25)}.custom-range:focus::-moz-range-thumb{box-shadow:0 0 0 1px #fff,0 0 0 .2rem rgba(0,123,255,.25)}.custom-range:focus::-ms-thumb{box-shadow:0 0 0 1px #fff,0 0 0 .2rem rgba(0,123,255,.25)}.custom-range::-moz-focus-outer{border:0}.custom-range::-webkit-slider-thumb{width:1rem;height:1rem;margin-top:-.25rem;background-color:#007bff;border:0;border-radius:1rem;-webkit-transition:background-color .15s ease-in-out,border-color .15s ease-in-out,box-shadow .15s ease-in-out;transition:background-color .15s ease-in-out,border-color .15s ease-in-out,box-shadow .15s ease-in-out;-webkit-appearance:none;appearance:none}@media (prefers-reduced-motion:reduce){.custom-range::-webkit-slider-thumb{-webkit-transition:none;transition:none}}.custom-range::-webkit-slider-thumb:active{background-color:#b3d7ff}.custom-range::-webkit-slider-runnable-track{width:100%;height:.5rem;color:transparent;cursor:pointer;background-color:#dee2e6;border-color:transparent;border-radius:1rem}.custom-range::-moz-range-thumb{width:1rem;height:1rem;background-color:#007bff;border:0;border-radius:1rem;-moz-transition:background-color .15s ease-in-out,border-color .15s ease-in-out,box-shadow .15s ease-in-out;transition:background-color .15s ease-in-out,border-color .15s ease-in-out,box-shadow .15s ease-in-out;-moz-appearance:none;appearance:none}@media (prefers-reduced-motion:reduce){.custom-range::-moz-range-thumb{-moz-transition:none;transition:none}}.custom-range::-moz-range-thumb:active{background-color:#b3d7ff}.custom-range::-moz-range-track{width:100%;height:.5rem;color:transparent;cursor:pointer;background-color:#dee2e6;border-color:transparent;border-radius:1rem}.custom-range::-ms-thumb{width:1rem;height:1rem;margin-top:0;margin-right:.2rem;margin-left:.2rem;background-color:#007bff;border:0;border-radius:1rem;-ms-transition:background-color .15s ease-in-out,border-color .15s ease-in-out,box-shadow .15s ease-in-out;transition:background-color .15s ease-in-out,border-color .15s ease-in-out,box-shadow .15s ease-in-out;appearance:none}@media (prefers-reduced-motion:reduce){.custom-range::-ms-thumb{-ms-transition:none;transition:none}}.custom-range::-ms-thumb:active{background-color:#b3d7ff}.custom-range::-ms-track{width:100%;height:.5rem;color:transparent;cursor:pointer;background-color:transparent;border-color:transparent;border-width:.5rem}.custom-range::-ms-fill-lower{background-color:#dee2e6;border-radius:1rem}.custom-range::-ms-fill-upper{margin-right:15px;background-color:#dee2e6;border-radius:1rem}.custom-range:disabled::-webkit-slider-thumb{background-color:#adb5bd}.custom-range:disabled::-webkit-slider-runnable-track{cursor:default}.custom-range:disabled::-moz-range-thumb{background-color:#adb5bd}.custom-range:disabled::-moz-range-track{cursor:default}.custom-range:disabled::-ms-thumb{background-color:#adb5bd}.custom-control-label::before,.custom-file-label,.custom-select{transition:background-color .15s ease-in-out,border-color .15s ease-in-out,box-shadow .15s ease-in-out}@media (prefers-reduced-motion:reduce){.custom-control-label::before,.custom-file-label,.custom-select{transition:none}}.nav{display:-ms-flexbox;display:flex;-ms-flex-wrap:wrap;flex-wrap:wrap;padding-left:0;margin-bottom:0;list-style:none}.nav-link{display:block;padding:.5rem 1rem}.nav-link:focus,.nav-link:hover{text-decoration:none}.nav-link.disabled{color:#6c757d;pointer-events:none;cursor:default}.nav-tabs{border-bottom:1px solid #dee2e6}.nav-tabs .nav-link{margin-bottom:-1px;background-color:transparent;border:1px solid transparent;border-top-left-radius:.25rem;border-top-right-radius:.25rem}.nav-tabs .nav-link:focus,.nav-tabs .nav-link:hover{isolation:isolate;border-color:#e9ecef #e9ecef #dee2e6}.nav-tabs .nav-link.disabled{color:#6c757d;background-color:transparent;border-color:transparent}.nav-tabs .nav-item.show .nav-link,.nav-tabs .nav-link.active{color:#495057;background-color:#fff;border-color:#dee2e6 #dee2e6 #fff}.nav-tabs .dropdown-menu{margin-top:-1px;border-top-left-radius:0;border-top-right-radius:0}.nav-pills .nav-link{background:0 0;border:0;border-radius:.25rem}.nav-pills .nav-link.active,.nav-pills .show>.nav-link{color:#fff;background-color:#007bff}.nav-fill .nav-item,.nav-fill>.nav-link{-ms-flex:1 1 auto;flex:1 1 auto;text-align:center}.nav-justified .nav-item,.nav-justified>.nav-link{-ms-flex-preferred-size:0;flex-basis:0;-ms-flex-positive:1;flex-grow:1;text-align:center}.tab-content>.tab-pane{display:none}.tab-content>.active{display:block}.navbar{position:relative;display:-ms-flexbox;display:flex;-ms-flex-wrap:wrap;flex-wrap:wrap;-ms-flex-align:center;align-items:center;-ms-flex-pack:justify;justify-content:space-between;padding:.5rem 1rem}.navbar .container,.navbar .container-fluid,.navbar .container-lg,.navbar .container-md,.navbar .container-sm,.navbar .container-xl{display:-ms-flexbox;display:flex;-ms-flex-wrap:wrap;flex-wrap:wrap;-ms-flex-align:center;align-items:center;-ms-flex-pack:justify;justify-content:space-between}.navbar-brand{display:inline-block;padding-top:.3125rem;padding-bottom:.3125rem;margin-right:1rem;font-size:1.25rem;line-height:inherit;white-space:nowrap}.navbar-brand:focus,.navbar-brand:hover{text-decoration:none}.navbar-nav{display:-ms-flexbox;display:flex;-ms-flex-direction:column;flex-direction:column;padding-left:0;margin-bottom:0;list-style:none}.navbar-nav .nav-link{padding-right:0;padding-left:0}.navbar-nav .dropdown-menu{position:static;float:none}.navbar-text{display:inline-block;padding-top:.5rem;padding-bottom:.5rem}.navbar-collapse{-ms-flex-preferred-size:100%;flex-basis:100%;-ms-flex-positive:1;flex-grow:1;-ms-flex-align:center;align-items:center}.navbar-toggler{padding:.25rem .75rem;font-size:1.25rem;line-height:1;background-color:transparent;border:1px solid transparent;border-radius:.25rem}.navbar-toggler:focus,.navbar-toggler:hover{text-decoration:none}.navbar-toggler-icon{display:inline-block;width:1.5em;height:1.5em;vertical-align:middle;content:"";background:50%/100% 100% no-repeat}.navbar-nav-scroll{max-height:75vh;overflow-y:auto}@media (max-width:575.98px){.navbar-expand-sm>.container,.navbar-expand-sm>.container-fluid,.navbar-expand-sm>.container-lg,.navbar-expand-sm>.container-md,.navbar-expand-sm>.container-sm,.navbar-expand-sm>.container-xl{padding-right:0;padding-left:0}}@media (min-width:576px){.navbar-expand-sm{-ms-flex-flow:row nowrap;flex-flow:row nowrap;-ms-flex-pack:start;justify-content:flex-start}.navbar-expand-sm .navbar-nav{-ms-flex-direction:row;flex-direction:row}.navbar-expand-sm .navbar-nav .dropdown-menu{position:absolute}.navbar-expand-sm .navbar-nav .nav-link{padding-right:.5rem;padding-left:.5rem}.navbar-expand-sm>.container,.navbar-expand-sm>.container-fluid,.navbar-expand-sm>.container-lg,.navbar-expand-sm>.container-md,.navbar-expand-sm>.container-sm,.navbar-expand-sm>.container-xl{-ms-flex-wrap:nowrap;flex-wrap:nowrap}.navbar-expand-sm .navbar-nav-scroll{overflow:visible}.navbar-expand-sm .navbar-collapse{display:-ms-flexbox!important;display:flex!important;-ms-flex-preferred-size:auto;flex-basis:auto}.navbar-expand-sm .navbar-toggler{display:none}}@media (max-width:767.98px){.navbar-expand-md>.container,.navbar-expand-md>.container-fluid,.navbar-expand-md>.container-lg,.navbar-expand-md>.container-md,.navbar-expand-md>.container-sm,.navbar-expand-md>.container-xl{padding-right:0;padding-left:0}}@media (min-width:768px){.navbar-expand-md{-ms-flex-flow:row nowrap;flex-flow:row nowrap;-ms-flex-pack:start;justify-content:flex-start}.navbar-expand-md .navbar-nav{-ms-flex-direction:row;flex-direction:row}.navbar-expand-md .navbar-nav .dropdown-menu{position:absolute}.navbar-expand-md .navbar-nav .nav-link{padding-right:.5rem;padding-left:.5rem}.navbar-expand-md>.container,.navbar-expand-md>.container-fluid,.navbar-expand-md>.container-lg,.navbar-expand-md>.container-md,.navbar-expand-md>.container-sm,.navbar-expand-md>.container-xl{-ms-flex-wrap:nowrap;flex-wrap:nowrap}.navbar-expand-md .navbar-nav-scroll{overflow:visible}.navbar-expand-md .navbar-collapse{display:-ms-flexbox!important;display:flex!important;-ms-flex-preferred-size:auto;flex-basis:auto}.navbar-expand-md .navbar-toggler{display:none}}@media (max-width:991.98px){.navbar-expand-lg>.container,.navbar-expand-lg>.container-fluid,.navbar-expand-lg>.container-lg,.navbar-expand-lg>.container-md,.navbar-expand-lg>.container-sm,.navbar-expand-lg>.container-xl{padding-right:0;padding-left:0}}@media (min-width:992px){.navbar-expand-lg{-ms-flex-flow:row nowrap;flex-flow:row nowrap;-ms-flex-pack:start;justify-content:flex-start}.navbar-expand-lg .navbar-nav{-ms-flex-direction:row;flex-direction:row}.navbar-expand-lg .navbar-nav .dropdown-menu{position:absolute}.navbar-expand-lg .navbar-nav .nav-link{padding-right:.5rem;padding-left:.5rem}.navbar-expand-lg>.container,.navbar-expand-lg>.container-fluid,.navbar-expand-lg>.container-lg,.navbar-expand-lg>.container-md,.navbar-expand-lg>.container-sm,.navbar-expand-lg>.container-xl{-ms-flex-wrap:nowrap;flex-wrap:nowrap}.navbar-expand-lg .navbar-nav-scroll{overflow:visible}.navbar-expand-lg .navbar-collapse{display:-ms-flexbox!important;display:flex!important;-ms-flex-preferred-size:auto;flex-basis:auto}.navbar-expand-lg .navbar-toggler{display:none}}@media (max-width:1199.98px){.navbar-expand-xl>.container,.navbar-expand-xl>.container-fluid,.navbar-expand-xl>.container-lg,.navbar-expand-xl>.container-md,.navbar-expand-xl>.container-sm,.navbar-expand-xl>.container-xl{padding-right:0;padding-left:0}}@media (min-width:1200px){.navbar-expand-xl{-ms-flex-flow:row nowrap;flex-flow:row nowrap;-ms-flex-pack:start;justify-content:flex-start}.navbar-expand-xl .navbar-nav{-ms-flex-direction:row;flex-direction:row}.navbar-expand-xl .navbar-nav .dropdown-menu{position:absolute}.navbar-expand-xl .navbar-nav .nav-link{padding-right:.5rem;padding-left:.5rem}.navbar-expand-xl>.container,.navbar-expand-xl>.container-fluid,.navbar-expand-xl>.container-lg,.navbar-expand-xl>.container-md,.navbar-expand-xl>.container-sm,.navbar-expand-xl>.container-xl{-ms-flex-wrap:nowrap;flex-wrap:nowrap}.navbar-expand-xl .navbar-nav-scroll{overflow:visible}.navbar-expand-xl .navbar-collapse{display:-ms-flexbox!important;display:flex!important;-ms-flex-preferred-size:auto;flex-basis:auto}.navbar-expand-xl .navbar-toggler{display:none}}.navbar-expand{-ms-flex-flow:row nowrap;flex-flow:row nowrap;-ms-flex-pack:start;justify-content:flex-start}.navbar-expand>.container,.navbar-expand>.container-fluid,.navbar-expand>.container-lg,.navbar-expand>.container-md,.navbar-expand>.container-sm,.navbar-expand>.container-xl{padding-right:0;padding-left:0}.navbar-expand .navbar-nav{-ms-flex-direction:row;flex-direction:row}.navbar-expand .navbar-nav .dropdown-menu{position:absolute}.navbar-expand .navbar-nav .nav-link{padding-right:.5rem;padding-left:.5rem}.navbar-expand>.container,.navbar-expand>.container-fluid,.navbar-expand>.container-lg,.navbar-expand>.container-md,.navbar-expand>.container-sm,.navbar-expand>.container-xl{-ms-flex-wrap:nowrap;flex-wrap:nowrap}.navbar-expand .navbar-nav-scroll{overflow:visible}.navbar-expand .navbar-collapse{display:-ms-flexbox!important;display:flex!important;-ms-flex-preferred-size:auto;flex-basis:auto}.navbar-expand .navbar-toggler{display:none}.navbar-light .navbar-brand{color:rgba(0,0,0,.9)}.navbar-light .navbar-brand:focus,.navbar-light .navbar-brand:hover{color:rgba(0,0,0,.9)}.navbar-light .navbar-nav .nav-link{color:rgba(0,0,0,.5)}.navbar-light .navbar-nav .nav-link:focus,.navbar-light .navbar-nav .nav-link:hover{color:rgba(0,0,0,.7)}.navbar-light .navbar-nav .nav-link.disabled{color:rgba(0,0,0,.3)}.navbar-light .navbar-nav .active>.nav-link,.navbar-light .navbar-nav .nav-link.active,.navbar-light .navbar-nav .nav-link.show,.navbar-light .navbar-nav .show>.nav-link{color:rgba(0,0,0,.9)}.navbar-light .navbar-toggler{color:rgba(0,0,0,.5);border-color:rgba(0,0,0,.1)}.navbar-light .navbar-toggler-icon{background-image:url("data:image/svg+xml,%3csvg xmlns='http://www.w3.org/2000/svg' width='30' height='30' viewBox='0 0 30 30'%3e%3cpath stroke='rgba%280, 0, 0, 0.5%29' stroke-linecap='round' stroke-miterlimit='10' stroke-width='2' d='M4 7h22M4 15h22M4 23h22'/%3e%3c/svg%3e")}.navbar-light .navbar-text{color:rgba(0,0,0,.5)}.navbar-light .navbar-text a{color:rgba(0,0,0,.9)}.navbar-light .navbar-text a:focus,.navbar-light .navbar-text a:hover{color:rgba(0,0,0,.9)}.navbar-dark .navbar-brand{color:#fff}.navbar-dark .navbar-brand:focus,.navbar-dark .navbar-brand:hover{color:#fff}.navbar-dark .navbar-nav .nav-link{color:rgba(255,255,255,.5)}.navbar-dark .navbar-nav .nav-link:focus,.navbar-dark .navbar-nav .nav-link:hover{color:rgba(255,255,255,.75)}.navbar-dark .navbar-nav .nav-link.disabled{color:rgba(255,255,255,.25)}.navbar-dark .navbar-nav .active>.nav-link,.navbar-dark .navbar-nav .nav-link.active,.navbar-dark .navbar-nav .nav-link.show,.navbar-dark .navbar-nav .show>.nav-link{color:#fff}.navbar-dark .navbar-toggler{color:rgba(255,255,255,.5);border-color:rgba(255,255,255,.1)}.navbar-dark .navbar-toggler-icon{background-image:url("data:image/svg+xml,%3csvg xmlns='http://www.w3.org/2000/svg' width='30' height='30' viewBox='0 0 30 30'%3e%3cpath stroke='rgba%28255, 255, 255, 0.5%29' stroke-linecap='round' stroke-miterlimit='10' stroke-width='2' d='M4 7h22M4 15h22M4 23h22'/%3e%3c/svg%3e")}.navbar-dark .navbar-text{color:rgba(255,255,255,.5)}.navbar-dark .navbar-text a{color:#fff}.navbar-dark .navbar-text a:focus,.navbar-dark .navbar-text a:hover{color:#fff}.card{position:relative;display:-ms-flexbox;display:flex;-ms-flex-direction:column;flex-direction:column;min-width:0;word-wrap:break-word;background-color:#fff;background-clip:border-box;border:1px solid rgba(0,0,0,.125);border-radius:.25rem}.card>hr{margin-right:0;margin-left:0}.card>.list-group{border-top:inherit;border-bottom:inherit}.card>.list-group:first-child{border-top-width:0;border-top-left-radius:calc(.25rem - 1px);border-top-right-radius:calc(.25rem - 1px)}.card>.list-group:last-child{border-bottom-width:0;border-bottom-right-radius:calc(.25rem - 1px);border-bottom-left-radius:calc(.25rem - 1px)}.card>.card-header+.list-group,.card>.list-group+.card-footer{border-top:0}.card-body{-ms-flex:1 1 auto;flex:1 1 auto;min-height:1px;padding:1.25rem}.card-title{margin-bottom:.75rem}.card-subtitle{margin-top:-.375rem;margin-bottom:0}.card-text:last-child{margin-bottom:0}.card-link:hover{text-decoration:none}.card-link+.card-link{margin-left:1.25rem}.card-header{padding:.75rem 1.25rem;margin-bottom:0;background-color:rgba(0,0,0,.03);border-bottom:1px solid rgba(0,0,0,.125)}.card-header:first-child{border-radius:calc(.25rem - 1px) calc(.25rem - 1px) 0 0}.card-footer{padding:.75rem 1.25rem;background-color:rgba(0,0,0,.03);border-top:1px solid rgba(0,0,0,.125)}.card-footer:last-child{border-radius:0 0 calc(.25rem - 1px) calc(.25rem - 1px)}.card-header-tabs{margin-right:-.625rem;margin-bottom:-.75rem;margin-left:-.625rem;border-bottom:0}.card-header-pills{margin-right:-.625rem;margin-left:-.625rem}.card-img-overlay{position:absolute;top:0;right:0;bottom:0;left:0;padding:1.25rem;border-radius:calc(.25rem - 1px)}.card-img,.card-img-bottom,.card-img-top{-ms-flex-negative:0;flex-shrink:0;width:100%}.card-img,.card-img-top{border-top-left-radius:calc(.25rem - 1px);border-top-right-radius:calc(.25rem - 1px)}.card-img,.card-img-bottom{border-bottom-right-radius:calc(.25rem - 1px);border-bottom-left-radius:calc(.25rem - 1px)}.card-deck .card{margin-bottom:15px}@media (min-width:576px){.card-deck{display:-ms-flexbox;display:flex;-ms-flex-flow:row wrap;flex-flow:row wrap;margin-right:-15px;margin-left:-15px}.card-deck .card{-ms-flex:1 0 0%;flex:1 0 0%;margin-right:15px;margin-bottom:0;margin-left:15px}}.card-group>.card{margin-bottom:15px}@media (min-width:576px){.card-group{display:-ms-flexbox;display:flex;-ms-flex-flow:row wrap;flex-flow:row wrap}.card-group>.card{-ms-flex:1 0 0%;flex:1 0 0%;margin-bottom:0}.card-group>.card+.card{margin-left:0;border-left:0}.card-group>.card:not(:last-child){border-top-right-radius:0;border-bottom-right-radius:0}.card-group>.card:not(:last-child) .card-header,.card-group>.card:not(:last-child) .card-img-top{border-top-right-radius:0}.card-group>.card:not(:last-child) .card-footer,.card-group>.card:not(:last-child) .card-img-bottom{border-bottom-right-radius:0}.card-group>.card:not(:first-child){border-top-left-radius:0;border-bottom-left-radius:0}.card-group>.card:not(:first-child) .card-header,.card-group>.card:not(:first-child) .card-img-top{border-top-left-radius:0}.card-group>.card:not(:first-child) .card-footer,.card-group>.card:not(:first-child) .card-img-bottom{border-bottom-left-radius:0}}.card-columns .card{margin-bottom:.75rem}@media (min-width:576px){.card-columns{-webkit-column-count:3;-moz-column-count:3;column-count:3;-webkit-column-gap:1.25rem;-moz-column-gap:1.25rem;column-gap:1.25rem;orphans:1;widows:1}.card-columns .card{display:inline-block;width:100%}}.accordion{overflow-anchor:none}.accordion>.card{overflow:hidden}.accordion>.card:not(:last-of-type){border-bottom:0;border-bottom-right-radius:0;border-bottom-left-radius:0}.accordion>.card:not(:first-of-type){border-top-left-radius:0;border-top-right-radius:0}.accordion>.card>.card-header{border-radius:0;margin-bottom:-1px}.breadcrumb{display:-ms-flexbox;display:flex;-ms-flex-wrap:wrap;flex-wrap:wrap;padding:.75rem 1rem;margin-bottom:1rem;list-style:none;background-color:#e9ecef;border-radius:.25rem}.breadcrumb-item+.breadcrumb-item{padding-left:.5rem}.breadcrumb-item+.breadcrumb-item::before{float:left;padding-right:.5rem;color:#6c757d;content:"/"}.breadcrumb-item+.breadcrumb-item:hover::before{text-decoration:underline}.breadcrumb-item+.breadcrumb-item:hover::before{text-decoration:none}.breadcrumb-item.active{color:#6c757d}.pagination{display:-ms-flexbox;display:flex;padding-left:0;list-style:none;border-radius:.25rem}.page-link{position:relative;display:block;padding:.5rem .75rem;margin-left:-1px;line-height:1.25;color:#007bff;background-color:#fff;border:1px solid #dee2e6}.page-link:hover{z-index:2;color:#0056b3;text-decoration:none;background-color:#e9ecef;border-color:#dee2e6}.page-link:focus{z-index:3;outline:0;box-shadow:0 0 0 .2rem rgba(0,123,255,.25)}.page-item:first-child .page-link{margin-left:0;border-top-left-radius:.25rem;border-bottom-left-radius:.25rem}.page-item:last-child .page-link{border-top-right-radius:.25rem;border-bottom-right-radius:.25rem}.page-item.active .page-link{z-index:3;color:#fff;background-color:#007bff;border-color:#007bff}.page-item.disabled .page-link{color:#6c757d;pointer-events:none;cursor:auto;background-color:#fff;border-color:#dee2e6}.pagination-lg .page-link{padding:.75rem 1.5rem;font-size:1.25rem;line-height:1.5}.pagination-lg .page-item:first-child .page-link{border-top-left-radius:.3rem;border-bottom-left-radius:.3rem}.pagination-lg .page-item:last-child .page-link{border-top-right-radius:.3rem;border-bottom-right-radius:.3rem}.pagination-sm .page-link{padding:.25rem .5rem;font-size:.875rem;line-height:1.5}.pagination-sm .page-item:first-child .page-link{border-top-left-radius:.2rem;border-bottom-left-radius:.2rem}.pagination-sm .page-item:last-child .page-link{border-top-right-radius:.2rem;border-bottom-right-radius:.2rem}.badge{display:inline-block;padding:.25em .4em;font-size:75%;font-weight:700;line-height:1;text-align:center;white-space:nowrap;vertical-align:baseline;border-radius:.25rem;transition:color .15s ease-in-out,background-color .15s ease-in-out,border-color .15s ease-in-out,box-shadow .15s ease-in-out}@media (prefers-reduced-motion:reduce){.badge{transition:none}}a.badge:focus,a.badge:hover{text-decoration:none}.badge:empty{display:none}.btn .badge{position:relative;top:-1px}.badge-pill{padding-right:.6em;padding-left:.6em;border-radius:10rem}.badge-primary{color:#fff;background-color:#007bff}a.badge-primary:focus,a.badge-primary:hover{color:#fff;background-color:#0062cc}a.badge-primary.focus,a.badge-primary:focus{outline:0;box-shadow:0 0 0 .2rem rgba(0,123,255,.5)}.badge-secondary{color:#fff;background-color:#6c757d}a.badge-secondary:focus,a.badge-secondary:hover{color:#fff;background-color:#545b62}a.badge-secondary.focus,a.badge-secondary:focus{outline:0;box-shadow:0 0 0 .2rem rgba(108,117,125,.5)}.badge-success{color:#fff;background-color:#28a745}a.badge-success:focus,a.badge-success:hover{color:#fff;background-color:#1e7e34}a.badge-success.focus,a.badge-success:focus{outline:0;box-shadow:0 0 0 .2rem rgba(40,167,69,.5)}.badge-info{color:#fff;background-color:#17a2b8}a.badge-info:focus,a.badge-info:hover{color:#fff;background-color:#117a8b}a.badge-info.focus,a.badge-info:focus{outline:0;box-shadow:0 0 0 .2rem rgba(23,162,184,.5)}.badge-warning{color:#212529;background-color:#ffc107}a.badge-warning:focus,a.badge-warning:hover{color:#212529;background-color:#d39e00}a.badge-warning.focus,a.badge-warning:focus{outline:0;box-shadow:0 0 0 .2rem rgba(255,193,7,.5)}.badge-danger{color:#fff;background-color:#dc3545}a.badge-danger:focus,a.badge-danger:hover{color:#fff;background-color:#bd2130}a.badge-danger.focus,a.badge-danger:focus{outline:0;box-shadow:0 0 0 .2rem rgba(220,53,69,.5)}.badge-light{color:#212529;background-color:#f8f9fa}a.badge-light:focus,a.badge-light:hover{color:#212529;background-color:#dae0e5}a.badge-light.focus,a.badge-light:focus{outline:0;box-shadow:0 0 0 .2rem rgba(248,249,250,.5)}.badge-dark{color:#fff;background-color:#343a40}a.badge-dark:focus,a.badge-dark:hover{color:#fff;background-color:#1d2124}a.badge-dark.focus,a.badge-dark:focus{outline:0;box-shadow:0 0 0 .2rem rgba(52,58,64,.5)}.jumbotron{padding:2rem 1rem;margin-bottom:2rem;background-color:#e9ecef;border-radius:.3rem}@media (min-width:576px){.jumbotron{padding:4rem 2rem}}.jumbotron-fluid{padding-right:0;padding-left:0;border-radius:0}.alert{position:relative;padding:.75rem 1.25rem;margin-bottom:1rem;border:1px solid transparent;border-radius:.25rem}.alert-heading{color:inherit}.alert-link{font-weight:700}.alert-dismissible{padding-right:4rem}.alert-dismissible .close{position:absolute;top:0;right:0;z-index:2;padding:.75rem 1.25rem;color:inherit}.alert-primary{color:#004085;background-color:#cce5ff;border-color:#b8daff}.alert-primary hr{border-top-color:#9fcdff}.alert-primary .alert-link{color:#002752}.alert-secondary{color:#383d41;background-color:#e2e3e5;border-color:#d6d8db}.alert-secondary hr{border-top-color:#c8cbcf}.alert-secondary .alert-link{color:#202326}.alert-success{color:#155724;background-color:#d4edda;border-color:#c3e6cb}.alert-success hr{border-top-color:#b1dfbb}.alert-success .alert-link{color:#0b2e13}.alert-info{color:#0c5460;background-color:#d1ecf1;border-color:#bee5eb}.alert-info hr{border-top-color:#abdde5}.alert-info .alert-link{color:#062c33}.alert-warning{color:#856404;background-color:#fff3cd;border-color:#ffeeba}.alert-warning hr{border-top-color:#ffe8a1}.alert-warning .alert-link{color:#533f03}.alert-danger{color:#721c24;background-color:#f8d7da;border-color:#f5c6cb}.alert-danger hr{border-top-color:#f1b0b7}.alert-danger .alert-link{color:#491217}.alert-light{color:#818182;background-color:#fefefe;border-color:#fdfdfe}.alert-light hr{border-top-color:#ececf6}.alert-light .alert-link{color:#686868}.alert-dark{color:#1b1e21;background-color:#d6d8d9;border-color:#c6c8ca}.alert-dark hr{border-top-color:#b9bbbe}.alert-dark .alert-link{color:#040505}@-webkit-keyframes progress-bar-stripes{from{background-position:1rem 0}to{background-position:0 0}}@keyframes progress-bar-stripes{from{background-position:1rem 0}to{background-position:0 0}}.progress{display:-ms-flexbox;display:flex;height:1rem;overflow:hidden;line-height:0;font-size:.75rem;background-color:#e9ecef;border-radius:.25rem}.progress-bar{display:-ms-flexbox;display:flex;-ms-flex-direction:column;flex-direction:column;-ms-flex-pack:center;justify-content:center;overflow:hidden;color:#fff;text-align:center;white-space:nowrap;background-color:#007bff;transition:width .6s ease}@media (prefers-reduced-motion:reduce){.progress-bar{transition:none}}.progress-bar-striped{background-image:linear-gradient(45deg,rgba(255,255,255,.15) 25%,transparent 25%,transparent 50%,rgba(255,255,255,.15) 50%,rgba(255,255,255,.15) 75%,transparent 75%,transparent);background-size:1rem 1rem}.progress-bar-animated{-webkit-animation:1s linear infinite progress-bar-stripes;animation:1s linear infinite progress-bar-stripes}@media (prefers-reduced-motion:reduce){.progress-bar-animated{-webkit-animation:none;animation:none}}.media{display:-ms-flexbox;display:flex;-ms-flex-align:start;align-items:flex-start}.media-body{-ms-flex:1;flex:1}.list-group{display:-ms-flexbox;display:flex;-ms-flex-direction:column;flex-direction:column;padding-left:0;margin-bottom:0;border-radius:.25rem}.list-group-item-action{width:100%;color:#495057;text-align:inherit}.list-group-item-action:focus,.list-group-item-action:hover{z-index:1;color:#495057;text-decoration:none;background-color:#f8f9fa}.list-group-item-action:active{color:#212529;background-color:#e9ecef}.list-group-item{position:relative;display:block;padding:.75rem 1.25rem;background-color:#fff;border:1px solid rgba(0,0,0,.125)}.list-group-item:first-child{border-top-left-radius:inherit;border-top-right-radius:inherit}.list-group-item:last-child{border-bottom-right-radius:inherit;border-bottom-left-radius:inherit}.list-group-item.disabled,.list-group-item:disabled{color:#6c757d;pointer-events:none;background-color:#fff}.list-group-item.active{z-index:2;color:#fff;background-color:#007bff;border-color:#007bff}.list-group-item+.list-group-item{border-top-width:0}.list-group-item+.list-group-item.active{margin-top:-1px;border-top-width:1px}.list-group-horizontal{-ms-flex-direction:row;flex-direction:row}.list-group-horizontal>.list-group-item:first-child{border-bottom-left-radius:.25rem;border-top-right-radius:0}.list-group-horizontal>.list-group-item:last-child{border-top-right-radius:.25rem;border-bottom-left-radius:0}.list-group-horizontal>.list-group-item.active{margin-top:0}.list-group-horizontal>.list-group-item+.list-group-item{border-top-width:1px;border-left-width:0}.list-group-horizontal>.list-group-item+.list-group-item.active{margin-left:-1px;border-left-width:1px}@media (min-width:576px){.list-group-horizontal-sm{-ms-flex-direction:row;flex-direction:row}.list-group-horizontal-sm>.list-group-item:first-child{border-bottom-left-radius:.25rem;border-top-right-radius:0}.list-group-horizontal-sm>.list-group-item:last-child{border-top-right-radius:.25rem;border-bottom-left-radius:0}.list-group-horizontal-sm>.list-group-item.active{margin-top:0}.list-group-horizontal-sm>.list-group-item+.list-group-item{border-top-width:1px;border-left-width:0}.list-group-horizontal-sm>.list-group-item+.list-group-item.active{margin-left:-1px;border-left-width:1px}}@media (min-width:768px){.list-group-horizontal-md{-ms-flex-direction:row;flex-direction:row}.list-group-horizontal-md>.list-group-item:first-child{border-bottom-left-radius:.25rem;border-top-right-radius:0}.list-group-horizontal-md>.list-group-item:last-child{border-top-right-radius:.25rem;border-bottom-left-radius:0}.list-group-horizontal-md>.list-group-item.active{margin-top:0}.list-group-horizontal-md>.list-group-item+.list-group-item{border-top-width:1px;border-left-width:0}.list-group-horizontal-md>.list-group-item+.list-group-item.active{margin-left:-1px;border-left-width:1px}}@media (min-width:992px){.list-group-horizontal-lg{-ms-flex-direction:row;flex-direction:row}.list-group-horizontal-lg>.list-group-item:first-child{border-bottom-left-radius:.25rem;border-top-right-radius:0}.list-group-horizontal-lg>.list-group-item:last-child{border-top-right-radius:.25rem;border-bottom-left-radius:0}.list-group-horizontal-lg>.list-group-item.active{margin-top:0}.list-group-horizontal-lg>.list-group-item+.list-group-item{border-top-width:1px;border-left-width:0}.list-group-horizontal-lg>.list-group-item+.list-group-item.active{margin-left:-1px;border-left-width:1px}}@media (min-width:1200px){.list-group-horizontal-xl{-ms-flex-direction:row;flex-direction:row}.list-group-horizontal-xl>.list-group-item:first-child{border-bottom-left-radius:.25rem;border-top-right-radius:0}.list-group-horizontal-xl>.list-group-item:last-child{border-top-right-radius:.25rem;border-bottom-left-radius:0}.list-group-horizontal-xl>.list-group-item.active{margin-top:0}.list-group-horizontal-xl>.list-group-item+.list-group-item{border-top-width:1px;border-left-width:0}.list-group-horizontal-xl>.list-group-item+.list-group-item.active{margin-left:-1px;border-left-width:1px}}.list-group-flush{border-radius:0}.list-group-flush>.list-group-item{border-width:0 0 1px}.list-group-flush>.list-group-item:last-child{border-bottom-width:0}.list-group-item-primary{color:#004085;background-color:#b8daff}.list-group-item-primary.list-group-item-action:focus,.list-group-item-primary.list-group-item-action:hover{color:#004085;background-color:#9fcdff}.list-group-item-primary.list-group-item-action.active{color:#fff;background-color:#004085;border-color:#004085}.list-group-item-secondary{color:#383d41;background-color:#d6d8db}.list-group-item-secondary.list-group-item-action:focus,.list-group-item-secondary.list-group-item-action:hover{color:#383d41;background-color:#c8cbcf}.list-group-item-secondary.list-group-item-action.active{color:#fff;background-color:#383d41;border-color:#383d41}.list-group-item-success{color:#155724;background-color:#c3e6cb}.list-group-item-success.list-group-item-action:focus,.list-group-item-success.list-group-item-action:hover{color:#155724;background-color:#b1dfbb}.list-group-item-success.list-group-item-action.active{color:#fff;background-color:#155724;border-color:#155724}.list-group-item-info{color:#0c5460;background-color:#bee5eb}.list-group-item-info.list-group-item-action:focus,.list-group-item-info.list-group-item-action:hover{color:#0c5460;background-color:#abdde5}.list-group-item-info.list-group-item-action.active{color:#fff;background-color:#0c5460;border-color:#0c5460}.list-group-item-warning{color:#856404;background-color:#ffeeba}.list-group-item-warning.list-group-item-action:focus,.list-group-item-warning.list-group-item-action:hover{color:#856404;background-color:#ffe8a1}.list-group-item-warning.list-group-item-action.active{color:#fff;background-color:#856404;border-color:#856404}.list-group-item-danger{color:#721c24;background-color:#f5c6cb}.list-group-item-danger.list-group-item-action:focus,.list-group-item-danger.list-group-item-action:hover{color:#721c24;background-color:#f1b0b7}.list-group-item-danger.list-group-item-action.active{color:#fff;background-color:#721c24;border-color:#721c24}.list-group-item-light{color:#818182;background-color:#fdfdfe}.list-group-item-light.list-group-item-action:focus,.list-group-item-light.list-group-item-action:hover{color:#818182;background-color:#ececf6}.list-group-item-light.list-group-item-action.active{color:#fff;background-color:#818182;border-color:#818182}.list-group-item-dark{color:#1b1e21;background-color:#c6c8ca}.list-group-item-dark.list-group-item-action:focus,.list-group-item-dark.list-group-item-action:hover{color:#1b1e21;background-color:#b9bbbe}.list-group-item-dark.list-group-item-action.active{color:#fff;background-color:#1b1e21;border-color:#1b1e21}.close{float:right;font-size:1.5rem;font-weight:700;line-height:1;color:#000;text-shadow:0 1px 0 #fff;opacity:.5}.close:hover{color:#000;text-decoration:none}.close:not(:disabled):not(.disabled):focus,.close:not(:disabled):not(.disabled):hover{opacity:.75}button.close{padding:0;background-color:transparent;border:0}a.close.disabled{pointer-events:none}.toast{-ms-flex-preferred-size:350px;flex-basis:350px;max-width:350px;font-size:.875rem;background-color:rgba(255,255,255,.85);background-clip:padding-box;border:1px solid rgba(0,0,0,.1);box-shadow:0 .25rem .75rem rgba(0,0,0,.1);opacity:0;border-radius:.25rem}.toast:not(:last-child){margin-bottom:.75rem}.toast.showing{opacity:1}.toast.show{display:block;opacity:1}.toast.hide{display:none}.toast-header{display:-ms-flexbox;display:flex;-ms-flex-align:center;align-items:center;padding:.25rem .75rem;color:#6c757d;background-color:rgba(255,255,255,.85);background-clip:padding-box;border-bottom:1px solid rgba(0,0,0,.05);border-top-left-radius:calc(.25rem - 1px);border-top-right-radius:calc(.25rem - 1px)}.toast-body{padding:.75rem}.modal-open{overflow:hidden}.modal-open .modal{overflow-x:hidden;overflow-y:auto}.modal{position:fixed;top:0;left:0;z-index:1050;display:none;width:100%;height:100%;overflow:hidden;outline:0}.modal-dialog{position:relative;width:auto;margin:.5rem;pointer-events:none}.modal.fade .modal-dialog{transition:-webkit-transform .3s ease-out;transition:transform .3s ease-out;transition:transform .3s ease-out,-webkit-transform .3s ease-out;-webkit-transform:translate(0,-50px);transform:translate(0,-50px)}@media (prefers-reduced-motion:reduce){.modal.fade .modal-dialog{transition:none}}.modal.show .modal-dialog{-webkit-transform:none;transform:none}.modal.modal-static .modal-dialog{-webkit-transform:scale(1.02);transform:scale(1.02)}.modal-dialog-scrollable{display:-ms-flexbox;display:flex;max-height:calc(100% - 1rem)}.modal-dialog-scrollable .modal-content{max-height:calc(100vh - 1rem);overflow:hidden}.modal-dialog-scrollable .modal-footer,.modal-dialog-scrollable .modal-header{-ms-flex-negative:0;flex-shrink:0}.modal-dialog-scrollable .modal-body{overflow-y:auto}.modal-dialog-centered{display:-ms-flexbox;display:flex;-ms-flex-align:center;align-items:center;min-height:calc(100% - 1rem)}.modal-dialog-centered::before{display:block;height:calc(100vh - 1rem);height:-webkit-min-content;height:-moz-min-content;height:min-content;content:""}.modal-dialog-centered.modal-dialog-scrollable{-ms-flex-direction:column;flex-direction:column;-ms-flex-pack:center;justify-content:center;height:100%}.modal-dialog-centered.modal-dialog-scrollable .modal-content{max-height:none}.modal-dialog-centered.modal-dialog-scrollable::before{content:none}.modal-content{position:relative;display:-ms-flexbox;display:flex;-ms-flex-direction:column;flex-direction:column;width:100%;pointer-events:auto;background-color:#fff;background-clip:padding-box;border:1px solid rgba(0,0,0,.2);border-radius:.3rem;outline:0}.modal-backdrop{position:fixed;top:0;left:0;z-index:1040;width:100vw;height:100vh;background-color:#000}.modal-backdrop.fade{opacity:0}.modal-backdrop.show{opacity:.5}.modal-header{display:-ms-flexbox;display:flex;-ms-flex-align:start;align-items:flex-start;-ms-flex-pack:justify;justify-content:space-between;padding:1rem 1rem;border-bottom:1px solid #dee2e6;border-top-left-radius:calc(.3rem - 1px);border-top-right-radius:calc(.3rem - 1px)}.modal-header .close{padding:1rem 1rem;margin:-1rem -1rem -1rem auto}.modal-title{margin-bottom:0;line-height:1.5}.modal-body{position:relative;-ms-flex:1 1 auto;flex:1 1 auto;padding:1rem}.modal-footer{display:-ms-flexbox;display:flex;-ms-flex-wrap:wrap;flex-wrap:wrap;-ms-flex-align:center;align-items:center;-ms-flex-pack:end;justify-content:flex-end;padding:.75rem;border-top:1px solid #dee2e6;border-bottom-right-radius:calc(.3rem - 1px);border-bottom-left-radius:calc(.3rem - 1px)}.modal-footer>*{margin:.25rem}.modal-scrollbar-measure{position:absolute;top:-9999px;width:50px;height:50px;overflow:scroll}@media (min-width:576px){.modal-dialog{max-width:500px;margin:1.75rem auto}.modal-dialog-scrollable{max-height:calc(100% - 3.5rem)}.modal-dialog-scrollable .modal-content{max-height:calc(100vh - 3.5rem)}.modal-dialog-centered{min-height:calc(100% - 3.5rem)}.modal-dialog-centered::before{height:calc(100vh - 3.5rem);height:-webkit-min-content;height:-moz-min-content;height:min-content}.modal-sm{max-width:300px}}@media (min-width:992px){.modal-lg,.modal-xl{max-width:800px}}@media (min-width:1200px){.modal-xl{max-width:1140px}}.tooltip{position:absolute;z-index:1070;display:block;margin:0;font-family:-apple-system,BlinkMacSystemFont,"Segoe UI",Roboto,"Helvetica Neue",Arial,"Noto Sans","Liberation Sans",sans-serif,"Apple Color Emoji","Segoe UI Emoji","Segoe UI Symbol","Noto Color Emoji";font-style:normal;font-weight:400;line-height:1.5;text-align:left;text-align:start;text-decoration:none;text-shadow:none;text-transform:none;letter-spacing:normal;word-break:normal;white-space:normal;word-spacing:normal;line-break:auto;font-size:.875rem;word-wrap:break-word;opacity:0}.tooltip.show{opacity:.9}.tooltip .arrow{position:absolute;display:block;width:.8rem;height:.4rem}.tooltip .arrow::before{position:absolute;content:"";border-color:transparent;border-style:solid}.bs-tooltip-auto[x-placement^=top],.bs-tooltip-top{padding:.4rem 0}.bs-tooltip-auto[x-placement^=top] .arrow,.bs-tooltip-top .arrow{bottom:0}.bs-tooltip-auto[x-placement^=top] .arrow::before,.bs-tooltip-top .arrow::before{top:0;border-width:.4rem .4rem 0;border-top-color:#000}.bs-tooltip-auto[x-placement^=right],.bs-tooltip-right{padding:0 .4rem}.bs-tooltip-auto[x-placement^=right] .arrow,.bs-tooltip-right .arrow{left:0;width:.4rem;height:.8rem}.bs-tooltip-auto[x-placement^=right] .arrow::before,.bs-tooltip-right .arrow::before{right:0;border-width:.4rem .4rem .4rem 0;border-right-color:#000}.bs-tooltip-auto[x-placement^=bottom],.bs-tooltip-bottom{padding:.4rem 0}.bs-tooltip-auto[x-placement^=bottom] .arrow,.bs-tooltip-bottom .arrow{top:0}.bs-tooltip-auto[x-placement^=bottom] .arrow::before,.bs-tooltip-bottom .arrow::before{bottom:0;border-width:0 .4rem .4rem;border-bottom-color:#000}.bs-tooltip-auto[x-placement^=left],.bs-tooltip-left{padding:0 .4rem}.bs-tooltip-auto[x-placement^=left] .arrow,.bs-tooltip-left .arrow{right:0;width:.4rem;height:.8rem}.bs-tooltip-auto[x-placement^=left] .arrow::before,.bs-tooltip-left .arrow::before{left:0;border-width:.4rem 0 .4rem .4rem;border-left-color:#000}.tooltip-inner{max-width:200px;padding:.25rem .5rem;color:#fff;text-align:center;background-color:#000;border-radius:.25rem}.popover{position:absolute;top:0;left:0;z-index:1060;display:block;max-width:276px;font-family:-apple-system,BlinkMacSystemFont,"Segoe UI",Roboto,"Helvetica Neue",Arial,"Noto Sans","Liberation Sans",sans-serif,"Apple Color Emoji","Segoe UI Emoji","Segoe UI Symbol","Noto Color Emoji";font-style:normal;font-weight:400;line-height:1.5;text-align:left;text-align:start;text-decoration:none;text-shadow:none;text-transform:none;letter-spacing:normal;word-break:normal;white-space:normal;word-spacing:normal;line-break:auto;font-size:.875rem;word-wrap:break-word;background-color:#fff;background-clip:padding-box;border:1px solid rgba(0,0,0,.2);border-radius:.3rem}.popover .arrow{position:absolute;display:block;width:1rem;height:.5rem;margin:0 .3rem}.popover .arrow::after,.popover .arrow::before{position:absolute;display:block;content:"";border-color:transparent;border-style:solid}.bs-popover-auto[x-placement^=top],.bs-popover-top{margin-bottom:.5rem}.bs-popover-auto[x-placement^=top]>.arrow,.bs-popover-top>.arrow{bottom:calc(-.5rem - 1px)}.bs-popover-auto[x-placement^=top]>.arrow::before,.bs-popover-top>.arrow::before{bottom:0;border-width:.5rem .5rem 0;border-top-color:rgba(0,0,0,.25)}.bs-popover-auto[x-placement^=top]>.arrow::after,.bs-popover-top>.arrow::after{bottom:1px;border-width:.5rem .5rem 0;border-top-color:#fff}.bs-popover-auto[x-placement^=right],.bs-popover-right{margin-left:.5rem}.bs-popover-auto[x-placement^=right]>.arrow,.bs-popover-right>.arrow{left:calc(-.5rem - 1px);width:.5rem;height:1rem;margin:.3rem 0}.bs-popover-auto[x-placement^=right]>.arrow::before,.bs-popover-right>.arrow::before{left:0;border-width:.5rem .5rem .5rem 0;border-right-color:rgba(0,0,0,.25)}.bs-popover-auto[x-placement^=right]>.arrow::after,.bs-popover-right>.arrow::after{left:1px;border-width:.5rem .5rem .5rem 0;border-right-color:#fff}.bs-popover-auto[x-placement^=bottom],.bs-popover-bottom{margin-top:.5rem}.bs-popover-auto[x-placement^=bottom]>.arrow,.bs-popover-bottom>.arrow{top:calc(-.5rem - 1px)}.bs-popover-auto[x-placement^=bottom]>.arrow::before,.bs-popover-bottom>.arrow::before{top:0;border-width:0 .5rem .5rem .5rem;border-bottom-color:rgba(0,0,0,.25)}.bs-popover-auto[x-placement^=bottom]>.arrow::after,.bs-popover-bottom>.arrow::after{top:1px;border-width:0 .5rem .5rem .5rem;border-bottom-color:#fff}.bs-popover-auto[x-placement^=bottom] .popover-header::before,.bs-popover-bottom .popover-header::before{position:absolute;top:0;left:50%;display:block;width:1rem;margin-left:-.5rem;content:"";border-bottom:1px solid #f7f7f7}.bs-popover-auto[x-placement^=left],.bs-popover-left{margin-right:.5rem}.bs-popover-auto[x-placement^=left]>.arrow,.bs-popover-left>.arrow{right:calc(-.5rem - 1px);width:.5rem;height:1rem;margin:.3rem 0}.bs-popover-auto[x-placement^=left]>.arrow::before,.bs-popover-left>.arrow::before{right:0;border-width:.5rem 0 .5rem .5rem;border-left-color:rgba(0,0,0,.25)}.bs-popover-auto[x-placement^=left]>.arrow::after,.bs-popover-left>.arrow::after{right:1px;border-width:.5rem 0 .5rem .5rem;border-left-color:#fff}.popover-header{padding:.5rem .75rem;margin-bottom:0;font-size:1rem;background-color:#f7f7f7;border-bottom:1px solid #ebebeb;border-top-left-radius:calc(.3rem - 1px);border-top-right-radius:calc(.3rem - 1px)}.popover-header:empty{display:none}.popover-body{padding:.5rem .75rem;color:#212529}.carousel{position:relative}.carousel.pointer-event{-ms-touch-action:pan-y;touch-action:pan-y}.carousel-inner{position:relative;width:100%;overflow:hidden}.carousel-inner::after{display:block;clear:both;content:""}.carousel-item{position:relative;display:none;float:left;width:100%;margin-right:-100%;-webkit-backface-visibility:hidden;backface-visibility:hidden;transition:-webkit-transform .6s ease-in-out;transition:transform .6s ease-in-out;transition:transform .6s ease-in-out,-webkit-transform .6s ease-in-out}@media (prefers-reduced-motion:reduce){.carousel-item{transition:none}}.carousel-item-next,.carousel-item-prev,.carousel-item.active{display:block}.active.carousel-item-right,.carousel-item-next:not(.carousel-item-left){-webkit-transform:translateX(100%);transform:translateX(100%)}.active.carousel-item-left,.carousel-item-prev:not(.carousel-item-right){-webkit-transform:translateX(-100%);transform:translateX(-100%)}.carousel-fade .carousel-item{opacity:0;transition-property:opacity;-webkit-transform:none;transform:none}.carousel-fade .carousel-item-next.carousel-item-left,.carousel-fade .carousel-item-prev.carousel-item-right,.carousel-fade .carousel-item.active{z-index:1;opacity:1}.carousel-fade .active.carousel-item-left,.carousel-fade .active.carousel-item-right{z-index:0;opacity:0;transition:opacity 0s .6s}@media (prefers-reduced-motion:reduce){.carousel-fade .active.carousel-item-left,.carousel-fade .active.carousel-item-right{transition:none}}.carousel-control-next,.carousel-control-prev{position:absolute;top:0;bottom:0;z-index:1;display:-ms-flexbox;display:flex;-ms-flex-align:center;align-items:center;-ms-flex-pack:center;justify-content:center;width:15%;padding:0;color:#fff;text-align:center;background:0 0;border:0;opacity:.5;transition:opacity .15s ease}@media (prefers-reduced-motion:reduce){.carousel-control-next,.carousel-control-prev{transition:none}}.carousel-control-next:focus,.carousel-control-next:hover,.carousel-control-prev:focus,.carousel-control-prev:hover{color:#fff;text-decoration:none;outline:0;opacity:.9}.carousel-control-prev{left:0}.carousel-control-next{right:0}.carousel-control-next-icon,.carousel-control-prev-icon{display:inline-block;width:20px;height:20px;background:50%/100% 100% no-repeat}.carousel-control-prev-icon{background-image:url("data:image/svg+xml,%3csvg xmlns='http://www.w3.org/2000/svg' fill='%23fff' width='8' height='8' viewBox='0 0 8 8'%3e%3cpath d='M5.25 0l-4 4 4 4 1.5-1.5L4.25 4l2.5-2.5L5.25 0z'/%3e%3c/svg%3e")}.carousel-control-next-icon{background-image:url("data:image/svg+xml,%3csvg xmlns='http://www.w3.org/2000/svg' fill='%23fff' width='8' height='8' viewBox='0 0 8 8'%3e%3cpath d='M2.75 0l-1.5 1.5L3.75 4l-2.5 2.5L2.75 8l4-4-4-4z'/%3e%3c/svg%3e")}.carousel-indicators{position:absolute;right:0;bottom:0;left:0;z-index:15;display:-ms-flexbox;display:flex;-ms-flex-pack:center;justify-content:center;padding-left:0;margin-right:15%;margin-left:15%;list-style:none}.carousel-indicators li{box-sizing:content-box;-ms-flex:0 1 auto;flex:0 1 auto;width:30px;height:3px;margin-right:3px;margin-left:3px;text-indent:-999px;cursor:pointer;background-color:#fff;background-clip:padding-box;border-top:10px solid transparent;border-bottom:10px solid transparent;opacity:.5;transition:opacity .6s ease}@media (prefers-reduced-motion:reduce){.carousel-indicators li{transition:none}}.carousel-indicators .active{opacity:1}.carousel-caption{position:absolute;right:15%;bottom:20px;left:15%;z-index:10;padding-top:20px;padding-bottom:20px;color:#fff;text-align:center}@-webkit-keyframes spinner-border{to{-webkit-transform:rotate(360deg);transform:rotate(360deg)}}@keyframes spinner-border{to{-webkit-transform:rotate(360deg);transform:rotate(360deg)}}.spinner-border{display:inline-block;width:2rem;height:2rem;vertical-align:-.125em;border:.25em solid currentcolor;border-right-color:transparent;border-radius:50%;-webkit-animation:.75s linear infinite spinner-border;animation:.75s linear infinite spinner-border}.spinner-border-sm{width:1rem;height:1rem;border-width:.2em}@-webkit-keyframes spinner-grow{0%{-webkit-transform:scale(0);transform:scale(0)}50%{opacity:1;-webkit-transform:none;transform:none}}@keyframes spinner-grow{0%{-webkit-transform:scale(0);transform:scale(0)}50%{opacity:1;-webkit-transform:none;transform:none}}.spinner-grow{display:inline-block;width:2rem;height:2rem;vertical-align:-.125em;background-color:currentcolor;border-radius:50%;opacity:0;-webkit-animation:.75s linear infinite spinner-grow;animation:.75s linear infinite spinner-grow}.spinner-grow-sm{width:1rem;height:1rem}@media (prefers-reduced-motion:reduce){.spinner-border,.spinner-grow{-webkit-animation-duration:1.5s;animation-duration:1.5s}}.align-baseline{vertical-align:baseline!important}.align-top{vertical-align:top!important}.align-middle{vertical-align:middle!important}.align-bottom{vertical-align:bottom!important}.align-text-bottom{vertical-align:text-bottom!important}.align-text-top{vertical-align:text-top!important}.bg-primary{background-color:#007bff!important}a.bg-primary:focus,a.bg-primary:hover,button.bg-primary:focus,button.bg-primary:hover{background-color:#0062cc!important}.bg-secondary{background-color:#6c757d!important}a.bg-secondary:focus,a.bg-secondary:hover,button.bg-secondary:focus,button.bg-secondary:hover{background-color:#545b62!important}.bg-success{background-color:#28a745!important}a.bg-success:focus,a.bg-success:hover,button.bg-success:focus,button.bg-success:hover{background-color:#1e7e34!important}.bg-info{background-color:#17a2b8!important}a.bg-info:focus,a.bg-info:hover,button.bg-info:focus,button.bg-info:hover{background-color:#117a8b!important}.bg-warning{background-color:#ffc107!important}a.bg-warning:focus,a.bg-warning:hover,button.bg-warning:focus,button.bg-warning:hover{background-color:#d39e00!important}.bg-danger{background-color:#dc3545!important}a.bg-danger:focus,a.bg-danger:hover,button.bg-danger:focus,button.bg-danger:hover{background-color:#bd2130!important}.bg-light{background-color:#f8f9fa!important}a.bg-light:focus,a.bg-light:hover,button.bg-light:focus,button.bg-light:hover{background-color:#dae0e5!important}.bg-dark{background-color:#343a40!important}a.bg-dark:focus,a.bg-dark:hover,button.bg-dark:focus,button.bg-dark:hover{background-color:#1d2124!important}.bg-white{background-color:#fff!important}.bg-transparent{background-color:transparent!important}.border{border:1px solid #dee2e6!important}.border-top{border-top:1px solid #dee2e6!important}.border-right{border-right:1px solid #dee2e6!important}.border-bottom{border-bottom:1px solid #dee2e6!important}.border-left{border-left:1px solid #dee2e6!important}.border-0{border:0!important}.border-top-0{border-top:0!important}.border-right-0{border-right:0!important}.border-bottom-0{border-bottom:0!important}.border-left-0{border-left:0!important}.border-primary{border-color:#007bff!important}.border-secondary{border-color:#6c757d!important}.border-success{border-color:#28a745!important}.border-info{border-color:#17a2b8!important}.border-warning{border-color:#ffc107!important}.border-danger{border-color:#dc3545!important}.border-light{border-color:#f8f9fa!important}.border-dark{border-color:#343a40!important}.border-white{border-color:#fff!important}.rounded-sm{border-radius:.2rem!important}.rounded{border-radius:.25rem!important}.rounded-top{border-top-left-radius:.25rem!important;border-top-right-radius:.25rem!important}.rounded-right{border-top-right-radius:.25rem!important;border-bottom-right-radius:.25rem!important}.rounded-bottom{border-bottom-right-radius:.25rem!important;border-bottom-left-radius:.25rem!important}.rounded-left{border-top-left-radius:.25rem!important;border-bottom-left-radius:.25rem!important}.rounded-lg{border-radius:.3rem!important}.rounded-circle{border-radius:50%!important}.rounded-pill{border-radius:50rem!important}.rounded-0{border-radius:0!important}.clearfix::after{display:block;clear:both;content:""}.d-none{display:none!important}.d-inline{display:inline!important}.d-inline-block{display:inline-block!important}.d-block{display:block!important}.d-table{display:table!important}.d-table-row{display:table-row!important}.d-table-cell{display:table-cell!important}.d-flex{display:-ms-flexbox!important;display:flex!important}.d-inline-flex{display:-ms-inline-flexbox!important;display:inline-flex!important}@media (min-width:576px){.d-sm-none{display:none!important}.d-sm-inline{display:inline!important}.d-sm-inline-block{display:inline-block!important}.d-sm-block{display:block!important}.d-sm-table{display:table!important}.d-sm-table-row{display:table-row!important}.d-sm-table-cell{display:table-cell!important}.d-sm-flex{display:-ms-flexbox!important;display:flex!important}.d-sm-inline-flex{display:-ms-inline-flexbox!important;display:inline-flex!important}}@media (min-width:768px){.d-md-none{display:none!important}.d-md-inline{display:inline!important}.d-md-inline-block{display:inline-block!important}.d-md-block{display:block!important}.d-md-table{display:table!important}.d-md-table-row{display:table-row!important}.d-md-table-cell{display:table-cell!important}.d-md-flex{display:-ms-flexbox!important;display:flex!important}.d-md-inline-flex{display:-ms-inline-flexbox!important;display:inline-flex!important}}@media (min-width:992px){.d-lg-none{display:none!important}.d-lg-inline{display:inline!important}.d-lg-inline-block{display:inline-block!important}.d-lg-block{display:block!important}.d-lg-table{display:table!important}.d-lg-table-row{display:table-row!important}.d-lg-table-cell{display:table-cell!important}.d-lg-flex{display:-ms-flexbox!important;display:flex!important}.d-lg-inline-flex{display:-ms-inline-flexbox!important;display:inline-flex!important}}@media (min-width:1200px){.d-xl-none{display:none!important}.d-xl-inline{display:inline!important}.d-xl-inline-block{display:inline-block!important}.d-xl-block{display:block!important}.d-xl-table{display:table!important}.d-xl-table-row{display:table-row!important}.d-xl-table-cell{display:table-cell!important}.d-xl-flex{display:-ms-flexbox!important;display:flex!important}.d-xl-inline-flex{display:-ms-inline-flexbox!important;display:inline-flex!important}}@media print{.d-print-none{display:none!important}.d-print-inline{display:inline!important}.d-print-inline-block{display:inline-block!important}.d-print-block{display:block!important}.d-print-table{display:table!important}.d-print-table-row{display:table-row!important}.d-print-table-cell{display:table-cell!important}.d-print-flex{display:-ms-flexbox!important;display:flex!important}.d-print-inline-flex{display:-ms-inline-flexbox!important;display:inline-flex!important}}.embed-responsive{position:relative;display:block;width:100%;padding:0;overflow:hidden}.embed-responsive::before{display:block;content:""}.embed-responsive .embed-responsive-item,.embed-responsive embed,.embed-responsive iframe,.embed-responsive object,.embed-responsive video{position:absolute;top:0;bottom:0;left:0;width:100%;height:100%;border:0}.embed-responsive-21by9::before{padding-top:42.857143%}.embed-responsive-16by9::before{padding-top:56.25%}.embed-responsive-4by3::before{padding-top:75%}.embed-responsive-1by1::before{padding-top:100%}.flex-row{-ms-flex-direction:row!important;flex-direction:row!important}.flex-column{-ms-flex-direction:column!important;flex-direction:column!important}.flex-row-reverse{-ms-flex-direction:row-reverse!important;flex-direction:row-reverse!important}.flex-column-reverse{-ms-flex-direction:column-reverse!important;flex-direction:column-reverse!important}.flex-wrap{-ms-flex-wrap:wrap!important;flex-wrap:wrap!important}.flex-nowrap{-ms-flex-wrap:nowrap!important;flex-wrap:nowrap!important}.flex-wrap-reverse{-ms-flex-wrap:wrap-reverse!important;flex-wrap:wrap-reverse!important}.flex-fill{-ms-flex:1 1 auto!important;flex:1 1 auto!important}.flex-grow-0{-ms-flex-positive:0!important;flex-grow:0!important}.flex-grow-1{-ms-flex-positive:1!important;flex-grow:1!important}.flex-shrink-0{-ms-flex-negative:0!important;flex-shrink:0!important}.flex-shrink-1{-ms-flex-negative:1!important;flex-shrink:1!important}.justify-content-start{-ms-flex-pack:start!important;justify-content:flex-start!important}.justify-content-end{-ms-flex-pack:end!important;justify-content:flex-end!important}.justify-content-center{-ms-flex-pack:center!important;justify-content:center!important}.justify-content-between{-ms-flex-pack:justify!important;justify-content:space-between!important}.justify-content-around{-ms-flex-pack:distribute!important;justify-content:space-around!important}.align-items-start{-ms-flex-align:start!important;align-items:flex-start!important}.align-items-end{-ms-flex-align:end!important;align-items:flex-end!important}.align-items-center{-ms-flex-align:center!important;align-items:center!important}.align-items-baseline{-ms-flex-align:baseline!important;align-items:baseline!important}.align-items-stretch{-ms-flex-align:stretch!important;align-items:stretch!important}.align-content-start{-ms-flex-line-pack:start!important;align-content:flex-start!important}.align-content-end{-ms-flex-line-pack:end!important;align-content:flex-end!important}.align-content-center{-ms-flex-line-pack:center!important;align-content:center!important}.align-content-between{-ms-flex-line-pack:justify!important;align-content:space-between!important}.align-content-around{-ms-flex-line-pack:distribute!important;align-content:space-around!important}.align-content-stretch{-ms-flex-line-pack:stretch!important;align-content:stretch!important}.align-self-auto{-ms-flex-item-align:auto!important;align-self:auto!important}.align-self-start{-ms-flex-item-align:start!important;align-self:flex-start!important}.align-self-end{-ms-flex-item-align:end!important;align-self:flex-end!important}.align-self-center{-ms-flex-item-align:center!important;align-self:center!important}.align-self-baseline{-ms-flex-item-align:baseline!important;align-self:baseline!important}.align-self-stretch{-ms-flex-item-align:stretch!important;align-self:stretch!important}@media (min-width:576px){.flex-sm-row{-ms-flex-direction:row!important;flex-direction:row!important}.flex-sm-column{-ms-flex-direction:column!important;flex-direction:column!important}.flex-sm-row-reverse{-ms-flex-direction:row-reverse!important;flex-direction:row-reverse!important}.flex-sm-column-reverse{-ms-flex-direction:column-reverse!important;flex-direction:column-reverse!important}.flex-sm-wrap{-ms-flex-wrap:wrap!important;flex-wrap:wrap!important}.flex-sm-nowrap{-ms-flex-wrap:nowrap!important;flex-wrap:nowrap!important}.flex-sm-wrap-reverse{-ms-flex-wrap:wrap-reverse!important;flex-wrap:wrap-reverse!important}.flex-sm-fill{-ms-flex:1 1 auto!important;flex:1 1 auto!important}.flex-sm-grow-0{-ms-flex-positive:0!important;flex-grow:0!important}.flex-sm-grow-1{-ms-flex-positive:1!important;flex-grow:1!important}.flex-sm-shrink-0{-ms-flex-negative:0!important;flex-shrink:0!important}.flex-sm-shrink-1{-ms-flex-negative:1!important;flex-shrink:1!important}.justify-content-sm-start{-ms-flex-pack:start!important;justify-content:flex-start!important}.justify-content-sm-end{-ms-flex-pack:end!important;justify-content:flex-end!important}.justify-content-sm-center{-ms-flex-pack:center!important;justify-content:center!important}.justify-content-sm-between{-ms-flex-pack:justify!important;justify-content:space-between!important}.justify-content-sm-around{-ms-flex-pack:distribute!important;justify-content:space-around!important}.align-items-sm-start{-ms-flex-align:start!important;align-items:flex-start!important}.align-items-sm-end{-ms-flex-align:end!important;align-items:flex-end!important}.align-items-sm-center{-ms-flex-align:center!important;align-items:center!important}.align-items-sm-baseline{-ms-flex-align:baseline!important;align-items:baseline!important}.align-items-sm-stretch{-ms-flex-align:stretch!important;align-items:stretch!important}.align-content-sm-start{-ms-flex-line-pack:start!important;align-content:flex-start!important}.align-content-sm-end{-ms-flex-line-pack:end!important;align-content:flex-end!important}.align-content-sm-center{-ms-flex-line-pack:center!important;align-content:center!important}.align-content-sm-between{-ms-flex-line-pack:justify!important;align-content:space-between!important}.align-content-sm-around{-ms-flex-line-pack:distribute!important;align-content:space-around!important}.align-content-sm-stretch{-ms-flex-line-pack:stretch!important;align-content:stretch!important}.align-self-sm-auto{-ms-flex-item-align:auto!important;align-self:auto!important}.align-self-sm-start{-ms-flex-item-align:start!important;align-self:flex-start!important}.align-self-sm-end{-ms-flex-item-align:end!important;align-self:flex-end!important}.align-self-sm-center{-ms-flex-item-align:center!important;align-self:center!important}.align-self-sm-baseline{-ms-flex-item-align:baseline!important;align-self:baseline!important}.align-self-sm-stretch{-ms-flex-item-align:stretch!important;align-self:stretch!important}}@media (min-width:768px){.flex-md-row{-ms-flex-direction:row!important;flex-direction:row!important}.flex-md-column{-ms-flex-direction:column!important;flex-direction:column!important}.flex-md-row-reverse{-ms-flex-direction:row-reverse!important;flex-direction:row-reverse!important}.flex-md-column-reverse{-ms-flex-direction:column-reverse!important;flex-direction:column-reverse!important}.flex-md-wrap{-ms-flex-wrap:wrap!important;flex-wrap:wrap!important}.flex-md-nowrap{-ms-flex-wrap:nowrap!important;flex-wrap:nowrap!important}.flex-md-wrap-reverse{-ms-flex-wrap:wrap-reverse!important;flex-wrap:wrap-reverse!important}.flex-md-fill{-ms-flex:1 1 auto!important;flex:1 1 auto!important}.flex-md-grow-0{-ms-flex-positive:0!important;flex-grow:0!important}.flex-md-grow-1{-ms-flex-positive:1!important;flex-grow:1!important}.flex-md-shrink-0{-ms-flex-negative:0!important;flex-shrink:0!important}.flex-md-shrink-1{-ms-flex-negative:1!important;flex-shrink:1!important}.justify-content-md-start{-ms-flex-pack:start!important;justify-content:flex-start!important}.justify-content-md-end{-ms-flex-pack:end!important;justify-content:flex-end!important}.justify-content-md-center{-ms-flex-pack:center!important;justify-content:center!important}.justify-content-md-between{-ms-flex-pack:justify!important;justify-content:space-between!important}.justify-content-md-around{-ms-flex-pack:distribute!important;justify-content:space-around!important}.align-items-md-start{-ms-flex-align:start!important;align-items:flex-start!important}.align-items-md-end{-ms-flex-align:end!important;align-items:flex-end!important}.align-items-md-center{-ms-flex-align:center!important;align-items:center!important}.align-items-md-baseline{-ms-flex-align:baseline!important;align-items:baseline!important}.align-items-md-stretch{-ms-flex-align:stretch!important;align-items:stretch!important}.align-content-md-start{-ms-flex-line-pack:start!important;align-content:flex-start!important}.align-content-md-end{-ms-flex-line-pack:end!important;align-content:flex-end!important}.align-content-md-center{-ms-flex-line-pack:center!important;align-content:center!important}.align-content-md-between{-ms-flex-line-pack:justify!important;align-content:space-between!important}.align-content-md-around{-ms-flex-line-pack:distribute!important;align-content:space-around!important}.align-content-md-stretch{-ms-flex-line-pack:stretch!important;align-content:stretch!important}.align-self-md-auto{-ms-flex-item-align:auto!important;align-self:auto!important}.align-self-md-start{-ms-flex-item-align:start!important;align-self:flex-start!important}.align-self-md-end{-ms-flex-item-align:end!important;align-self:flex-end!important}.align-self-md-center{-ms-flex-item-align:center!important;align-self:center!important}.align-self-md-baseline{-ms-flex-item-align:baseline!important;align-self:baseline!important}.align-self-md-stretch{-ms-flex-item-align:stretch!important;align-self:stretch!important}}@media (min-width:992px){.flex-lg-row{-ms-flex-direction:row!important;flex-direction:row!important}.flex-lg-column{-ms-flex-direction:column!important;flex-direction:column!important}.flex-lg-row-reverse{-ms-flex-direction:row-reverse!important;flex-direction:row-reverse!important}.flex-lg-column-reverse{-ms-flex-direction:column-reverse!important;flex-direction:column-reverse!important}.flex-lg-wrap{-ms-flex-wrap:wrap!important;flex-wrap:wrap!important}.flex-lg-nowrap{-ms-flex-wrap:nowrap!important;flex-wrap:nowrap!important}.flex-lg-wrap-reverse{-ms-flex-wrap:wrap-reverse!important;flex-wrap:wrap-reverse!important}.flex-lg-fill{-ms-flex:1 1 auto!important;flex:1 1 auto!important}.flex-lg-grow-0{-ms-flex-positive:0!important;flex-grow:0!important}.flex-lg-grow-1{-ms-flex-positive:1!important;flex-grow:1!important}.flex-lg-shrink-0{-ms-flex-negative:0!important;flex-shrink:0!important}.flex-lg-shrink-1{-ms-flex-negative:1!important;flex-shrink:1!important}.justify-content-lg-start{-ms-flex-pack:start!important;justify-content:flex-start!important}.justify-content-lg-end{-ms-flex-pack:end!important;justify-content:flex-end!important}.justify-content-lg-center{-ms-flex-pack:center!important;justify-content:center!important}.justify-content-lg-between{-ms-flex-pack:justify!important;justify-content:space-between!important}.justify-content-lg-around{-ms-flex-pack:distribute!important;justify-content:space-around!important}.align-items-lg-start{-ms-flex-align:start!important;align-items:flex-start!important}.align-items-lg-end{-ms-flex-align:end!important;align-items:flex-end!important}.align-items-lg-center{-ms-flex-align:center!important;align-items:center!important}.align-items-lg-baseline{-ms-flex-align:baseline!important;align-items:baseline!important}.align-items-lg-stretch{-ms-flex-align:stretch!important;align-items:stretch!important}.align-content-lg-start{-ms-flex-line-pack:start!important;align-content:flex-start!important}.align-content-lg-end{-ms-flex-line-pack:end!important;align-content:flex-end!important}.align-content-lg-center{-ms-flex-line-pack:center!important;align-content:center!important}.align-content-lg-between{-ms-flex-line-pack:justify!important;align-content:space-between!important}.align-content-lg-around{-ms-flex-line-pack:distribute!important;align-content:space-around!important}.align-content-lg-stretch{-ms-flex-line-pack:stretch!important;align-content:stretch!important}.align-self-lg-auto{-ms-flex-item-align:auto!important;align-self:auto!important}.align-self-lg-start{-ms-flex-item-align:start!important;align-self:flex-start!important}.align-self-lg-end{-ms-flex-item-align:end!important;align-self:flex-end!important}.align-self-lg-center{-ms-flex-item-align:center!important;align-self:center!important}.align-self-lg-baseline{-ms-flex-item-align:baseline!important;align-self:baseline!important}.align-self-lg-stretch{-ms-flex-item-align:stretch!important;align-self:stretch!important}}@media (min-width:1200px){.flex-xl-row{-ms-flex-direction:row!important;flex-direction:row!important}.flex-xl-column{-ms-flex-direction:column!important;flex-direction:column!important}.flex-xl-row-reverse{-ms-flex-direction:row-reverse!important;flex-direction:row-reverse!important}.flex-xl-column-reverse{-ms-flex-direction:column-reverse!important;flex-direction:column-reverse!important}.flex-xl-wrap{-ms-flex-wrap:wrap!important;flex-wrap:wrap!important}.flex-xl-nowrap{-ms-flex-wrap:nowrap!important;flex-wrap:nowrap!important}.flex-xl-wrap-reverse{-ms-flex-wrap:wrap-reverse!important;flex-wrap:wrap-reverse!important}.flex-xl-fill{-ms-flex:1 1 auto!important;flex:1 1 auto!important}.flex-xl-grow-0{-ms-flex-positive:0!important;flex-grow:0!important}.flex-xl-grow-1{-ms-flex-positive:1!important;flex-grow:1!important}.flex-xl-shrink-0{-ms-flex-negative:0!important;flex-shrink:0!important}.flex-xl-shrink-1{-ms-flex-negative:1!important;flex-shrink:1!important}.justify-content-xl-start{-ms-flex-pack:start!important;justify-content:flex-start!important}.justify-content-xl-end{-ms-flex-pack:end!important;justify-content:flex-end!important}.justify-content-xl-center{-ms-flex-pack:center!important;justify-content:center!important}.justify-content-xl-between{-ms-flex-pack:justify!important;justify-content:space-between!important}.justify-content-xl-around{-ms-flex-pack:distribute!important;justify-content:space-around!important}.align-items-xl-start{-ms-flex-align:start!important;align-items:flex-start!important}.align-items-xl-end{-ms-flex-align:end!important;align-items:flex-end!important}.align-items-xl-center{-ms-flex-align:center!important;align-items:center!important}.align-items-xl-baseline{-ms-flex-align:baseline!important;align-items:baseline!important}.align-items-xl-stretch{-ms-flex-align:stretch!important;align-items:stretch!important}.align-content-xl-start{-ms-flex-line-pack:start!important;align-content:flex-start!important}.align-content-xl-end{-ms-flex-line-pack:end!important;align-content:flex-end!important}.align-content-xl-center{-ms-flex-line-pack:center!important;align-content:center!important}.align-content-xl-between{-ms-flex-line-pack:justify!important;align-content:space-between!important}.align-content-xl-around{-ms-flex-line-pack:distribute!important;align-content:space-around!important}.align-content-xl-stretch{-ms-flex-line-pack:stretch!important;align-content:stretch!important}.align-self-xl-auto{-ms-flex-item-align:auto!important;align-self:auto!important}.align-self-xl-start{-ms-flex-item-align:start!important;align-self:flex-start!important}.align-self-xl-end{-ms-flex-item-align:end!important;align-self:flex-end!important}.align-self-xl-center{-ms-flex-item-align:center!important;align-self:center!important}.align-self-xl-baseline{-ms-flex-item-align:baseline!important;align-self:baseline!important}.align-self-xl-stretch{-ms-flex-item-align:stretch!important;align-self:stretch!important}}.float-left{float:left!important}.float-right{float:right!important}.float-none{float:none!important}@media (min-width:576px){.float-sm-left{float:left!important}.float-sm-right{float:right!important}.float-sm-none{float:none!important}}@media (min-width:768px){.float-md-left{float:left!important}.float-md-right{float:right!important}.float-md-none{float:none!important}}@media (min-width:992px){.float-lg-left{float:left!important}.float-lg-right{float:right!important}.float-lg-none{float:none!important}}@media (min-width:1200px){.float-xl-left{float:left!important}.float-xl-right{float:right!important}.float-xl-none{float:none!important}}.user-select-all{-webkit-user-select:all!important;-moz-user-select:all!important;user-select:all!important}.user-select-auto{-webkit-user-select:auto!important;-moz-user-select:auto!important;-ms-user-select:auto!important;user-select:auto!important}.user-select-none{-webkit-user-select:none!important;-moz-user-select:none!important;-ms-user-select:none!important;user-select:none!important}.overflow-auto{overflow:auto!important}.overflow-hidden{overflow:hidden!important}.position-static{position:static!important}.position-relative{position:relative!important}.position-absolute{position:absolute!important}.position-fixed{position:fixed!important}.position-sticky{position:-webkit-sticky!important;position:sticky!important}.fixed-top{position:fixed;top:0;right:0;left:0;z-index:1030}.fixed-bottom{position:fixed;right:0;bottom:0;left:0;z-index:1030}@supports ((position:-webkit-sticky) or (position:sticky)){.sticky-top{position:-webkit-sticky;position:sticky;top:0;z-index:1020}}.sr-only{position:absolute;width:1px;height:1px;padding:0;margin:-1px;overflow:hidden;clip:rect(0,0,0,0);white-space:nowrap;border:0}.sr-only-focusable:active,.sr-only-focusable:focus{position:static;width:auto;height:auto;overflow:visible;clip:auto;white-space:normal}.shadow-sm{box-shadow:0 .125rem .25rem rgba(0,0,0,.075)!important}.shadow{box-shadow:0 .5rem 1rem rgba(0,0,0,.15)!important}.shadow-lg{box-shadow:0 1rem 3rem rgba(0,0,0,.175)!important}.shadow-none{box-shadow:none!important}.w-25{width:25%!important}.w-50{width:50%!important}.w-75{width:75%!important}.w-100{width:100%!important}.w-auto{width:auto!important}.h-25{height:25%!important}.h-50{height:50%!important}.h-75{height:75%!important}.h-100{height:100%!important}.h-auto{height:auto!important}.mw-100{max-width:100%!important}.mh-100{max-height:100%!important}.min-vw-100{min-width:100vw!important}.min-vh-100{min-height:100vh!important}.vw-100{width:100vw!important}.vh-100{height:100vh!important}.m-0{margin:0!important}.mt-0,.my-0{margin-top:0!important}.mr-0,.mx-0{margin-right:0!important}.mb-0,.my-0{margin-bottom:0!important}.ml-0,.mx-0{margin-left:0!important}.m-1{margin:.25rem!important}.mt-1,.my-1{margin-top:.25rem!important}.mr-1,.mx-1{margin-right:.25rem!important}.mb-1,.my-1{margin-bottom:.25rem!important}.ml-1,.mx-1{margin-left:.25rem!important}.m-2{margin:.5rem!important}.mt-2,.my-2{margin-top:.5rem!important}.mr-2,.mx-2{margin-right:.5rem!important}.mb-2,.my-2{margin-bottom:.5rem!important}.ml-2,.mx-2{margin-left:.5rem!important}.m-3{margin:1rem!important}.mt-3,.my-3{margin-top:1rem!important}.mr-3,.mx-3{margin-right:1rem!important}.mb-3,.my-3{margin-bottom:1rem!important}.ml-3,.mx-3{margin-left:1rem!important}.m-4{margin:1.5rem!important}.mt-4,.my-4{margin-top:1.5rem!important}.mr-4,.mx-4{margin-right:1.5rem!important}.mb-4,.my-4{margin-bottom:1.5rem!important}.ml-4,.mx-4{margin-left:1.5rem!important}.m-5{margin:3rem!important}.mt-5,.my-5{margin-top:3rem!important}.mr-5,.mx-5{margin-right:3rem!important}.mb-5,.my-5{margin-bottom:3rem!important}.ml-5,.mx-5{margin-left:3rem!important}.p-0{padding:0!important}.pt-0,.py-0{padding-top:0!important}.pr-0,.px-0{padding-right:0!important}.pb-0,.py-0{padding-bottom:0!important}.pl-0,.px-0{padding-left:0!important}.p-1{padding:.25rem!important}.pt-1,.py-1{padding-top:.25rem!important}.pr-1,.px-1{padding-right:.25rem!important}.pb-1,.py-1{padding-bottom:.25rem!important}.pl-1,.px-1{padding-left:.25rem!important}.p-2{padding:.5rem!important}.pt-2,.py-2{padding-top:.5rem!important}.pr-2,.px-2{padding-right:.5rem!important}.pb-2,.py-2{padding-bottom:.5rem!important}.pl-2,.px-2{padding-left:.5rem!important}.p-3{padding:1rem!important}.pt-3,.py-3{padding-top:1rem!important}.pr-3,.px-3{padding-right:1rem!important}.pb-3,.py-3{padding-bottom:1rem!important}.pl-3,.px-3{padding-left:1rem!important}.p-4{padding:1.5rem!important}.pt-4,.py-4{padding-top:1.5rem!important}.pr-4,.px-4{padding-right:1.5rem!important}.pb-4,.py-4{padding-bottom:1.5rem!important}.pl-4,.px-4{padding-left:1.5rem!important}.p-5{padding:3rem!important}.pt-5,.py-5{padding-top:3rem!important}.pr-5,.px-5{padding-right:3rem!important}.pb-5,.py-5{padding-bottom:3rem!important}.pl-5,.px-5{padding-left:3rem!important}.m-n1{margin:-.25rem!important}.mt-n1,.my-n1{margin-top:-.25rem!important}.mr-n1,.mx-n1{margin-right:-.25rem!important}.mb-n1,.my-n1{margin-bottom:-.25rem!important}.ml-n1,.mx-n1{margin-left:-.25rem!important}.m-n2{margin:-.5rem!important}.mt-n2,.my-n2{margin-top:-.5rem!important}.mr-n2,.mx-n2{margin-right:-.5rem!important}.mb-n2,.my-n2{margin-bottom:-.5rem!important}.ml-n2,.mx-n2{margin-left:-.5rem!important}.m-n3{margin:-1rem!important}.mt-n3,.my-n3{margin-top:-1rem!important}.mr-n3,.mx-n3{margin-right:-1rem!important}.mb-n3,.my-n3{margin-bottom:-1rem!important}.ml-n3,.mx-n3{margin-left:-1rem!important}.m-n4{margin:-1.5rem!important}.mt-n4,.my-n4{margin-top:-1.5rem!important}.mr-n4,.mx-n4{margin-right:-1.5rem!important}.mb-n4,.my-n4{margin-bottom:-1.5rem!important}.ml-n4,.mx-n4{margin-left:-1.5rem!important}.m-n5{margin:-3rem!important}.mt-n5,.my-n5{margin-top:-3rem!important}.mr-n5,.mx-n5{margin-right:-3rem!important}.mb-n5,.my-n5{margin-bottom:-3rem!important}.ml-n5,.mx-n5{margin-left:-3rem!important}.m-auto{margin:auto!important}.mt-auto,.my-auto{margin-top:auto!important}.mr-auto,.mx-auto{margin-right:auto!important}.mb-auto,.my-auto{margin-bottom:auto!important}.ml-auto,.mx-auto{margin-left:auto!important}@media (min-width:576px){.m-sm-0{margin:0!important}.mt-sm-0,.my-sm-0{margin-top:0!important}.mr-sm-0,.mx-sm-0{margin-right:0!important}.mb-sm-0,.my-sm-0{margin-bottom:0!important}.ml-sm-0,.mx-sm-0{margin-left:0!important}.m-sm-1{margin:.25rem!important}.mt-sm-1,.my-sm-1{margin-top:.25rem!important}.mr-sm-1,.mx-sm-1{margin-right:.25rem!important}.mb-sm-1,.my-sm-1{margin-bottom:.25rem!important}.ml-sm-1,.mx-sm-1{margin-left:.25rem!important}.m-sm-2{margin:.5rem!important}.mt-sm-2,.my-sm-2{margin-top:.5rem!important}.mr-sm-2,.mx-sm-2{margin-right:.5rem!important}.mb-sm-2,.my-sm-2{margin-bottom:.5rem!important}.ml-sm-2,.mx-sm-2{margin-left:.5rem!important}.m-sm-3{margin:1rem!important}.mt-sm-3,.my-sm-3{margin-top:1rem!important}.mr-sm-3,.mx-sm-3{margin-right:1rem!important}.mb-sm-3,.my-sm-3{margin-bottom:1rem!important}.ml-sm-3,.mx-sm-3{margin-left:1rem!important}.m-sm-4{margin:1.5rem!important}.mt-sm-4,.my-sm-4{margin-top:1.5rem!important}.mr-sm-4,.mx-sm-4{margin-right:1.5rem!important}.mb-sm-4,.my-sm-4{margin-bottom:1.5rem!important}.ml-sm-4,.mx-sm-4{margin-left:1.5rem!important}.m-sm-5{margin:3rem!important}.mt-sm-5,.my-sm-5{margin-top:3rem!important}.mr-sm-5,.mx-sm-5{margin-right:3rem!important}.mb-sm-5,.my-sm-5{margin-bottom:3rem!important}.ml-sm-5,.mx-sm-5{margin-left:3rem!important}.p-sm-0{padding:0!important}.pt-sm-0,.py-sm-0{padding-top:0!important}.pr-sm-0,.px-sm-0{padding-right:0!important}.pb-sm-0,.py-sm-0{padding-bottom:0!important}.pl-sm-0,.px-sm-0{padding-left:0!important}.p-sm-1{padding:.25rem!important}.pt-sm-1,.py-sm-1{padding-top:.25rem!important}.pr-sm-1,.px-sm-1{padding-right:.25rem!important}.pb-sm-1,.py-sm-1{padding-bottom:.25rem!important}.pl-sm-1,.px-sm-1{padding-left:.25rem!important}.p-sm-2{padding:.5rem!important}.pt-sm-2,.py-sm-2{padding-top:.5rem!important}.pr-sm-2,.px-sm-2{padding-right:.5rem!important}.pb-sm-2,.py-sm-2{padding-bottom:.5rem!important}.pl-sm-2,.px-sm-2{padding-left:.5rem!important}.p-sm-3{padding:1rem!important}.pt-sm-3,.py-sm-3{padding-top:1rem!important}.pr-sm-3,.px-sm-3{padding-right:1rem!important}.pb-sm-3,.py-sm-3{padding-bottom:1rem!important}.pl-sm-3,.px-sm-3{padding-left:1rem!important}.p-sm-4{padding:1.5rem!important}.pt-sm-4,.py-sm-4{padding-top:1.5rem!important}.pr-sm-4,.px-sm-4{padding-right:1.5rem!important}.pb-sm-4,.py-sm-4{padding-bottom:1.5rem!important}.pl-sm-4,.px-sm-4{padding-left:1.5rem!important}.p-sm-5{padding:3rem!important}.pt-sm-5,.py-sm-5{padding-top:3rem!important}.pr-sm-5,.px-sm-5{padding-right:3rem!important}.pb-sm-5,.py-sm-5{padding-bottom:3rem!important}.pl-sm-5,.px-sm-5{padding-left:3rem!important}.m-sm-n1{margin:-.25rem!important}.mt-sm-n1,.my-sm-n1{margin-top:-.25rem!important}.mr-sm-n1,.mx-sm-n1{margin-right:-.25rem!important}.mb-sm-n1,.my-sm-n1{margin-bottom:-.25rem!important}.ml-sm-n1,.mx-sm-n1{margin-left:-.25rem!important}.m-sm-n2{margin:-.5rem!important}.mt-sm-n2,.my-sm-n2{margin-top:-.5rem!important}.mr-sm-n2,.mx-sm-n2{margin-right:-.5rem!important}.mb-sm-n2,.my-sm-n2{margin-bottom:-.5rem!important}.ml-sm-n2,.mx-sm-n2{margin-left:-.5rem!important}.m-sm-n3{margin:-1rem!important}.mt-sm-n3,.my-sm-n3{margin-top:-1rem!important}.mr-sm-n3,.mx-sm-n3{margin-right:-1rem!important}.mb-sm-n3,.my-sm-n3{margin-bottom:-1rem!important}.ml-sm-n3,.mx-sm-n3{margin-left:-1rem!important}.m-sm-n4{margin:-1.5rem!important}.mt-sm-n4,.my-sm-n4{margin-top:-1.5rem!important}.mr-sm-n4,.mx-sm-n4{margin-right:-1.5rem!important}.mb-sm-n4,.my-sm-n4{margin-bottom:-1.5rem!important}.ml-sm-n4,.mx-sm-n4{margin-left:-1.5rem!important}.m-sm-n5{margin:-3rem!important}.mt-sm-n5,.my-sm-n5{margin-top:-3rem!important}.mr-sm-n5,.mx-sm-n5{margin-right:-3rem!important}.mb-sm-n5,.my-sm-n5{margin-bottom:-3rem!important}.ml-sm-n5,.mx-sm-n5{margin-left:-3rem!important}.m-sm-auto{margin:auto!important}.mt-sm-auto,.my-sm-auto{margin-top:auto!important}.mr-sm-auto,.mx-sm-auto{margin-right:auto!important}.mb-sm-auto,.my-sm-auto{margin-bottom:auto!important}.ml-sm-auto,.mx-sm-auto{margin-left:auto!important}}@media (min-width:768px){.m-md-0{margin:0!important}.mt-md-0,.my-md-0{margin-top:0!important}.mr-md-0,.mx-md-0{margin-right:0!important}.mb-md-0,.my-md-0{margin-bottom:0!important}.ml-md-0,.mx-md-0{margin-left:0!important}.m-md-1{margin:.25rem!important}.mt-md-1,.my-md-1{margin-top:.25rem!important}.mr-md-1,.mx-md-1{margin-right:.25rem!important}.mb-md-1,.my-md-1{margin-bottom:.25rem!important}.ml-md-1,.mx-md-1{margin-left:.25rem!important}.m-md-2{margin:.5rem!important}.mt-md-2,.my-md-2{margin-top:.5rem!important}.mr-md-2,.mx-md-2{margin-right:.5rem!important}.mb-md-2,.my-md-2{margin-bottom:.5rem!important}.ml-md-2,.mx-md-2{margin-left:.5rem!important}.m-md-3{margin:1rem!important}.mt-md-3,.my-md-3{margin-top:1rem!important}.mr-md-3,.mx-md-3{margin-right:1rem!important}.mb-md-3,.my-md-3{margin-bottom:1rem!important}.ml-md-3,.mx-md-3{margin-left:1rem!important}.m-md-4{margin:1.5rem!important}.mt-md-4,.my-md-4{margin-top:1.5rem!important}.mr-md-4,.mx-md-4{margin-right:1.5rem!important}.mb-md-4,.my-md-4{margin-bottom:1.5rem!important}.ml-md-4,.mx-md-4{margin-left:1.5rem!important}.m-md-5{margin:3rem!important}.mt-md-5,.my-md-5{margin-top:3rem!important}.mr-md-5,.mx-md-5{margin-right:3rem!important}.mb-md-5,.my-md-5{margin-bottom:3rem!important}.ml-md-5,.mx-md-5{margin-left:3rem!important}.p-md-0{padding:0!important}.pt-md-0,.py-md-0{padding-top:0!important}.pr-md-0,.px-md-0{padding-right:0!important}.pb-md-0,.py-md-0{padding-bottom:0!important}.pl-md-0,.px-md-0{padding-left:0!important}.p-md-1{padding:.25rem!important}.pt-md-1,.py-md-1{padding-top:.25rem!important}.pr-md-1,.px-md-1{padding-right:.25rem!important}.pb-md-1,.py-md-1{padding-bottom:.25rem!important}.pl-md-1,.px-md-1{padding-left:.25rem!important}.p-md-2{padding:.5rem!important}.pt-md-2,.py-md-2{padding-top:.5rem!important}.pr-md-2,.px-md-2{padding-right:.5rem!important}.pb-md-2,.py-md-2{padding-bottom:.5rem!important}.pl-md-2,.px-md-2{padding-left:.5rem!important}.p-md-3{padding:1rem!important}.pt-md-3,.py-md-3{padding-top:1rem!important}.pr-md-3,.px-md-3{padding-right:1rem!important}.pb-md-3,.py-md-3{padding-bottom:1rem!important}.pl-md-3,.px-md-3{padding-left:1rem!important}.p-md-4{padding:1.5rem!important}.pt-md-4,.py-md-4{padding-top:1.5rem!important}.pr-md-4,.px-md-4{padding-right:1.5rem!important}.pb-md-4,.py-md-4{padding-bottom:1.5rem!important}.pl-md-4,.px-md-4{padding-left:1.5rem!important}.p-md-5{padding:3rem!important}.pt-md-5,.py-md-5{padding-top:3rem!important}.pr-md-5,.px-md-5{padding-right:3rem!important}.pb-md-5,.py-md-5{padding-bottom:3rem!important}.pl-md-5,.px-md-5{padding-left:3rem!important}.m-md-n1{margin:-.25rem!important}.mt-md-n1,.my-md-n1{margin-top:-.25rem!important}.mr-md-n1,.mx-md-n1{margin-right:-.25rem!important}.mb-md-n1,.my-md-n1{margin-bottom:-.25rem!important}.ml-md-n1,.mx-md-n1{margin-left:-.25rem!important}.m-md-n2{margin:-.5rem!important}.mt-md-n2,.my-md-n2{margin-top:-.5rem!important}.mr-md-n2,.mx-md-n2{margin-right:-.5rem!important}.mb-md-n2,.my-md-n2{margin-bottom:-.5rem!important}.ml-md-n2,.mx-md-n2{margin-left:-.5rem!important}.m-md-n3{margin:-1rem!important}.mt-md-n3,.my-md-n3{margin-top:-1rem!important}.mr-md-n3,.mx-md-n3{margin-right:-1rem!important}.mb-md-n3,.my-md-n3{margin-bottom:-1rem!important}.ml-md-n3,.mx-md-n3{margin-left:-1rem!important}.m-md-n4{margin:-1.5rem!important}.mt-md-n4,.my-md-n4{margin-top:-1.5rem!important}.mr-md-n4,.mx-md-n4{margin-right:-1.5rem!important}.mb-md-n4,.my-md-n4{margin-bottom:-1.5rem!important}.ml-md-n4,.mx-md-n4{margin-left:-1.5rem!important}.m-md-n5{margin:-3rem!important}.mt-md-n5,.my-md-n5{margin-top:-3rem!important}.mr-md-n5,.mx-md-n5{margin-right:-3rem!important}.mb-md-n5,.my-md-n5{margin-bottom:-3rem!important}.ml-md-n5,.mx-md-n5{margin-left:-3rem!important}.m-md-auto{margin:auto!important}.mt-md-auto,.my-md-auto{margin-top:auto!important}.mr-md-auto,.mx-md-auto{margin-right:auto!important}.mb-md-auto,.my-md-auto{margin-bottom:auto!important}.ml-md-auto,.mx-md-auto{margin-left:auto!important}}@media (min-width:992px){.m-lg-0{margin:0!important}.mt-lg-0,.my-lg-0{margin-top:0!important}.mr-lg-0,.mx-lg-0{margin-right:0!important}.mb-lg-0,.my-lg-0{margin-bottom:0!important}.ml-lg-0,.mx-lg-0{margin-left:0!important}.m-lg-1{margin:.25rem!important}.mt-lg-1,.my-lg-1{margin-top:.25rem!important}.mr-lg-1,.mx-lg-1{margin-right:.25rem!important}.mb-lg-1,.my-lg-1{margin-bottom:.25rem!important}.ml-lg-1,.mx-lg-1{margin-left:.25rem!important}.m-lg-2{margin:.5rem!important}.mt-lg-2,.my-lg-2{margin-top:.5rem!important}.mr-lg-2,.mx-lg-2{margin-right:.5rem!important}.mb-lg-2,.my-lg-2{margin-bottom:.5rem!important}.ml-lg-2,.mx-lg-2{margin-left:.5rem!important}.m-lg-3{margin:1rem!important}.mt-lg-3,.my-lg-3{margin-top:1rem!important}.mr-lg-3,.mx-lg-3{margin-right:1rem!important}.mb-lg-3,.my-lg-3{margin-bottom:1rem!important}.ml-lg-3,.mx-lg-3{margin-left:1rem!important}.m-lg-4{margin:1.5rem!important}.mt-lg-4,.my-lg-4{margin-top:1.5rem!important}.mr-lg-4,.mx-lg-4{margin-right:1.5rem!important}.mb-lg-4,.my-lg-4{margin-bottom:1.5rem!important}.ml-lg-4,.mx-lg-4{margin-left:1.5rem!important}.m-lg-5{margin:3rem!important}.mt-lg-5,.my-lg-5{margin-top:3rem!important}.mr-lg-5,.mx-lg-5{margin-right:3rem!important}.mb-lg-5,.my-lg-5{margin-bottom:3rem!important}.ml-lg-5,.mx-lg-5{margin-left:3rem!important}.p-lg-0{padding:0!important}.pt-lg-0,.py-lg-0{padding-top:0!important}.pr-lg-0,.px-lg-0{padding-right:0!important}.pb-lg-0,.py-lg-0{padding-bottom:0!important}.pl-lg-0,.px-lg-0{padding-left:0!important}.p-lg-1{padding:.25rem!important}.pt-lg-1,.py-lg-1{padding-top:.25rem!important}.pr-lg-1,.px-lg-1{padding-right:.25rem!important}.pb-lg-1,.py-lg-1{padding-bottom:.25rem!important}.pl-lg-1,.px-lg-1{padding-left:.25rem!important}.p-lg-2{padding:.5rem!important}.pt-lg-2,.py-lg-2{padding-top:.5rem!important}.pr-lg-2,.px-lg-2{padding-right:.5rem!important}.pb-lg-2,.py-lg-2{padding-bottom:.5rem!important}.pl-lg-2,.px-lg-2{padding-left:.5rem!important}.p-lg-3{padding:1rem!important}.pt-lg-3,.py-lg-3{padding-top:1rem!important}.pr-lg-3,.px-lg-3{padding-right:1rem!important}.pb-lg-3,.py-lg-3{padding-bottom:1rem!important}.pl-lg-3,.px-lg-3{padding-left:1rem!important}.p-lg-4{padding:1.5rem!important}.pt-lg-4,.py-lg-4{padding-top:1.5rem!important}.pr-lg-4,.px-lg-4{padding-right:1.5rem!important}.pb-lg-4,.py-lg-4{padding-bottom:1.5rem!important}.pl-lg-4,.px-lg-4{padding-left:1.5rem!important}.p-lg-5{padding:3rem!important}.pt-lg-5,.py-lg-5{padding-top:3rem!important}.pr-lg-5,.px-lg-5{padding-right:3rem!important}.pb-lg-5,.py-lg-5{padding-bottom:3rem!important}.pl-lg-5,.px-lg-5{padding-left:3rem!important}.m-lg-n1{margin:-.25rem!important}.mt-lg-n1,.my-lg-n1{margin-top:-.25rem!important}.mr-lg-n1,.mx-lg-n1{margin-right:-.25rem!important}.mb-lg-n1,.my-lg-n1{margin-bottom:-.25rem!important}.ml-lg-n1,.mx-lg-n1{margin-left:-.25rem!important}.m-lg-n2{margin:-.5rem!important}.mt-lg-n2,.my-lg-n2{margin-top:-.5rem!important}.mr-lg-n2,.mx-lg-n2{margin-right:-.5rem!important}.mb-lg-n2,.my-lg-n2{margin-bottom:-.5rem!important}.ml-lg-n2,.mx-lg-n2{margin-left:-.5rem!important}.m-lg-n3{margin:-1rem!important}.mt-lg-n3,.my-lg-n3{margin-top:-1rem!important}.mr-lg-n3,.mx-lg-n3{margin-right:-1rem!important}.mb-lg-n3,.my-lg-n3{margin-bottom:-1rem!important}.ml-lg-n3,.mx-lg-n3{margin-left:-1rem!important}.m-lg-n4{margin:-1.5rem!important}.mt-lg-n4,.my-lg-n4{margin-top:-1.5rem!important}.mr-lg-n4,.mx-lg-n4{margin-right:-1.5rem!important}.mb-lg-n4,.my-lg-n4{margin-bottom:-1.5rem!important}.ml-lg-n4,.mx-lg-n4{margin-left:-1.5rem!important}.m-lg-n5{margin:-3rem!important}.mt-lg-n5,.my-lg-n5{margin-top:-3rem!important}.mr-lg-n5,.mx-lg-n5{margin-right:-3rem!important}.mb-lg-n5,.my-lg-n5{margin-bottom:-3rem!important}.ml-lg-n5,.mx-lg-n5{margin-left:-3rem!important}.m-lg-auto{margin:auto!important}.mt-lg-auto,.my-lg-auto{margin-top:auto!important}.mr-lg-auto,.mx-lg-auto{margin-right:auto!important}.mb-lg-auto,.my-lg-auto{margin-bottom:auto!important}.ml-lg-auto,.mx-lg-auto{margin-left:auto!important}}@media (min-width:1200px){.m-xl-0{margin:0!important}.mt-xl-0,.my-xl-0{margin-top:0!important}.mr-xl-0,.mx-xl-0{margin-right:0!important}.mb-xl-0,.my-xl-0{margin-bottom:0!important}.ml-xl-0,.mx-xl-0{margin-left:0!important}.m-xl-1{margin:.25rem!important}.mt-xl-1,.my-xl-1{margin-top:.25rem!important}.mr-xl-1,.mx-xl-1{margin-right:.25rem!important}.mb-xl-1,.my-xl-1{margin-bottom:.25rem!important}.ml-xl-1,.mx-xl-1{margin-left:.25rem!important}.m-xl-2{margin:.5rem!important}.mt-xl-2,.my-xl-2{margin-top:.5rem!important}.mr-xl-2,.mx-xl-2{margin-right:.5rem!important}.mb-xl-2,.my-xl-2{margin-bottom:.5rem!important}.ml-xl-2,.mx-xl-2{margin-left:.5rem!important}.m-xl-3{margin:1rem!important}.mt-xl-3,.my-xl-3{margin-top:1rem!important}.mr-xl-3,.mx-xl-3{margin-right:1rem!important}.mb-xl-3,.my-xl-3{margin-bottom:1rem!important}.ml-xl-3,.mx-xl-3{margin-left:1rem!important}.m-xl-4{margin:1.5rem!important}.mt-xl-4,.my-xl-4{margin-top:1.5rem!important}.mr-xl-4,.mx-xl-4{margin-right:1.5rem!important}.mb-xl-4,.my-xl-4{margin-bottom:1.5rem!important}.ml-xl-4,.mx-xl-4{margin-left:1.5rem!important}.m-xl-5{margin:3rem!important}.mt-xl-5,.my-xl-5{margin-top:3rem!important}.mr-xl-5,.mx-xl-5{margin-right:3rem!important}.mb-xl-5,.my-xl-5{margin-bottom:3rem!important}.ml-xl-5,.mx-xl-5{margin-left:3rem!important}.p-xl-0{padding:0!important}.pt-xl-0,.py-xl-0{padding-top:0!important}.pr-xl-0,.px-xl-0{padding-right:0!important}.pb-xl-0,.py-xl-0{padding-bottom:0!important}.pl-xl-0,.px-xl-0{padding-left:0!important}.p-xl-1{padding:.25rem!important}.pt-xl-1,.py-xl-1{padding-top:.25rem!important}.pr-xl-1,.px-xl-1{padding-right:.25rem!important}.pb-xl-1,.py-xl-1{padding-bottom:.25rem!important}.pl-xl-1,.px-xl-1{padding-left:.25rem!important}.p-xl-2{padding:.5rem!important}.pt-xl-2,.py-xl-2{padding-top:.5rem!important}.pr-xl-2,.px-xl-2{padding-right:.5rem!important}.pb-xl-2,.py-xl-2{padding-bottom:.5rem!important}.pl-xl-2,.px-xl-2{padding-left:.5rem!important}.p-xl-3{padding:1rem!important}.pt-xl-3,.py-xl-3{padding-top:1rem!important}.pr-xl-3,.px-xl-3{padding-right:1rem!important}.pb-xl-3,.py-xl-3{padding-bottom:1rem!important}.pl-xl-3,.px-xl-3{padding-left:1rem!important}.p-xl-4{padding:1.5rem!important}.pt-xl-4,.py-xl-4{padding-top:1.5rem!important}.pr-xl-4,.px-xl-4{padding-right:1.5rem!important}.pb-xl-4,.py-xl-4{padding-bottom:1.5rem!important}.pl-xl-4,.px-xl-4{padding-left:1.5rem!important}.p-xl-5{padding:3rem!important}.pt-xl-5,.py-xl-5{padding-top:3rem!important}.pr-xl-5,.px-xl-5{padding-right:3rem!important}.pb-xl-5,.py-xl-5{padding-bottom:3rem!important}.pl-xl-5,.px-xl-5{padding-left:3rem!important}.m-xl-n1{margin:-.25rem!important}.mt-xl-n1,.my-xl-n1{margin-top:-.25rem!important}.mr-xl-n1,.mx-xl-n1{margin-right:-.25rem!important}.mb-xl-n1,.my-xl-n1{margin-bottom:-.25rem!important}.ml-xl-n1,.mx-xl-n1{margin-left:-.25rem!important}.m-xl-n2{margin:-.5rem!important}.mt-xl-n2,.my-xl-n2{margin-top:-.5rem!important}.mr-xl-n2,.mx-xl-n2{margin-right:-.5rem!important}.mb-xl-n2,.my-xl-n2{margin-bottom:-.5rem!important}.ml-xl-n2,.mx-xl-n2{margin-left:-.5rem!important}.m-xl-n3{margin:-1rem!important}.mt-xl-n3,.my-xl-n3{margin-top:-1rem!important}.mr-xl-n3,.mx-xl-n3{margin-right:-1rem!important}.mb-xl-n3,.my-xl-n3{margin-bottom:-1rem!important}.ml-xl-n3,.mx-xl-n3{margin-left:-1rem!important}.m-xl-n4{margin:-1.5rem!important}.mt-xl-n4,.my-xl-n4{margin-top:-1.5rem!important}.mr-xl-n4,.mx-xl-n4{margin-right:-1.5rem!important}.mb-xl-n4,.my-xl-n4{margin-bottom:-1.5rem!important}.ml-xl-n4,.mx-xl-n4{margin-left:-1.5rem!important}.m-xl-n5{margin:-3rem!important}.mt-xl-n5,.my-xl-n5{margin-top:-3rem!important}.mr-xl-n5,.mx-xl-n5{margin-right:-3rem!important}.mb-xl-n5,.my-xl-n5{margin-bottom:-3rem!important}.ml-xl-n5,.mx-xl-n5{margin-left:-3rem!important}.m-xl-auto{margin:auto!important}.mt-xl-auto,.my-xl-auto{margin-top:auto!important}.mr-xl-auto,.mx-xl-auto{margin-right:auto!important}.mb-xl-auto,.my-xl-auto{margin-bottom:auto!important}.ml-xl-auto,.mx-xl-auto{margin-left:auto!important}}.stretched-link::after{position:absolute;top:0;right:0;bottom:0;left:0;z-index:1;pointer-events:auto;content:"";background-color:rgba(0,0,0,0)}.text-monospace{font-family:SFMono-Regular,Menlo,Monaco,Consolas,"Liberation Mono","Courier New",monospace!important}.text-justify{text-align:justify!important}.text-wrap{white-space:normal!important}.text-nowrap{white-space:nowrap!important}.text-truncate{overflow:hidden;text-overflow:ellipsis;white-space:nowrap}.text-left{text-align:left!important}.text-right{text-align:right!important}.text-center{text-align:center!important}@media (min-width:576px){.text-sm-left{text-align:left!important}.text-sm-right{text-align:right!important}.text-sm-center{text-align:center!important}}@media (min-width:768px){.text-md-left{text-align:left!important}.text-md-right{text-align:right!important}.text-md-center{text-align:center!important}}@media (min-width:992px){.text-lg-left{text-align:left!important}.text-lg-right{text-align:right!important}.text-lg-center{text-align:center!important}}@media (min-width:1200px){.text-xl-left{text-align:left!important}.text-xl-right{text-align:right!important}.text-xl-center{text-align:center!important}}.text-lowercase{text-transform:lowercase!important}.text-uppercase{text-transform:uppercase!important}.text-capitalize{text-transform:capitalize!important}.font-weight-light{font-weight:300!important}.font-weight-lighter{font-weight:lighter!important}.font-weight-normal{font-weight:400!important}.font-weight-bold{font-weight:700!important}.font-weight-bolder{font-weight:bolder!important}.font-italic{font-style:italic!important}.text-white{color:#fff!important}.text-primary{color:#007bff!important}a.text-primary:focus,a.text-primary:hover{color:#0056b3!important}.text-secondary{color:#6c757d!important}a.text-secondary:focus,a.text-secondary:hover{color:#494f54!important}.text-success{color:#28a745!important}a.text-success:focus,a.text-success:hover{color:#19692c!important}.text-info{color:#17a2b8!important}a.text-info:focus,a.text-info:hover{color:#0f6674!important}.text-warning{color:#ffc107!important}a.text-warning:focus,a.text-warning:hover{color:#ba8b00!important}.text-danger{color:#dc3545!important}a.text-danger:focus,a.text-danger:hover{color:#a71d2a!important}.text-light{color:#f8f9fa!important}a.text-light:focus,a.text-light:hover{color:#cbd3da!important}.text-dark{color:#343a40!important}a.text-dark:focus,a.text-dark:hover{color:#121416!important}.text-body{color:#212529!important}.text-muted{color:#6c757d!important}.text-black-50{color:rgba(0,0,0,.5)!important}.text-white-50{color:rgba(255,255,255,.5)!important}.text-hide{font:0/0 a;color:transparent;text-shadow:none;background-color:transparent;border:0}.text-decoration-none{text-decoration:none!important}.text-break{word-break:break-word!important;word-wrap:break-word!important}.text-reset{color:inherit!important}.visible{visibility:visible!important}.invisible{visibility:hidden!important}@media print{*,::after,::before{text-shadow:none!important;box-shadow:none!important}a:not(.btn){text-decoration:underline}abbr[title]::after{content:" (" attr(title) ")"}pre{white-space:pre-wrap!important}blockquote,pre{border:1px solid #adb5bd;page-break-inside:avoid}img,tr{page-break-inside:avoid}h2,h3,p{orphans:3;widows:3}h2,h3{page-break-after:avoid}@page{size:a3}body{min-width:992px!important}.container{min-width:992px!important}.navbar{display:none}.badge{border:1px solid #000}.table{border-collapse:collapse!important}.table td,.table th{background-color:#fff!important}.table-bordered td,.table-bordered th{border:1px solid #dee2e6!important}.table-dark{color:inherit}.table-dark tbody+tbody,.table-dark td,.table-dark th,.table-dark thead th{border-color:#dee2e6}.table .thead-dark th{color:inherit;border-color:#dee2e6}} -/*# sourceMappingURL=bootstrap.min.css.map */ \ No newline at end of file diff --git a/spaces/wetey/Headline-Content-Generator/README.md b/spaces/wetey/Headline-Content-Generator/README.md deleted file mode 100644 index fd8df9613f6346f9af29a865b521d37c3425bbbc..0000000000000000000000000000000000000000 --- a/spaces/wetey/Headline-Content-Generator/README.md +++ /dev/null @@ -1,38 +0,0 @@ ---- -title: Headline Content Generator -emoji: 📚 -colorFrom: blue -colorTo: gray -sdk: gradio -sdk_version: 3.27.0 -app_file: app.py -pinned: false ---- - -This app can generate a headline for a given paragraph or a paraghraph from a headline.
      -To use:
      -Paste text into input text box.
      -To generate a headline, click on "Generate headline", to generate a short paragraph, click on "Generate short Paragraph"
      - -Reference:
      -Headline = "Introducing droidlet, a one-stop shop for modularly building intelligent agents" -Content = "Droidlet is a platform for building intelligent agents that simplifies integrating a wide range of machine learning algorithms to facilitate rapid prototyping. - It can be used to quickly test out different algorithms with a robot. - Droidlet can help researchers easily build agents that can complete complex tasks in the real world or in simulated environments. - This article introduces Droidlet and explains how the platform works."
      - -Example - Headline generation:
      -Input = "Droidlet is a platform for building intelligent agents that simplifies integrating a wide range of machine learning algorithms to facilitate rapid prototyping. - It can be used to quickly test out different algorithms with a robot. - Droidlet can help researchers easily build agents that can complete complex tasks in the real world or in simulated environments. - This article introduces Droidlet and explains how the platform works."

      -Output from model = "Droidlet helps researchers develop robot-like agents with automated physics"
      - -Example - short paraghraph generation:
      -Input = "Introducing droidlet, a one-stop shop for modularly building intelligent agents"

      -Output from model = "The team behind the project has partnered with Google to design and build smart agents. - The company is looking to expand its presence over time. - It will allow companies to build real-world agents in many different ways, - such as building robots, creating artificial intelligence, and more. - The new product is available for purchase in the UK. - In addition, the company has announced that it will be able to build one of the most effective agents in the world." diff --git a/spaces/whitphx/gradio-static-test/dist/assets/index-44ee6c5c.js b/spaces/whitphx/gradio-static-test/dist/assets/index-44ee6c5c.js deleted file mode 100644 index 8e1a50ebe4efa77142ac83b9ede821d6024634af..0000000000000000000000000000000000000000 --- a/spaces/whitphx/gradio-static-test/dist/assets/index-44ee6c5c.js +++ /dev/null @@ -1,2 +0,0 @@ -import{E as u,L as v}from"./index-46909c92.js";import{s as k,t,h as S,L as w,i as z,w as x,f as R,a as U,b as _,I as T,x as V}from"./index-1040e6d9.js";import"../lite.js";import"./Blocks-99723874.js";import"./Button-0391b19a.js";import"./BlockLabel-a3ec523d.js";import"./Empty-91947ea3.js";/* empty css */import"./Copy-d654b047.js";import"./Download-35908774.js";const Y=94,g=1,C=95,Z=96,f=2,$=[9,10,11,12,13,32,133,160,5760,8192,8193,8194,8195,8196,8197,8198,8199,8200,8201,8202,8232,8233,8239,8287,12288],G=58,N=40,X=95,q=91,c=45,E=46,j=35,D=37;function p(e){return e>=65&&e<=90||e>=97&&e<=122||e>=161}function I(e){return e>=48&&e<=57}const B=new u((e,o)=>{for(let r=!1,a=0,O=0;;O++){let{next:l}=e;if(p(l)||l==c||l==X||r&&I(l))!r&&(l!=c||O>0)&&(r=!0),a===O&&l==c&&a++,e.advance();else{r&&e.acceptToken(l==N?C:a==2&&o.canShift(f)?f:Z);break}}}),A=new u(e=>{if($.includes(e.peek(-1))){let{next:o}=e;(p(o)||o==X||o==j||o==E||o==q||o==G||o==c)&&e.acceptToken(Y)}}),F=new u(e=>{if(!$.includes(e.peek(-1))){let{next:o}=e;if(o==D&&(e.advance(),e.acceptToken(g)),p(o)){do e.advance();while(p(e.next));e.acceptToken(g)}}}),L=k({"AtKeyword import charset namespace keyframes media supports":t.definitionKeyword,"from to selector":t.keyword,NamespaceName:t.namespace,KeyframeName:t.labelName,TagName:t.tagName,ClassName:t.className,PseudoClassName:t.constant(t.className),IdName:t.labelName,"FeatureName PropertyName":t.propertyName,AttributeName:t.attributeName,NumberLiteral:t.number,KeywordQuery:t.keyword,UnaryQueryOp:t.operatorKeyword,"CallTag ValueName":t.atom,VariableName:t.variableName,Callee:t.operatorKeyword,Unit:t.unit,"UniversalSelector NestingSelector":t.definitionOperator,MatchOp:t.compareOperator,"ChildOp SiblingOp, LogicOp":t.logicOperator,BinOp:t.arithmeticOperator,Important:t.modifier,Comment:t.blockComment,ParenthesizedContent:t.special(t.name),ColorLiteral:t.color,StringLiteral:t.string,":":t.punctuation,"PseudoOp #":t.derefOperator,"; ,":t.separator,"( )":t.paren,"[ ]":t.squareBracket,"{ }":t.brace}),K={__proto__:null,lang:32,"nth-child":32,"nth-last-child":32,"nth-of-type":32,"nth-last-of-type":32,dir:32,"host-context":32,url:60,"url-prefix":60,domain:60,regexp:60,selector:134},J={__proto__:null,"@import":114,"@media":138,"@charset":142,"@namespace":146,"@keyframes":152,"@supports":164},H={__proto__:null,not:128,only:128,from:158,to:160},M=v.deserialize({version:14,states:"7WQYQ[OOO#_Q[OOOOQP'#Cd'#CdOOQP'#Cc'#CcO#fQ[O'#CfO$YQXO'#CaO$aQ[O'#ChO$lQ[O'#DPO$qQ[O'#DTOOQP'#Ed'#EdO$vQdO'#DeO%bQ[O'#DrO$vQdO'#DtO%sQ[O'#DvO&OQ[O'#DyO&TQ[O'#EPO&cQ[O'#EROOQS'#Ec'#EcOOQS'#ET'#ETQYQ[OOO&jQXO'#CdO'_QWO'#DaO'dQWO'#EjO'oQ[O'#EjQOQWOOOOQP'#Cg'#CgOOQP,59Q,59QO#fQ[O,59QO'yQ[O'#EWO(eQWO,58{O(mQ[O,59SO$lQ[O,59kO$qQ[O,59oO'yQ[O,59sO'yQ[O,59uO'yQ[O,59vO(xQ[O'#D`OOQS,58{,58{OOQP'#Ck'#CkOOQO'#C}'#C}OOQP,59S,59SO)PQWO,59SO)UQWO,59SOOQP'#DR'#DROOQP,59k,59kOOQO'#DV'#DVO)ZQ`O,59oOOQS'#Cp'#CpO$vQdO'#CqO)cQvO'#CsO*pQtO,5:POOQO'#Cx'#CxO)UQWO'#CwO+UQWO'#CyOOQS'#Eg'#EgOOQO'#Dh'#DhO+ZQ[O'#DoO+iQWO'#EkO&TQ[O'#DmO+wQWO'#DpOOQO'#El'#ElO(hQWO,5:^O+|QpO,5:`OOQS'#Dx'#DxO,UQWO,5:bO,ZQ[O,5:bOOQO'#D{'#D{O,cQWO,5:eO,hQWO,5:kO,pQWO,5:mOOQS-E8R-E8RO$vQdO,59{O,xQ[O'#EYO-VQWO,5;UO-VQWO,5;UOOQP1G.l1G.lO-|QXO,5:rOOQO-E8U-E8UOOQS1G.g1G.gOOQP1G.n1G.nO)PQWO1G.nO)UQWO1G.nOOQP1G/V1G/VO.ZQ`O1G/ZO.tQXO1G/_O/[QXO1G/aO/rQXO1G/bO0YQWO,59zO0_Q[O'#DOO0fQdO'#CoOOQP1G/Z1G/ZO$vQdO1G/ZO0mQpO,59]OOQS,59_,59_O$vQdO,59aO0uQWO1G/kOOQS,59c,59cO0zQ!bO,59eO1SQWO'#DhO1_QWO,5:TO1dQWO,5:ZO&TQ[O,5:VO&TQ[O'#EZO1lQWO,5;VO1wQWO,5:XO'yQ[O,5:[OOQS1G/x1G/xOOQS1G/z1G/zOOQS1G/|1G/|O2YQWO1G/|O2_QdO'#D|OOQS1G0P1G0POOQS1G0V1G0VOOQS1G0X1G0XO2mQtO1G/gOOQO,5:t,5:tO3TQ[O,5:tOOQO-E8W-E8WO3bQWO1G0pOOQP7+$Y7+$YOOQP7+$u7+$uO$vQdO7+$uOOQS1G/f1G/fO3mQXO'#EiO3tQWO,59jO3yQtO'#EUO4nQdO'#EfO4xQWO,59ZO4}QpO7+$uOOQS1G.w1G.wOOQS1G.{1G.{OOQS7+%V7+%VO5VQWO1G/PO$vQdO1G/oOOQO1G/u1G/uOOQO1G/q1G/qO5[QWO,5:uOOQO-E8X-E8XO5jQXO1G/vOOQS7+%h7+%hO5qQYO'#CsO(hQWO'#E[O5yQdO,5:hOOQS,5:h,5:hO6XQtO'#EXO$vQdO'#EXO7VQdO7+%ROOQO7+%R7+%ROOQO1G0`1G0`O7jQpO<T![;'S%^;'S;=`%o<%lO%^^;TUoWOy%^z!Q%^!Q![;g![;'S%^;'S;=`%o<%lO%^^;nYoW#[UOy%^z!Q%^!Q![;g![!g%^!g!h<^!h#X%^#X#Y<^#Y;'S%^;'S;=`%o<%lO%^^[[oW#[UOy%^z!O%^!O!P;g!P!Q%^!Q![>T![!g%^!g!h<^!h#X%^#X#Y<^#Y;'S%^;'S;=`%o<%lO%^_?VSpVOy%^z;'S%^;'S;=`%o<%lO%^^?hWjSOy%^z!O%^!O!P;O!P!Q%^!Q![>T![;'S%^;'S;=`%o<%lO%^_@VU#XPOy%^z!Q%^!Q![;g![;'S%^;'S;=`%o<%lO%^~@nTjSOy%^z{@}{;'S%^;'S;=`%o<%lO%^~ASUoWOy@}yzAfz{Bm{;'S@};'S;=`Co<%lO@}~AiTOzAfz{Ax{;'SAf;'S;=`Bg<%lOAf~A{VOzAfz{Ax{!PAf!P!QBb!Q;'SAf;'S;=`Bg<%lOAf~BgOR~~BjP;=`<%lAf~BrWoWOy@}yzAfz{Bm{!P@}!P!QC[!Q;'S@};'S;=`Co<%lO@}~CcSoWR~Oy%^z;'S%^;'S;=`%o<%lO%^~CrP;=`<%l@}^Cz[#[UOy%^z!O%^!O!P;g!P!Q%^!Q![>T![!g%^!g!h<^!h#X%^#X#Y<^#Y;'S%^;'S;=`%o<%lO%^XDuU]POy%^z![%^![!]EX!];'S%^;'S;=`%o<%lO%^XE`S^PoWOy%^z;'S%^;'S;=`%o<%lO%^_EqS!WVOy%^z;'S%^;'S;=`%o<%lO%^YFSSzQOy%^z;'S%^;'S;=`%o<%lO%^XFeU|POy%^z!`%^!`!aFw!a;'S%^;'S;=`%o<%lO%^XGOS|PoWOy%^z;'S%^;'S;=`%o<%lO%^XG_WOy%^z!c%^!c!}Gw!}#T%^#T#oGw#o;'S%^;'S;=`%o<%lO%^XHO[!YPoWOy%^z}%^}!OGw!O!Q%^!Q![Gw![!c%^!c!}Gw!}#T%^#T#oGw#o;'S%^;'S;=`%o<%lO%^XHySxPOy%^z;'S%^;'S;=`%o<%lO%^^I[SvUOy%^z;'S%^;'S;=`%o<%lO%^XIkUOy%^z#b%^#b#cI}#c;'S%^;'S;=`%o<%lO%^XJSUoWOy%^z#W%^#W#XJf#X;'S%^;'S;=`%o<%lO%^XJmS!`PoWOy%^z;'S%^;'S;=`%o<%lO%^XJ|UOy%^z#f%^#f#gJf#g;'S%^;'S;=`%o<%lO%^XKeS!RPOy%^z;'S%^;'S;=`%o<%lO%^_KvS!QVOy%^z;'S%^;'S;=`%o<%lO%^ZLXU!PPOy%^z!_%^!_!`6y!`;'S%^;'S;=`%o<%lO%^WLnP;=`<%l$}",tokenizers:[A,F,B,0,1,2,3],topRules:{StyleSheet:[0,4],Styles:[1,84]},specialized:[{term:95,get:e=>K[e]||-1},{term:56,get:e=>J[e]||-1},{term:96,get:e=>H[e]||-1}],tokenPrec:1123});let Q=null;function m(){if(!Q&&typeof document=="object"&&document.body){let{style:e}=document.body,o=[],r=new Set;for(let a in e)a!="cssText"&&a!="cssFloat"&&typeof e[a]=="string"&&(/[A-Z]/.test(a)&&(a=a.replace(/[A-Z]/g,O=>"-"+O.toLowerCase())),r.has(a)||(o.push(a),r.add(a)));Q=o.sort().map(a=>({type:"property",label:a}))}return Q||[]}const h=["active","after","any-link","autofill","backdrop","before","checked","cue","default","defined","disabled","empty","enabled","file-selector-button","first","first-child","first-letter","first-line","first-of-type","focus","focus-visible","focus-within","fullscreen","has","host","host-context","hover","in-range","indeterminate","invalid","is","lang","last-child","last-of-type","left","link","marker","modal","not","nth-child","nth-last-child","nth-last-of-type","nth-of-type","only-child","only-of-type","optional","out-of-range","part","placeholder","placeholder-shown","read-only","read-write","required","right","root","scope","selection","slotted","target","target-text","valid","visited","where"].map(e=>({type:"class",label:e})),b=["above","absolute","activeborder","additive","activecaption","after-white-space","ahead","alias","all","all-scroll","alphabetic","alternate","always","antialiased","appworkspace","asterisks","attr","auto","auto-flow","avoid","avoid-column","avoid-page","avoid-region","axis-pan","background","backwards","baseline","below","bidi-override","blink","block","block-axis","bold","bolder","border","border-box","both","bottom","break","break-all","break-word","bullets","button","button-bevel","buttonface","buttonhighlight","buttonshadow","buttontext","calc","capitalize","caps-lock-indicator","caption","captiontext","caret","cell","center","checkbox","circle","cjk-decimal","clear","clip","close-quote","col-resize","collapse","color","color-burn","color-dodge","column","column-reverse","compact","condensed","contain","content","contents","content-box","context-menu","continuous","copy","counter","counters","cover","crop","cross","crosshair","currentcolor","cursive","cyclic","darken","dashed","decimal","decimal-leading-zero","default","default-button","dense","destination-atop","destination-in","destination-out","destination-over","difference","disc","discard","disclosure-closed","disclosure-open","document","dot-dash","dot-dot-dash","dotted","double","down","e-resize","ease","ease-in","ease-in-out","ease-out","element","ellipse","ellipsis","embed","end","ethiopic-abegede-gez","ethiopic-halehame-aa-er","ethiopic-halehame-gez","ew-resize","exclusion","expanded","extends","extra-condensed","extra-expanded","fantasy","fast","fill","fill-box","fixed","flat","flex","flex-end","flex-start","footnotes","forwards","from","geometricPrecision","graytext","grid","groove","hand","hard-light","help","hidden","hide","higher","highlight","highlighttext","horizontal","hsl","hsla","hue","icon","ignore","inactiveborder","inactivecaption","inactivecaptiontext","infinite","infobackground","infotext","inherit","initial","inline","inline-axis","inline-block","inline-flex","inline-grid","inline-table","inset","inside","intrinsic","invert","italic","justify","keep-all","landscape","large","larger","left","level","lighter","lighten","line-through","linear","linear-gradient","lines","list-item","listbox","listitem","local","logical","loud","lower","lower-hexadecimal","lower-latin","lower-norwegian","lowercase","ltr","luminosity","manipulation","match","matrix","matrix3d","medium","menu","menutext","message-box","middle","min-intrinsic","mix","monospace","move","multiple","multiple_mask_images","multiply","n-resize","narrower","ne-resize","nesw-resize","no-close-quote","no-drop","no-open-quote","no-repeat","none","normal","not-allowed","nowrap","ns-resize","numbers","numeric","nw-resize","nwse-resize","oblique","opacity","open-quote","optimizeLegibility","optimizeSpeed","outset","outside","outside-shape","overlay","overline","padding","padding-box","painted","page","paused","perspective","pinch-zoom","plus-darker","plus-lighter","pointer","polygon","portrait","pre","pre-line","pre-wrap","preserve-3d","progress","push-button","radial-gradient","radio","read-only","read-write","read-write-plaintext-only","rectangle","region","relative","repeat","repeating-linear-gradient","repeating-radial-gradient","repeat-x","repeat-y","reset","reverse","rgb","rgba","ridge","right","rotate","rotate3d","rotateX","rotateY","rotateZ","round","row","row-resize","row-reverse","rtl","run-in","running","s-resize","sans-serif","saturation","scale","scale3d","scaleX","scaleY","scaleZ","screen","scroll","scrollbar","scroll-position","se-resize","self-start","self-end","semi-condensed","semi-expanded","separate","serif","show","single","skew","skewX","skewY","skip-white-space","slide","slider-horizontal","slider-vertical","sliderthumb-horizontal","sliderthumb-vertical","slow","small","small-caps","small-caption","smaller","soft-light","solid","source-atop","source-in","source-out","source-over","space","space-around","space-between","space-evenly","spell-out","square","start","static","status-bar","stretch","stroke","stroke-box","sub","subpixel-antialiased","svg_masks","super","sw-resize","symbolic","symbols","system-ui","table","table-caption","table-cell","table-column","table-column-group","table-footer-group","table-header-group","table-row","table-row-group","text","text-bottom","text-top","textarea","textfield","thick","thin","threeddarkshadow","threedface","threedhighlight","threedlightshadow","threedshadow","to","top","transform","translate","translate3d","translateX","translateY","translateZ","transparent","ultra-condensed","ultra-expanded","underline","unidirectional-pan","unset","up","upper-latin","uppercase","url","var","vertical","vertical-text","view-box","visible","visibleFill","visiblePainted","visibleStroke","visual","w-resize","wait","wave","wider","window","windowframe","windowtext","words","wrap","wrap-reverse","x-large","x-small","xor","xx-large","xx-small"].map(e=>({type:"keyword",label:e})).concat(["aliceblue","antiquewhite","aqua","aquamarine","azure","beige","bisque","black","blanchedalmond","blue","blueviolet","brown","burlywood","cadetblue","chartreuse","chocolate","coral","cornflowerblue","cornsilk","crimson","cyan","darkblue","darkcyan","darkgoldenrod","darkgray","darkgreen","darkkhaki","darkmagenta","darkolivegreen","darkorange","darkorchid","darkred","darksalmon","darkseagreen","darkslateblue","darkslategray","darkturquoise","darkviolet","deeppink","deepskyblue","dimgray","dodgerblue","firebrick","floralwhite","forestgreen","fuchsia","gainsboro","ghostwhite","gold","goldenrod","gray","grey","green","greenyellow","honeydew","hotpink","indianred","indigo","ivory","khaki","lavender","lavenderblush","lawngreen","lemonchiffon","lightblue","lightcoral","lightcyan","lightgoldenrodyellow","lightgray","lightgreen","lightpink","lightsalmon","lightseagreen","lightskyblue","lightslategray","lightsteelblue","lightyellow","lime","limegreen","linen","magenta","maroon","mediumaquamarine","mediumblue","mediumorchid","mediumpurple","mediumseagreen","mediumslateblue","mediumspringgreen","mediumturquoise","mediumvioletred","midnightblue","mintcream","mistyrose","moccasin","navajowhite","navy","oldlace","olive","olivedrab","orange","orangered","orchid","palegoldenrod","palegreen","paleturquoise","palevioletred","papayawhip","peachpuff","peru","pink","plum","powderblue","purple","rebeccapurple","red","rosybrown","royalblue","saddlebrown","salmon","sandybrown","seagreen","seashell","sienna","silver","skyblue","slateblue","slategray","snow","springgreen","steelblue","tan","teal","thistle","tomato","turquoise","violet","wheat","white","whitesmoke","yellow","yellowgreen"].map(e=>({type:"constant",label:e}))),ee=["a","abbr","address","article","aside","b","bdi","bdo","blockquote","body","br","button","canvas","caption","cite","code","col","colgroup","dd","del","details","dfn","dialog","div","dl","dt","em","figcaption","figure","footer","form","header","hgroup","h1","h2","h3","h4","h5","h6","hr","html","i","iframe","img","input","ins","kbd","label","legend","li","main","meter","nav","ol","output","p","pre","ruby","section","select","small","source","span","strong","sub","summary","sup","table","tbody","td","template","textarea","tfoot","th","thead","tr","u","ul"].map(e=>({type:"type",label:e})),n=/^(\w[\w-]*|-\w[\w-]*|)$/,ae=/^-(-[\w-]*)?$/;function Oe(e,o){var r;if((e.name=="("||e.type.isError)&&(e=e.parent||e),e.name!="ArgList")return!1;let a=(r=e.parent)===null||r===void 0?void 0:r.firstChild;return a?.name!="Callee"?!1:o.sliceString(a.from,a.to)=="var"}const y=new V,te=["Declaration"];function W(e,o){if(o.to-o.from>4096){let r=y.get(o);if(r)return r;let a=[],O=new Set,l=o.cursor(T.IncludeAnonymous);if(l.firstChild())do for(let i of W(e,l.node))O.has(i.label)||(O.add(i.label),a.push(i));while(l.nextSibling());return y.set(o,a),a}else{let r=[],a=new Set;return o.cursor().iterate(O=>{var l;if(O.name=="VariableName"&&O.matchContext(te)&&((l=O.node.nextSibling)===null||l===void 0?void 0:l.name)==":"){let i=e.sliceString(O.from,O.to);a.has(i)||(a.add(i),r.push({label:i,type:"variable"}))}}),r}}const oe=e=>{var o;let{state:r,pos:a}=e,O=S(r).resolveInner(a,-1),l=O.type.isError&&O.from==O.to-1&&r.doc.sliceString(O.from,O.to)=="-";if(O.name=="PropertyName"||l&&((o=O.parent)===null||o===void 0?void 0:o.name)=="Block")return{from:O.from,options:m(),validFor:n};if(O.name=="ValueName")return{from:O.from,options:b,validFor:n};if(O.name=="PseudoClassName")return{from:O.from,options:h,validFor:n};if(O.name=="VariableName"||(e.explicit||l)&&Oe(O,r.doc))return{from:O.name=="VariableName"?O.from:a,options:W(r.doc,S(r).topNode),validFor:ae};if(O.name=="TagName"){for(let{parent:d}=O;d;d=d.parent)if(d.name=="Block")return{from:O.from,options:m(),validFor:n};return{from:O.from,options:ee,validFor:n}}if(!e.explicit)return null;let i=O.resolve(a),s=i.childBefore(a);return s&&s.name==":"&&i.name=="PseudoClassSelector"?{from:a,options:h,validFor:n}:s&&s.name==":"&&i.name=="Declaration"||i.name=="ArgList"?{from:a,options:b,validFor:n}:i.name=="Block"?{from:a,options:m(),validFor:n}:null},P=w.define({name:"css",parser:M.configure({props:[z.add({Declaration:x()}),R.add({Block:U})]}),languageData:{commentTokens:{block:{open:"/*",close:"*/"}},indentOnInput:/^\s*\}$/,wordChars:"-"}});function ue(){return new _(P,P.data.of({autocomplete:oe}))}export{ue as css,oe as cssCompletionSource,P as cssLanguage}; -//# sourceMappingURL=index-44ee6c5c.js.map diff --git a/spaces/whyu/MM-Vet_Evaluator/app.py b/spaces/whyu/MM-Vet_Evaluator/app.py deleted file mode 100644 index 2e9dfd50e2f5b43527a284ba1e6c280f2c2babd4..0000000000000000000000000000000000000000 --- a/spaces/whyu/MM-Vet_Evaluator/app.py +++ /dev/null @@ -1,325 +0,0 @@ -import gradio as gr -import openai -import json -import os -from tqdm import tqdm -import pandas as pd -import numpy as np -from collections import Counter -import time -from zipfile import ZipFile - -openai.api_key = os.environ.get("AZURE_OPENAI_KEY") -openai.api_base = os.environ.get("AZURE_OPENAI_ENDPOINT") -openai.api_type = 'azure' -openai.api_version = os.environ.get("AZURE_OPENAI_API_VERSION") -deployment_id = os.environ.get("AZURE_OPENAI_DEP_ID") -gpt_model = deployment_id - - - - -prompt = """Compare the ground truth and prediction from AI models, to give a correctness score for the prediction. in the ground truth means it is totally right only when all elements in the ground truth are present in the prediction, and means it is totally right when any one element in the ground truth is present in the prediction. The correctness score is 0.0 (totally wrong), 0.1, 0.2, 0.3, 0.4, 0.5, 0.6, 0.7, 0.8, 0.9, or 1.0 (totally right). Just complete the last space of the correctness score. - -Question | Ground truth | Prediction | Correctness ---- | --- | --- | --- -What is x in the equation? | -1 -5 | x = 3 | 0.0 -What is x in the equation? | -1 -5 | x = -1 | 0.5 -What is x in the equation? | -1 -5 | x = -5 | 0.5 -What is x in the equation? | -1 -5 | x = -5 or 5 | 0.5 -What is x in the equation? | -1 -5 | x = -1 or x = -5 | 1.0 -Can you explain this meme? | This meme is poking fun at the fact that the names of the countries Iceland and Greenland are misleading. Despite its name, Iceland is known for its beautiful green landscapes, while Greenland is mostly covered in ice and snow. The meme is saying that the person has trust issues because the names of these countries do not accurately represent their landscapes. | The meme talks about Iceland and Greenland. It's pointing out that despite their names, Iceland is not very icy and Greenland isn't very green. | 0.4 -Can you explain this meme? | This meme is poking fun at the fact that the names of the countries Iceland and Greenland are misleading. Despite its name, Iceland is known for its beautiful green landscapes, while Greenland is mostly covered in ice and snow. The meme is saying that the person has trust issues because the names of these countries do not accurately represent their landscapes. | The meme is using humor to point out the misleading nature of Iceland's and Greenland's names. Iceland, despite its name, has lush green landscapes while Greenland is mostly covered in ice and snow. The text 'This is why I have trust issues' is a playful way to suggest that these contradictions can lead to distrust or confusion. The humor in this meme is derived from the unexpected contrast between the names of the countries and their actual physical characteristics. | 1.0 -""" - - - -def grade(file_obj, progress=gr.Progress()): - # load metadata - # Download mm-vet.zip and `unzip mm-vet.zip` and change the path below - mmvet_path = "mm-vet" - use_sub_set = False - decimal_places = 1 # number of decimal places to round to - - - if use_sub_set: - bard_set_file = os.path.join(mmvet_path, "bard_set.json") - with open(bard_set_file, 'r') as f: - sub_set = json.load(f) - sub_set_name = 'bardset' - sub_set_name = sub_set_name + '_' - else: - sub_set = None - sub_set_name = '' - - mmvet_metadata = os.path.join(mmvet_path, "mm-vet.json") - with open(mmvet_metadata, 'r') as f: - data = json.load(f) - - - counter = Counter() - cap_set_list = [] - cap_set_counter = [] - len_data = 0 - for id, value in data.items(): - if sub_set is not None and id not in sub_set: - continue - question = value["question"] - answer = value["answer"] - cap = value["capability"] - cap = set(cap) - counter.update(cap) - if cap not in cap_set_list: - cap_set_list.append(cap) - cap_set_counter.append(1) - else: - cap_set_counter[cap_set_list.index(cap)] += 1 - - len_data += 1 - - sorted_list = counter.most_common() - columns = [k for k, v in sorted_list] - columns.append("total") - columns.append("std") - columns.append('runs') - df = pd.DataFrame(columns=columns) - - - cap_set_sorted_indices = np.argsort(-np.array(cap_set_counter)) - new_cap_set_list = [] - new_cap_set_counter = [] - for index in cap_set_sorted_indices: - new_cap_set_list.append(cap_set_list[index]) - new_cap_set_counter.append(cap_set_counter[index]) - - cap_set_list = new_cap_set_list - cap_set_counter = new_cap_set_counter - cap_set_names = ["_".join(list(cap_set)) for cap_set in cap_set_list] - - columns2 = cap_set_names - columns2.append("total") - columns2.append("std") - columns2.append('runs') - df2 = pd.DataFrame(columns=columns2) - - - ###### change your model name ###### - model = file_obj.name.split("/")[-1][:-5] - # result_path = "results" - num_run = 1 # we set 5 in the paper - # model_results_file = os.path.join(result_path, f"{model}.json") - model_results_file = file_obj.name - - # grade results for each sample to svae - grade_file = f'{model}_{gpt_model}-grade-{num_run}runs.json' - # grade_file = os.path.join(result_path, grade_file) - - # score results regarding capabilities/capability integration to save - cap_score_file = f'{model}_{sub_set_name}{gpt_model}-cap-score-{num_run}runs.csv' - # cap_score_file = os.path.join(result_path, cap_score_file) - cap_int_score_file = f'{model}_{sub_set_name}{gpt_model}-cap-int-score-{num_run}runs.csv' - # cap_int_score_file = os.path.join(result_path, cap_int_score_file) - - - - with open(model_results_file) as f: - results = json.load(f) - if os.path.exists(grade_file): - with open(grade_file, 'r') as f: - grade_results = json.load(f) - else: - grade_results = {} - - - def need_more_runs(): - need_more_runs = False - if len(grade_results) > 0: - for k, v in grade_results.items(): - if len(v['score']) < num_run: - need_more_runs = True - break - return need_more_runs or len(grade_results) < len_data - - - while need_more_runs(): - for j in range(num_run): - print(f'eval run {j}') - for id, line in progress.tqdm(data.items(), desc="Grading"): - if sub_set is not None and id not in sub_set: - continue - if id in grade_results and len(grade_results[id]['score']) >= (j + 1): - continue - - model_pred = results[id] - - question = prompt + '\n' + ' | '.join([line['question'], line['answer'].replace("", " ").replace("", " "), model_pred, ""]) - messages = [ - {"role": "user", "content": question}, - ] - - if id not in grade_results: - sample_grade = {'model': [], 'content': [], 'score': []} - else: - sample_grade = grade_results[id] - - - grade_sample_run_complete = False - temperature = 0.0 - - num_sleep = 0 - while not grade_sample_run_complete: - try: - response = openai.ChatCompletion.create( - # model=gpt_model, - engine=gpt_model, - max_tokens=3, - temperature=temperature, - messages=messages) - content = response['choices'][0]['message']['content'] - flag = True - try_time = 1 - while flag: - try: - content = content.split(' ')[0].strip() - score = float(content) - if score > 1.0 or score < 0.0: - assert False - flag = False - except: - question = prompt + '\n' + ' | '.join([line['question'], line['answer'].replace("", " ").replace("", " "), model_pred, ""]) + "\nPredict the correctness of the answer (digit): " - messages = [ - {"role": "user", "content": question}, - ] - response = openai.ChatCompletion.create( - # model=gpt_model, - engine=gpt_model, - max_tokens=3, - temperature=temperature, - messages=messages) - content = response['choices'][0]['message']['content'] - try_time += 1 - temperature += 0.5 - print(f"{id} try {try_time} times") - print(content) - if try_time > 5: - score = 0.0 - flag = False - grade_sample_run_complete = True - except: - # gpt4 may have token rate limit - num_sleep += 1 - if num_sleep > 12: - score = 0.0 - grade_sample_run_complete = True - num_sleep = 0 - continue - print("sleep 5s") - time.sleep(5) - - - if len(sample_grade['model']) >= j + 1: - sample_grade['model'][j] = response['model'] - sample_grade['content'][j] = content - sample_grade['score'][j] = score - else: - sample_grade['model'].append(response['model']) - sample_grade['content'].append(content) - sample_grade['score'].append(score) - grade_results[id] = sample_grade - - with open(grade_file, 'w') as f: - json.dump(grade_results, f, indent=4) - - - assert not need_more_runs() - cap_socres = {k: [0.0]*num_run for k in columns[:-2]} - counter['total'] = len_data - - cap_socres2 = {k: [0.0]*num_run for k in columns2[:-2]} - counter2 = {columns2[i]:cap_set_counter[i] for i in range(len(cap_set_counter))} - counter2['total'] = len_data - - for k, v in grade_results.items(): - if sub_set is not None and k not in sub_set: - continue - for i in range(num_run): - score = v['score'][i] - caps = set(data[k]['capability']) - for c in caps: - cap_socres[c][i] += score - - cap_socres['total'][i] += score - - index = cap_set_list.index(caps) - cap_socres2[cap_set_names[index]][i] += score - cap_socres2['total'][i] += score - - for k, v in cap_socres.items(): - cap_socres[k] = np.array(v) / counter[k] *100 - - - std = round(cap_socres['total'].std(), decimal_places) - total_copy = cap_socres['total'].copy() - runs = str(list(np.round(total_copy, decimal_places))) - - for k, v in cap_socres.items(): - cap_socres[k] = round(v.mean(), decimal_places) - - cap_socres['std'] = std - cap_socres['runs'] = runs - df.loc[model] = cap_socres - - - for k, v in cap_socres2.items(): - cap_socres2[k] = round(np.mean(np.array(v) / counter2[k] *100), decimal_places) - cap_socres2['std'] = std - cap_socres2['runs'] = runs - df2.loc[model] = cap_socres2 - - df.to_csv(cap_score_file) - df2.to_csv(cap_int_score_file) - - files = [cap_score_file, cap_int_score_file, grade_file] - zip_file = f"results.zip" - with ZipFile(zip_file, "w") as zipObj: - for idx, file in enumerate(files): - zipObj.write(file, file) - for file in files: - os.remove(file) - return zip_file - - - -# demo = gr.Interface( -# fn=grade, -# inputs=gr.File(file_types=[".json"]), -# outputs="file") - - -markdown = """ -

      -
      -

      - - -# [MM-Vet: Evaluating Large Multimodal Models for Integrated Capabilities](https://github.com/yuweihao/MM-Vet) - -In this demo, we offer MM-Vet LLM-based (GPT-4) evaluator to grade open-ended outputs from your models. - -Plese upload your json file of your model results containing `{v1_0: ..., v1_1: ..., }`like [this json file](https://raw.githubusercontent.com/yuweihao/MM-Vet/main/results/llava_llama2_13b_chat.json). - -The grading may last 5 minutes. Sine we only support 1 queue, the grading time may be longer when you need to wait for other users' grading to finish. - -The grading results will be downloaded as a zip file. -""" - - -with gr.Blocks() as demo: - gr.Markdown(markdown) - with gr.Row(): - inp = gr.File(file_types=[".json"]) - out = gr.File(file_types=[".zip"]) - inp.change(grade, inp, out) - -if __name__ == "__main__": - demo.queue().launch() \ No newline at end of file diff --git a/spaces/wouaf/WOUAF-Text-to-Image/torch_utils/ops/conv2d_resample.py b/spaces/wouaf/WOUAF-Text-to-Image/torch_utils/ops/conv2d_resample.py deleted file mode 100644 index cd4750744c83354bab78704d4ef51ad1070fcc4a..0000000000000000000000000000000000000000 --- a/spaces/wouaf/WOUAF-Text-to-Image/torch_utils/ops/conv2d_resample.py +++ /dev/null @@ -1,156 +0,0 @@ -# Copyright (c) 2021, NVIDIA CORPORATION. All rights reserved. -# -# NVIDIA CORPORATION and its licensors retain all intellectual property -# and proprietary rights in and to this software, related documentation -# and any modifications thereto. Any use, reproduction, disclosure or -# distribution of this software and related documentation without an express -# license agreement from NVIDIA CORPORATION is strictly prohibited. - -"""2D convolution with optional up/downsampling.""" - -import torch - -from .. import misc -from . import conv2d_gradfix -from . import upfirdn2d -from .upfirdn2d import _parse_padding -from .upfirdn2d import _get_filter_size - -#---------------------------------------------------------------------------- - -def _get_weight_shape(w): - with misc.suppress_tracer_warnings(): # this value will be treated as a constant - shape = [int(sz) for sz in w.shape] - misc.assert_shape(w, shape) - return shape - -#---------------------------------------------------------------------------- - -def _conv2d_wrapper(x, w, stride=1, padding=0, groups=1, transpose=False, flip_weight=True): - """Wrapper for the underlying `conv2d()` and `conv_transpose2d()` implementations. - """ - out_channels, in_channels_per_group, kh, kw = _get_weight_shape(w) - - # Flip weight if requested. - if not flip_weight: # conv2d() actually performs correlation (flip_weight=True) not convolution (flip_weight=False). - w = w.flip([2, 3]) - - # Workaround performance pitfall in cuDNN 8.0.5, triggered when using - # 1x1 kernel + memory_format=channels_last + less than 64 channels. - if kw == 1 and kh == 1 and stride == 1 and padding in [0, [0, 0], (0, 0)] and not transpose: - if x.stride()[1] == 1 and min(out_channels, in_channels_per_group) < 64: - if out_channels <= 4 and groups == 1: - in_shape = x.shape - x = w.squeeze(3).squeeze(2) @ x.reshape([in_shape[0], in_channels_per_group, -1]) - x = x.reshape([in_shape[0], out_channels, in_shape[2], in_shape[3]]) - else: - x = x.to(memory_format=torch.contiguous_format) - w = w.to(memory_format=torch.contiguous_format) - x = conv2d_gradfix.conv2d(x, w, groups=groups) - return x.to(memory_format=torch.channels_last) - - # Otherwise => execute using conv2d_gradfix. - op = conv2d_gradfix.conv_transpose2d if transpose else conv2d_gradfix.conv2d - return op(x, w, stride=stride, padding=padding, groups=groups) - -#---------------------------------------------------------------------------- - -@misc.profiled_function -def conv2d_resample(x, w, f=None, up=1, down=1, padding=0, groups=1, flip_weight=True, flip_filter=False): - r"""2D convolution with optional up/downsampling. - - Padding is performed only once at the beginning, not between the operations. - - Args: - x: Input tensor of shape - `[batch_size, in_channels, in_height, in_width]`. - w: Weight tensor of shape - `[out_channels, in_channels//groups, kernel_height, kernel_width]`. - f: Low-pass filter for up/downsampling. Must be prepared beforehand by - calling upfirdn2d.setup_filter(). None = identity (default). - up: Integer upsampling factor (default: 1). - down: Integer downsampling factor (default: 1). - padding: Padding with respect to the upsampled image. Can be a single number - or a list/tuple `[x, y]` or `[x_before, x_after, y_before, y_after]` - (default: 0). - groups: Split input channels into N groups (default: 1). - flip_weight: False = convolution, True = correlation (default: True). - flip_filter: False = convolution, True = correlation (default: False). - - Returns: - Tensor of the shape `[batch_size, num_channels, out_height, out_width]`. - """ - # Validate arguments. - assert isinstance(x, torch.Tensor) and (x.ndim == 4) - assert isinstance(w, torch.Tensor) and (w.ndim == 4) and (w.dtype == x.dtype) - assert f is None or (isinstance(f, torch.Tensor) and f.ndim in [1, 2] and f.dtype == torch.float32) - assert isinstance(up, int) and (up >= 1) - assert isinstance(down, int) and (down >= 1) - assert isinstance(groups, int) and (groups >= 1) - out_channels, in_channels_per_group, kh, kw = _get_weight_shape(w) - fw, fh = _get_filter_size(f) - px0, px1, py0, py1 = _parse_padding(padding) - - # Adjust padding to account for up/downsampling. - if up > 1: - px0 += (fw + up - 1) // 2 - px1 += (fw - up) // 2 - py0 += (fh + up - 1) // 2 - py1 += (fh - up) // 2 - if down > 1: - px0 += (fw - down + 1) // 2 - px1 += (fw - down) // 2 - py0 += (fh - down + 1) // 2 - py1 += (fh - down) // 2 - - # Fast path: 1x1 convolution with downsampling only => downsample first, then convolve. - if kw == 1 and kh == 1 and (down > 1 and up == 1): - x = upfirdn2d.upfirdn2d(x=x, f=f, down=down, padding=[px0,px1,py0,py1], flip_filter=flip_filter) - x = _conv2d_wrapper(x=x, w=w, groups=groups, flip_weight=flip_weight) - return x - - # Fast path: 1x1 convolution with upsampling only => convolve first, then upsample. - if kw == 1 and kh == 1 and (up > 1 and down == 1): - x = _conv2d_wrapper(x=x, w=w, groups=groups, flip_weight=flip_weight) - x = upfirdn2d.upfirdn2d(x=x, f=f, up=up, padding=[px0,px1,py0,py1], gain=up**2, flip_filter=flip_filter) - return x - - # Fast path: downsampling only => use strided convolution. - if down > 1 and up == 1: - x = upfirdn2d.upfirdn2d(x=x, f=f, padding=[px0,px1,py0,py1], flip_filter=flip_filter) - x = _conv2d_wrapper(x=x, w=w, stride=down, groups=groups, flip_weight=flip_weight) - return x - - # Fast path: upsampling with optional downsampling => use transpose strided convolution. - if up > 1: - if groups == 1: - w = w.transpose(0, 1) - else: - w = w.reshape(groups, out_channels // groups, in_channels_per_group, kh, kw) - w = w.transpose(1, 2) - w = w.reshape(groups * in_channels_per_group, out_channels // groups, kh, kw) - px0 -= kw - 1 - px1 -= kw - up - py0 -= kh - 1 - py1 -= kh - up - pxt = max(min(-px0, -px1), 0) - pyt = max(min(-py0, -py1), 0) - x = _conv2d_wrapper(x=x, w=w, stride=up, padding=[pyt,pxt], groups=groups, transpose=True, flip_weight=(not flip_weight)) - x = upfirdn2d.upfirdn2d(x=x, f=f, padding=[px0+pxt,px1+pxt,py0+pyt,py1+pyt], gain=up**2, flip_filter=flip_filter) - if down > 1: - x = upfirdn2d.upfirdn2d(x=x, f=f, down=down, flip_filter=flip_filter) - return x - - # Fast path: no up/downsampling, padding supported by the underlying implementation => use plain conv2d. - if up == 1 and down == 1: - if px0 == px1 and py0 == py1 and px0 >= 0 and py0 >= 0: - return _conv2d_wrapper(x=x, w=w, padding=[py0,px0], groups=groups, flip_weight=flip_weight) - - # Fallback: Generic reference implementation. - x = upfirdn2d.upfirdn2d(x=x, f=(f if up > 1 else None), up=up, padding=[px0,px1,py0,py1], gain=up**2, flip_filter=flip_filter) - x = _conv2d_wrapper(x=x, w=w, groups=groups, flip_weight=flip_weight) - if down > 1: - x = upfirdn2d.upfirdn2d(x=x, f=f, down=down, flip_filter=flip_filter) - return x - -#---------------------------------------------------------------------------- diff --git a/spaces/xfys/yolov5_tracking/trackers/strong_sort/deep/models/densenet.py b/spaces/xfys/yolov5_tracking/trackers/strong_sort/deep/models/densenet.py deleted file mode 100644 index a1d9b7ef85a79cbc4c4e8a81840935531df636b8..0000000000000000000000000000000000000000 --- a/spaces/xfys/yolov5_tracking/trackers/strong_sort/deep/models/densenet.py +++ /dev/null @@ -1,380 +0,0 @@ -""" -Code source: https://github.com/pytorch/vision -""" -from __future__ import division, absolute_import -import re -from collections import OrderedDict -import torch -import torch.nn as nn -from torch.nn import functional as F -from torch.utils import model_zoo - -__all__ = [ - 'densenet121', 'densenet169', 'densenet201', 'densenet161', - 'densenet121_fc512' -] - -model_urls = { - 'densenet121': - 'https://download.pytorch.org/models/densenet121-a639ec97.pth', - 'densenet169': - 'https://download.pytorch.org/models/densenet169-b2777c0a.pth', - 'densenet201': - 'https://download.pytorch.org/models/densenet201-c1103571.pth', - 'densenet161': - 'https://download.pytorch.org/models/densenet161-8d451a50.pth', -} - - -class _DenseLayer(nn.Sequential): - - def __init__(self, num_input_features, growth_rate, bn_size, drop_rate): - super(_DenseLayer, self).__init__() - self.add_module('norm1', nn.BatchNorm2d(num_input_features)), - self.add_module('relu1', nn.ReLU(inplace=True)), - self.add_module( - 'conv1', - nn.Conv2d( - num_input_features, - bn_size * growth_rate, - kernel_size=1, - stride=1, - bias=False - ) - ), - self.add_module('norm2', nn.BatchNorm2d(bn_size * growth_rate)), - self.add_module('relu2', nn.ReLU(inplace=True)), - self.add_module( - 'conv2', - nn.Conv2d( - bn_size * growth_rate, - growth_rate, - kernel_size=3, - stride=1, - padding=1, - bias=False - ) - ), - self.drop_rate = drop_rate - - def forward(self, x): - new_features = super(_DenseLayer, self).forward(x) - if self.drop_rate > 0: - new_features = F.dropout( - new_features, p=self.drop_rate, training=self.training - ) - return torch.cat([x, new_features], 1) - - -class _DenseBlock(nn.Sequential): - - def __init__( - self, num_layers, num_input_features, bn_size, growth_rate, drop_rate - ): - super(_DenseBlock, self).__init__() - for i in range(num_layers): - layer = _DenseLayer( - num_input_features + i*growth_rate, growth_rate, bn_size, - drop_rate - ) - self.add_module('denselayer%d' % (i+1), layer) - - -class _Transition(nn.Sequential): - - def __init__(self, num_input_features, num_output_features): - super(_Transition, self).__init__() - self.add_module('norm', nn.BatchNorm2d(num_input_features)) - self.add_module('relu', nn.ReLU(inplace=True)) - self.add_module( - 'conv', - nn.Conv2d( - num_input_features, - num_output_features, - kernel_size=1, - stride=1, - bias=False - ) - ) - self.add_module('pool', nn.AvgPool2d(kernel_size=2, stride=2)) - - -class DenseNet(nn.Module): - """Densely connected network. - - Reference: - Huang et al. Densely Connected Convolutional Networks. CVPR 2017. - - Public keys: - - ``densenet121``: DenseNet121. - - ``densenet169``: DenseNet169. - - ``densenet201``: DenseNet201. - - ``densenet161``: DenseNet161. - - ``densenet121_fc512``: DenseNet121 + FC. - """ - - def __init__( - self, - num_classes, - loss, - growth_rate=32, - block_config=(6, 12, 24, 16), - num_init_features=64, - bn_size=4, - drop_rate=0, - fc_dims=None, - dropout_p=None, - **kwargs - ): - - super(DenseNet, self).__init__() - self.loss = loss - - # First convolution - self.features = nn.Sequential( - OrderedDict( - [ - ( - 'conv0', - nn.Conv2d( - 3, - num_init_features, - kernel_size=7, - stride=2, - padding=3, - bias=False - ) - ), - ('norm0', nn.BatchNorm2d(num_init_features)), - ('relu0', nn.ReLU(inplace=True)), - ( - 'pool0', - nn.MaxPool2d(kernel_size=3, stride=2, padding=1) - ), - ] - ) - ) - - # Each denseblock - num_features = num_init_features - for i, num_layers in enumerate(block_config): - block = _DenseBlock( - num_layers=num_layers, - num_input_features=num_features, - bn_size=bn_size, - growth_rate=growth_rate, - drop_rate=drop_rate - ) - self.features.add_module('denseblock%d' % (i+1), block) - num_features = num_features + num_layers*growth_rate - if i != len(block_config) - 1: - trans = _Transition( - num_input_features=num_features, - num_output_features=num_features // 2 - ) - self.features.add_module('transition%d' % (i+1), trans) - num_features = num_features // 2 - - # Final batch norm - self.features.add_module('norm5', nn.BatchNorm2d(num_features)) - - self.global_avgpool = nn.AdaptiveAvgPool2d(1) - self.feature_dim = num_features - self.fc = self._construct_fc_layer(fc_dims, num_features, dropout_p) - - # Linear layer - self.classifier = nn.Linear(self.feature_dim, num_classes) - - self._init_params() - - def _construct_fc_layer(self, fc_dims, input_dim, dropout_p=None): - """Constructs fully connected layer. - - Args: - fc_dims (list or tuple): dimensions of fc layers, if None, no fc layers are constructed - input_dim (int): input dimension - dropout_p (float): dropout probability, if None, dropout is unused - """ - if fc_dims is None: - self.feature_dim = input_dim - return None - - assert isinstance( - fc_dims, (list, tuple) - ), 'fc_dims must be either list or tuple, but got {}'.format( - type(fc_dims) - ) - - layers = [] - for dim in fc_dims: - layers.append(nn.Linear(input_dim, dim)) - layers.append(nn.BatchNorm1d(dim)) - layers.append(nn.ReLU(inplace=True)) - if dropout_p is not None: - layers.append(nn.Dropout(p=dropout_p)) - input_dim = dim - - self.feature_dim = fc_dims[-1] - - return nn.Sequential(*layers) - - def _init_params(self): - for m in self.modules(): - if isinstance(m, nn.Conv2d): - nn.init.kaiming_normal_( - m.weight, mode='fan_out', nonlinearity='relu' - ) - if m.bias is not None: - nn.init.constant_(m.bias, 0) - elif isinstance(m, nn.BatchNorm2d): - nn.init.constant_(m.weight, 1) - nn.init.constant_(m.bias, 0) - elif isinstance(m, nn.BatchNorm1d): - nn.init.constant_(m.weight, 1) - nn.init.constant_(m.bias, 0) - elif isinstance(m, nn.Linear): - nn.init.normal_(m.weight, 0, 0.01) - if m.bias is not None: - nn.init.constant_(m.bias, 0) - - def forward(self, x): - f = self.features(x) - f = F.relu(f, inplace=True) - v = self.global_avgpool(f) - v = v.view(v.size(0), -1) - - if self.fc is not None: - v = self.fc(v) - - if not self.training: - return v - - y = self.classifier(v) - - if self.loss == 'softmax': - return y - elif self.loss == 'triplet': - return y, v - else: - raise KeyError('Unsupported loss: {}'.format(self.loss)) - - -def init_pretrained_weights(model, model_url): - """Initializes model with pretrained weights. - - Layers that don't match with pretrained layers in name or size are kept unchanged. - """ - pretrain_dict = model_zoo.load_url(model_url) - - # '.'s are no longer allowed in module names, but pervious _DenseLayer - # has keys 'norm.1', 'relu.1', 'conv.1', 'norm.2', 'relu.2', 'conv.2'. - # They are also in the checkpoints in model_urls. This pattern is used - # to find such keys. - pattern = re.compile( - r'^(.*denselayer\d+\.(?:norm|relu|conv))\.((?:[12])\.(?:weight|bias|running_mean|running_var))$' - ) - for key in list(pretrain_dict.keys()): - res = pattern.match(key) - if res: - new_key = res.group(1) + res.group(2) - pretrain_dict[new_key] = pretrain_dict[key] - del pretrain_dict[key] - - model_dict = model.state_dict() - pretrain_dict = { - k: v - for k, v in pretrain_dict.items() - if k in model_dict and model_dict[k].size() == v.size() - } - model_dict.update(pretrain_dict) - model.load_state_dict(model_dict) - - -""" -Dense network configurations: --- -densenet121: num_init_features=64, growth_rate=32, block_config=(6, 12, 24, 16) -densenet169: num_init_features=64, growth_rate=32, block_config=(6, 12, 32, 32) -densenet201: num_init_features=64, growth_rate=32, block_config=(6, 12, 48, 32) -densenet161: num_init_features=96, growth_rate=48, block_config=(6, 12, 36, 24) -""" - - -def densenet121(num_classes, loss='softmax', pretrained=True, **kwargs): - model = DenseNet( - num_classes=num_classes, - loss=loss, - num_init_features=64, - growth_rate=32, - block_config=(6, 12, 24, 16), - fc_dims=None, - dropout_p=None, - **kwargs - ) - if pretrained: - init_pretrained_weights(model, model_urls['densenet121']) - return model - - -def densenet169(num_classes, loss='softmax', pretrained=True, **kwargs): - model = DenseNet( - num_classes=num_classes, - loss=loss, - num_init_features=64, - growth_rate=32, - block_config=(6, 12, 32, 32), - fc_dims=None, - dropout_p=None, - **kwargs - ) - if pretrained: - init_pretrained_weights(model, model_urls['densenet169']) - return model - - -def densenet201(num_classes, loss='softmax', pretrained=True, **kwargs): - model = DenseNet( - num_classes=num_classes, - loss=loss, - num_init_features=64, - growth_rate=32, - block_config=(6, 12, 48, 32), - fc_dims=None, - dropout_p=None, - **kwargs - ) - if pretrained: - init_pretrained_weights(model, model_urls['densenet201']) - return model - - -def densenet161(num_classes, loss='softmax', pretrained=True, **kwargs): - model = DenseNet( - num_classes=num_classes, - loss=loss, - num_init_features=96, - growth_rate=48, - block_config=(6, 12, 36, 24), - fc_dims=None, - dropout_p=None, - **kwargs - ) - if pretrained: - init_pretrained_weights(model, model_urls['densenet161']) - return model - - -def densenet121_fc512(num_classes, loss='softmax', pretrained=True, **kwargs): - model = DenseNet( - num_classes=num_classes, - loss=loss, - num_init_features=64, - growth_rate=32, - block_config=(6, 12, 24, 16), - fc_dims=[512], - dropout_p=None, - **kwargs - ) - if pretrained: - init_pretrained_weights(model, model_urls['densenet121']) - return model diff --git a/spaces/xianbao/sd-to-diffusers/app.py b/spaces/xianbao/sd-to-diffusers/app.py deleted file mode 100644 index e8ce7fc52ff3e6e4ec9fa06b543dbb435e7373c9..0000000000000000000000000000000000000000 --- a/spaces/xianbao/sd-to-diffusers/app.py +++ /dev/null @@ -1,198 +0,0 @@ -import os -import subprocess -from huggingface_hub import HfApi, upload_folder -import gradio as gr -import hf_utils -import utils -from safetensors import safe_open -import torch - -subprocess.run(["git", "clone", "https://github.com/huggingface/diffusers", "diffs"]) - -def error_str(error, title="Error"): - return f"""#### {title} - {error}""" if error else "" - -def on_token_change(token): - model_names, error = hf_utils.get_my_model_names(token) - if model_names: - model_names.append("Other") - - return gr.update(visible=bool(model_names)), gr.update(choices=model_names, value=model_names[0] if model_names else None), gr.update(visible=bool(model_names)), gr.update(value=error_str(error)) - -def url_to_model_id(model_id_str): - return model_id_str.split("/")[-2] + "/" + model_id_str.split("/")[-1] if model_id_str.startswith("https://huggingface.co/") else model_id_str - -def get_ckpt_names(token, radio_model_names, input_model): - - model_id = url_to_model_id(input_model) if radio_model_names == "Other" else radio_model_names - - if token == "" or model_id == "": - return error_str("Please enter both a token and a model name.", title="Invalid input"), gr.update(choices=[]), gr.update(visible=False) - - try: - api = HfApi(token=token) - ckpt_files = [f for f in api.list_repo_files(repo_id=model_id) if f.endswith(".ckpt") or f.endswith(".safetensors")] - - if not ckpt_files: - return error_str("No checkpoint files found in the model repo."), gr.update(choices=[]), gr.update(visible=False) - - return None, gr.update(choices=ckpt_files, value=ckpt_files[0], visible=True), gr.update(visible=True) - - except Exception as e: - return error_str(e), gr.update(choices=[]), None - -def convert_and_push(radio_model_names, input_model, ckpt_name, sd_version, token, path_in_repo, ema, safetensors): - extract_ema = ema == "ema" - - if sd_version == None: - return error_str("You must select a stable diffusion version.", title="Invalid input") - - model_id = url_to_model_id(input_model) if radio_model_names == "Other" else radio_model_names - - try: - model_id = url_to_model_id(model_id) - - # 1. Download the checkpoint file - ckpt_path, revision = hf_utils.download_file(repo_id=model_id, filename=ckpt_name, token=token) - - if safetensors == "yes": - tensors = {} - with safe_open(ckpt_path, framework="pt", device="cpu") as f: - for key in f.keys(): - tensors[key] = f.get_tensor(key) - - new_checkpoint_path = "/".join(ckpt_path.split("/")[:-1] + ["model_safe.ckpt"]) - torch.save(tensors, new_checkpoint_path) - ckpt_path = new_checkpoint_path - print("Converting ckpt_path", ckpt_path) - - print(ckpt_path) - - # 2. Run the conversion script - os.makedirs(model_id, exist_ok=True) - run_command = [ - "python3", - "./diffs/scripts/convert_original_stable_diffusion_to_diffusers.py", - "--checkpoint_path", - ckpt_path, - "--dump_path" , - model_id, - ] - if extract_ema: - run_command.append("--extract_ema") - subprocess.run(run_command) - - # 3. Push to the model repo - commit_message="Add Diffusers weights" - upload_folder( - folder_path=model_id, - repo_id=model_id, - path_in_repo=path_in_repo, - token=token, - create_pr=True, - commit_message=commit_message, - commit_description=f"Add Diffusers weights converted from checkpoint `{ckpt_name}` in revision {revision}", - ) - - # # 4. Delete the downloaded checkpoint file, yaml files, and the converted model folder - hf_utils.delete_file(revision) - subprocess.run(["rm", "-rf", model_id.split('/')[0]]) - import glob - for f in glob.glob("*.yaml*"): - subprocess.run(["rm", "-rf", f]) - - return f"""Successfully converted the checkpoint and opened a PR to add the weights to the model repo. - You can view and merge the PR [here]({hf_utils.get_pr_url(HfApi(token=token), model_id, commit_message)}).""" - - return "Done" - - except Exception as e: - return error_str(e) - - -DESCRIPTION = """### Convert a stable diffusion checkpoint to Diffusers🧨 - With this space, you can easily convert a CompVis stable diffusion checkpoint to Diffusers and automatically create a pull request to the model repo. - You can choose to convert a checkpoint from one of your own models, or from any other model on the Hub. - You can skip the queue by running the app in the colab: [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/gist/qunash/f0f3152c5851c0c477b68b7b98d547fe/convert-sd-to-diffusers.ipynb)""" - -with gr.Blocks() as demo: - - gr.Markdown(DESCRIPTION) - with gr.Row(): - - with gr.Column(scale=11): - with gr.Column(): - gr.Markdown("## 1. Load model info") - input_token = gr.Textbox( - max_lines=1, - type="password", - label="Enter your Hugging Face token", - placeholder="READ permission is sufficient" - ) - gr.Markdown("You can get a token [here](https://huggingface.co/settings/tokens)") - with gr.Group(visible=False) as group_model: - radio_model_names = gr.Radio(label="Choose a model") - input_model = gr.Textbox( - max_lines=1, - label="Model name or URL", - placeholder="username/model_name", - visible=False, - ) - - btn_get_ckpts = gr.Button("Load", visible=False) - - with gr.Column(scale=10): - with gr.Column(visible=False) as group_convert: - gr.Markdown("## 2. Convert to Diffusers🧨") - radio_ckpts = gr.Radio(label="Choose the checkpoint to convert", visible=False) - path_in_repo = gr.Textbox(label="Path where the weights will be saved", placeholder="Leave empty for root folder") - ema = gr.Radio(label="Extract EMA or non-EMA?", choices=["ema", "non-ema"]) - safetensors = gr.Radio(label="Extract from safetensors", choices=["yes", "no"], value="no") - radio_sd_version = gr.Radio(label="Choose the model version", choices=["v1", "v2", "v2.1"]) - gr.Markdown("Conversion may take a few minutes.") - btn_convert = gr.Button("Convert & Push") - - error_output = gr.Markdown(label="Output") - - input_token.change( - fn=on_token_change, - inputs=input_token, - outputs=[group_model, radio_model_names, btn_get_ckpts, error_output], - queue=False, - scroll_to_output=True) - - radio_model_names.change( - lambda x: gr.update(visible=x == "Other"), - inputs=radio_model_names, - outputs=input_model, - queue=False, - scroll_to_output=True) - - btn_get_ckpts.click( - fn=get_ckpt_names, - inputs=[input_token, radio_model_names, input_model], - outputs=[error_output, radio_ckpts, group_convert], - scroll_to_output=True, - queue=False - ) - - btn_convert.click( - fn=convert_and_push, - inputs=[radio_model_names, input_model, radio_ckpts, radio_sd_version, input_token, path_in_repo, ema, safetensors], - outputs=error_output, - scroll_to_output=True - ) - - # gr.Markdown("""""") - gr.HTML(""" -
      -
      -

      Space by: Twitter Follow


      - Buy Me A Coffee

      -

      visitors

      -
      - """) - -demo.queue() -demo.launch(debug=True, share=utils.is_google_colab()) diff --git a/spaces/xiaoxin1111/vits-uma-genshin-honkai/text/symbols.py b/spaces/xiaoxin1111/vits-uma-genshin-honkai/text/symbols.py deleted file mode 100644 index edfbd24247be8c757275ce80b9ec27a0ffa808f3..0000000000000000000000000000000000000000 --- a/spaces/xiaoxin1111/vits-uma-genshin-honkai/text/symbols.py +++ /dev/null @@ -1,39 +0,0 @@ -''' -Defines the set of symbols used in text input to the model. -''' - -'''# japanese_cleaners -_pad = '_' -_punctuation = ',.!?-' -_letters = 'AEINOQUabdefghijkmnoprstuvwyzʃʧ↓↑ ' -''' - -'''# japanese_cleaners2 -_pad = '_' -_punctuation = ',.!?-~…' -_letters = 'AEINOQUabdefghijkmnoprstuvwyzʃʧʦ↓↑ ' -''' - -'''# korean_cleaners -_pad = '_' -_punctuation = ',.!?…~' -_letters = 'ㄱㄴㄷㄹㅁㅂㅅㅇㅈㅊㅋㅌㅍㅎㄲㄸㅃㅆㅉㅏㅓㅗㅜㅡㅣㅐㅔ ' -''' - -'''# chinese_cleaners -_pad = '_' -_punctuation = '，。！？—…' -_letters = 'ㄅㄆㄇㄈㄉㄊㄋㄌㄍㄎㄏㄐㄑㄒㄓㄔㄕㄖㄗㄘㄙㄚㄛㄜㄝㄞㄟㄠㄡㄢㄣㄤㄥㄦㄧㄨㄩˉˊˇˋ˙ ' -''' - -# zh_ja_mixture_cleaners -_pad = '_' -_punctuation = ',.!?-~…' -_letters = 'AEINOQUabdefghijklmnoprstuvwyzʃʧʦɯɹəɥ⁼ʰ`→↓↑ ' - - -# Export all symbols: -symbols = [_pad] + list(_punctuation) + list(_letters) - -# Special symbol ids -SPACE_ID = symbols.index(" ") \ No newline at end of file diff --git a/spaces/xwsm/gpt/crazy_functions/test_project/python/dqn/dqn.py b/spaces/xwsm/gpt/crazy_functions/test_project/python/dqn/dqn.py deleted file mode 100644 index 6cea64d39baa7ff4c1e549869aaa4b0ae17779a9..0000000000000000000000000000000000000000 --- a/spaces/xwsm/gpt/crazy_functions/test_project/python/dqn/dqn.py +++ /dev/null @@ -1,245 +0,0 @@ -from typing import Any, Dict, List, Optional, Tuple, Type, Union - -import gym -import numpy as np -import torch as th -from torch.nn import functional as F - -from stable_baselines3.common import logger -from stable_baselines3.common.off_policy_algorithm import OffPolicyAlgorithm -from stable_baselines3.common.preprocessing import maybe_transpose -from stable_baselines3.common.type_aliases import GymEnv, MaybeCallback, Schedule -from stable_baselines3.common.utils import get_linear_fn, is_vectorized_observation, polyak_update -from stable_baselines3.dqn.policies import DQNPolicy - - -class DQN(OffPolicyAlgorithm): - """ - Deep Q-Network (DQN) - - Paper: https://arxiv.org/abs/1312.5602, https://www.nature.com/articles/nature14236 - Default hyperparameters are taken from the nature paper, - except for the optimizer and learning rate that were taken from Stable Baselines defaults. - - :param policy: The policy model to use (MlpPolicy, CnnPolicy, ...) - :param env: The environment to learn from (if registered in Gym, can be str) - :param learning_rate: The learning rate, it can be a function - of the current progress remaining (from 1 to 0) - :param buffer_size: size of the replay buffer - :param learning_starts: how many steps of the model to collect transitions for before learning starts - :param batch_size: Minibatch size for each gradient update - :param tau: the soft update coefficient ("Polyak update", between 0 and 1) default 1 for hard update - :param gamma: the discount factor - :param train_freq: Update the model every ``train_freq`` steps. Alternatively pass a tuple of frequency and unit - like ``(5, "step")`` or ``(2, "episode")``. - :param gradient_steps: How many gradient steps to do after each rollout (see ``train_freq``) - Set to ``-1`` means to do as many gradient steps as steps done in the environment - during the rollout. - :param optimize_memory_usage: Enable a memory efficient variant of the replay buffer - at a cost of more complexity. - See https://github.com/DLR-RM/stable-baselines3/issues/37#issuecomment-637501195 - :param target_update_interval: update the target network every ``target_update_interval`` - environment steps. - :param exploration_fraction: fraction of entire training period over which the exploration rate is reduced - :param exploration_initial_eps: initial value of random action probability - :param exploration_final_eps: final value of random action probability - :param max_grad_norm: The maximum value for the gradient clipping - :param tensorboard_log: the log location for tensorboard (if None, no logging) - :param create_eval_env: Whether to create a second environment that will be - used for evaluating the agent periodically. (Only available when passing string for the environment) - :param policy_kwargs: additional arguments to be passed to the policy on creation - :param verbose: the verbosity level: 0 no output, 1 info, 2 debug - :param seed: Seed for the pseudo random generators - :param device: Device (cpu, cuda, ...) on which the code should be run. - Setting it to auto, the code will be run on the GPU if possible. - :param _init_setup_model: Whether or not to build the network at the creation of the instance - """ - - def __init__( - self, - policy: Union[str, Type[DQNPolicy]], - env: Union[GymEnv, str], - learning_rate: Union[float, Schedule] = 1e-4, - buffer_size: int = 1000000, - learning_starts: int = 50000, - batch_size: Optional[int] = 32, - tau: float = 1.0, - gamma: float = 0.99, - train_freq: Union[int, Tuple[int, str]] = 4, - gradient_steps: int = 1, - optimize_memory_usage: bool = False, - target_update_interval: int = 10000, - exploration_fraction: float = 0.1, - exploration_initial_eps: float = 1.0, - exploration_final_eps: float = 0.05, - max_grad_norm: float = 10, - tensorboard_log: Optional[str] = None, - create_eval_env: bool = False, - policy_kwargs: Optional[Dict[str, Any]] = None, - verbose: int = 0, - seed: Optional[int] = None, - device: Union[th.device, str] = "auto", - _init_setup_model: bool = True, - ): - - super(DQN, self).__init__( - policy, - env, - DQNPolicy, - learning_rate, - buffer_size, - learning_starts, - batch_size, - tau, - gamma, - train_freq, - gradient_steps, - action_noise=None, # No action noise - policy_kwargs=policy_kwargs, - tensorboard_log=tensorboard_log, - verbose=verbose, - device=device, - create_eval_env=create_eval_env, - seed=seed, - sde_support=False, - optimize_memory_usage=optimize_memory_usage, - supported_action_spaces=(gym.spaces.Discrete,), - ) - - self.exploration_initial_eps = exploration_initial_eps - self.exploration_final_eps = exploration_final_eps - self.exploration_fraction = exploration_fraction - self.target_update_interval = target_update_interval - self.max_grad_norm = max_grad_norm - # "epsilon" for the epsilon-greedy exploration - self.exploration_rate = 0.0 - # Linear schedule will be defined in `_setup_model()` - self.exploration_schedule = None - self.q_net, self.q_net_target = None, None - - if _init_setup_model: - self._setup_model() - - def _setup_model(self) -> None: - super(DQN, self)._setup_model() - self._create_aliases() - self.exploration_schedule = get_linear_fn( - self.exploration_initial_eps, self.exploration_final_eps, self.exploration_fraction - ) - - def _create_aliases(self) -> None: - self.q_net = self.policy.q_net - self.q_net_target = self.policy.q_net_target - - def _on_step(self) -> None: - """ - Update the exploration rate and target network if needed. - This method is called in ``collect_rollouts()`` after each step in the environment. - """ - if self.num_timesteps % self.target_update_interval == 0: - polyak_update(self.q_net.parameters(), self.q_net_target.parameters(), self.tau) - - self.exploration_rate = self.exploration_schedule(self._current_progress_remaining) - logger.record("rollout/exploration rate", self.exploration_rate) - - def train(self, gradient_steps: int, batch_size: int = 100) -> None: - # Update learning rate according to schedule - self._update_learning_rate(self.policy.optimizer) - - losses = [] - for _ in range(gradient_steps): - # Sample replay buffer - replay_data = self.replay_buffer.sample(batch_size, env=self._vec_normalize_env) - - with th.no_grad(): - # Compute the next Q-values using the target network - next_q_values = self.q_net_target(replay_data.next_observations) - # Follow greedy policy: use the one with the highest value - next_q_values, _ = next_q_values.max(dim=1) - # Avoid potential broadcast issue - next_q_values = next_q_values.reshape(-1, 1) - # 1-step TD target - target_q_values = replay_data.rewards + (1 - replay_data.dones) * self.gamma * next_q_values - - # Get current Q-values estimates - current_q_values = self.q_net(replay_data.observations) - - # Retrieve the q-values for the actions from the replay buffer - current_q_values = th.gather(current_q_values, dim=1, index=replay_data.actions.long()) - - # Compute Huber loss (less sensitive to outliers) - loss = F.smooth_l1_loss(current_q_values, target_q_values) - losses.append(loss.item()) - - # Optimize the policy - self.policy.optimizer.zero_grad() - loss.backward() - # Clip gradient norm - th.nn.utils.clip_grad_norm_(self.policy.parameters(), self.max_grad_norm) - self.policy.optimizer.step() - - # Increase update counter - self._n_updates += gradient_steps - - logger.record("train/n_updates", self._n_updates, exclude="tensorboard") - logger.record("train/loss", np.mean(losses)) - - def predict( - self, - observation: np.ndarray, - state: Optional[np.ndarray] = None, - mask: Optional[np.ndarray] = None, - deterministic: bool = False, - ) -> Tuple[np.ndarray, Optional[np.ndarray]]: - """ - Overrides the base_class predict function to include epsilon-greedy exploration. - - :param observation: the input observation - :param state: The last states (can be None, used in recurrent policies) - :param mask: The last masks (can be None, used in recurrent policies) - :param deterministic: Whether or not to return deterministic actions. - :return: the model's action and the next state - (used in recurrent policies) - """ - if not deterministic and np.random.rand() < self.exploration_rate: - if is_vectorized_observation(maybe_transpose(observation, self.observation_space), self.observation_space): - n_batch = observation.shape[0] - action = np.array([self.action_space.sample() for _ in range(n_batch)]) - else: - action = np.array(self.action_space.sample()) - else: - action, state = self.policy.predict(observation, state, mask, deterministic) - return action, state - - def learn( - self, - total_timesteps: int, - callback: MaybeCallback = None, - log_interval: int = 4, - eval_env: Optional[GymEnv] = None, - eval_freq: int = -1, - n_eval_episodes: int = 5, - tb_log_name: str = "DQN", - eval_log_path: Optional[str] = None, - reset_num_timesteps: bool = True, - ) -> OffPolicyAlgorithm: - - return super(DQN, self).learn( - total_timesteps=total_timesteps, - callback=callback, - log_interval=log_interval, - eval_env=eval_env, - eval_freq=eval_freq, - n_eval_episodes=n_eval_episodes, - tb_log_name=tb_log_name, - eval_log_path=eval_log_path, - reset_num_timesteps=reset_num_timesteps, - ) - - def _excluded_save_params(self) -> List[str]: - return super(DQN, self)._excluded_save_params() + ["q_net", "q_net_target"] - - def _get_torch_save_params(self) -> Tuple[List[str], List[str]]: - state_dicts = ["policy", "policy.optimizer"] - - return state_dicts, [] diff --git a/spaces/yderre-aubay/midi-player-demo/src/main/components/PianoRoll/PianoRollCanvas/shaders/NoteShader.ts b/spaces/yderre-aubay/midi-player-demo/src/main/components/PianoRoll/PianoRollCanvas/shaders/NoteShader.ts deleted file mode 100644 index c99698bae687f714eea4eda9230a541b7de625ec..0000000000000000000000000000000000000000 --- a/spaces/yderre-aubay/midi-player-demo/src/main/components/PianoRoll/PianoRollCanvas/shaders/NoteShader.ts +++ /dev/null @@ -1,113 +0,0 @@ -import { - Attrib, - rectToTriangleBounds, - rectToTriangles, - Shader, - uniformMat4, - uniformVec4, -} from "@ryohey/webgl-react" -import { vec4 } from "gl-matrix" -import { IRect } from "../../../../../common/geometry" - -export interface IColorData { - color: vec4 -} - -export class NoteBuffer { - private gl: WebGLRenderingContext - - readonly buffers: { - position: WebGLBuffer - bounds: WebGLBuffer - color: WebGLBuffer - } - - private _vertexCount: number = 0 - - constructor(gl: WebGLRenderingContext) { - this.gl = gl - this.buffers = { - position: gl.createBuffer()!, - bounds: gl.createBuffer()!, - color: gl.createBuffer()!, - } - } - - update(rects: (IRect & IColorData)[]) { - const { gl } = this - const positions = rects.flatMap(rectToTriangles) - gl.bindBuffer(gl.ARRAY_BUFFER, this.buffers.position) - gl.bufferData(gl.ARRAY_BUFFER, new Float32Array(positions), gl.DYNAMIC_DRAW) - - const bounds = rects.flatMap(rectToTriangleBounds) - gl.bindBuffer(gl.ARRAY_BUFFER, this.buffers.bounds) - gl.bufferData(gl.ARRAY_BUFFER, new Float32Array(bounds), gl.DYNAMIC_DRAW) - - const colors = rects.flatMap((obj) => - Array.from(Array(6)).flatMap(() => Array.from(obj.color)), - ) - gl.bindBuffer(gl.ARRAY_BUFFER, this.buffers.color) - gl.bufferData(gl.ARRAY_BUFFER, new Float32Array(colors), gl.DYNAMIC_DRAW) - - this._vertexCount = rects.length * 6 - } - - get vertexCount() { - return this._vertexCount - } -} - -export const NoteShader = (gl: WebGLRenderingContext) => - new Shader( - gl, - ` - precision lowp float; - attribute vec4 aVertexPosition; - - // XYZW -> X, Y, Width, Height - attribute vec4 aBounds; - attribute vec4 aColor; - - uniform mat4 uProjectionMatrix; - varying vec4 vBounds; - varying vec2 vPosition; - varying vec4 vColor; - - void main() { - gl_Position = uProjectionMatrix * aVertexPosition; - vBounds = aBounds; - vPosition = aVertexPosition.xy; - vColor = aColor; - } - `, - ` - precision lowp float; - - uniform vec4 uStrokeColor; - varying vec4 vBounds; - varying vec2 vPosition; - varying vec4 vColor; - - void main() { - float border = 1.0; - float localX = vPosition.x - vBounds.x; - float localY = vPosition.y - vBounds.y; - - if ((localX < border) || (localX >= (vBounds.z - border)) || (localY < border) || (localY > (vBounds.w - border))) { - // draw outline - gl_FragColor = uStrokeColor; - } else { - gl_FragColor = vColor; - } - } - `, - (program) => ({ - position: new Attrib(gl, program, "aVertexPosition", 2), - bounds: new Attrib(gl, program, "aBounds", 4), - color: new Attrib(gl, program, "aColor", 4), - }), - (program) => ({ - projectionMatrix: uniformMat4(gl, program, "uProjectionMatrix"), - strokeColor: uniformVec4(gl, program, "uStrokeColor"), - }), - ) diff --git a/spaces/yderre-aubay/midi-player-demo/src/main/stores/ExportStore.ts b/spaces/yderre-aubay/midi-player-demo/src/main/stores/ExportStore.ts deleted file mode 100644 index 7973c2fdf6a64cb9c45a2f01d598af2354d33804..0000000000000000000000000000000000000000 --- a/spaces/yderre-aubay/midi-player-demo/src/main/stores/ExportStore.ts +++ /dev/null @@ -1,16 +0,0 @@ -import { makeObservable, observable } from "mobx" - -export class ExportStore { - openExportDialog = false - openExportProgressDialog = false - progress = 0 - isCanceled = false - - constructor() { - makeObservable(this, { - openExportDialog: observable, - openExportProgressDialog: observable, - progress: observable, - }) - } -} diff --git a/spaces/ysharma/LLaVA_v1/docs/LLaVA_from_LLaMA2.md b/spaces/ysharma/LLaVA_v1/docs/LLaVA_from_LLaMA2.md deleted file mode 100644 index b4163668a33ff705c28f5b103b727514161e5652..0000000000000000000000000000000000000000 --- a/spaces/ysharma/LLaVA_v1/docs/LLaVA_from_LLaMA2.md +++ /dev/null @@ -1,29 +0,0 @@ -# LLaVA (based on Llama 2 LLM, Preview) - -*NOTE: This is a technical preview. We are still running hyperparameter search, and will release the final model soon. If you'd like to contribute to this, please contact us.* - -:llama: **-Introduction-** [Llama 2 is an open-source LLM released by Meta AI](https://about.fb.com/news/2023/07/llama-2/) today (July 18, 2023). Compared with its early version [Llama 1](https://ai.meta.com/blog/large-language-model-llama-meta-ai/), Llama 2 is more favored in ***stronger language performance***, ***longer context window***, and importantly ***commercially usable***! While Llama 2 is changing the LLM market landscape in the language space, its multimodal ability remains unknown. We quickly develop the LLaVA variant based on the latest Llama 2 checkpoints, and release it to the community for the public use. - -You need to apply for and download the lastest Llama 2 checkpoints to start your own training (apply [here](https://ai.meta.com/resources/models-and-libraries/llama-downloads/)) - - -## Training - -Please checkout [`pretrain.sh`](https://github.com/haotian-liu/LLaVA/blob/main/scripts/pretrain.sh), [`finetune.sh`](https://github.com/haotian-liu/LLaVA/blob/main/scripts/finetune.sh), [`finetune_lora.sh`](https://github.com/haotian-liu/LLaVA/blob/main/scripts/finetune_lora.sh). - -## LLaVA (based on Llama 2), What is different? - -:volcano: How is the new LLaVA based on Llama 2 different from Llama 1? The comparisons of the training process are described: -- **Pre-training**. The pre-trained base LLM is changed from Llama 1 to Llama 2 -- **Language instruction-tuning**. The previous LLaVA model starts with Vicuna, which is instruct tuned on ShareGPT data from Llama 1; The new LLaVA model starts with Llama 2 Chat, which is an instruct tuned checkpoint on dialogue data from Llama 2. -- **Multimodal instruction-tuning**. The same LLaVA-Lighting process is applied. - - -### Results - -- Llama 2 is better at following the instructions of role playing; Llama 2 fails in following the instructions of translation -- The quantitative evaluation on [LLaVA-Bench](https://github.com/haotian-liu/LLaVA/blob/main/docs/LLaVA_Bench.md) demonstrates on-par performance between Llama 2 and Llama 1 in LLaVA's multimodal chat ability. - - - - diff --git a/spaces/ysharma/LLaVA_v1/llava/conversation.py b/spaces/ysharma/LLaVA_v1/llava/conversation.py deleted file mode 100644 index 6ee30cf9942d6f3184e845c0436f5c1d80e00043..0000000000000000000000000000000000000000 --- a/spaces/ysharma/LLaVA_v1/llava/conversation.py +++ /dev/null @@ -1,381 +0,0 @@ -import dataclasses -from enum import auto, Enum -from typing import List, Tuple - - -class SeparatorStyle(Enum): - """Different separator style.""" - SINGLE = auto() - TWO = auto() - MPT = auto() - PLAIN = auto() - LLAMA_2 = auto() - - -@dataclasses.dataclass -class Conversation: - """A class that keeps all conversation history.""" - system: str - roles: List[str] - messages: List[List[str]] - offset: int - sep_style: SeparatorStyle = SeparatorStyle.SINGLE - sep: str = "###" - sep2: str = None - version: str = "Unknown" - - skip_next: bool = False - - def get_prompt(self): - messages = self.messages - if len(messages) > 0 and type(messages[0][1]) is tuple: - messages = self.messages.copy() - init_role, init_msg = messages[0].copy() - init_msg = init_msg[0].replace("", "").strip() - if 'mmtag' in self.version: - messages[0] = (init_role, init_msg) - messages.insert(0, (self.roles[0], "")) - messages.insert(1, (self.roles[1], "Received.")) - else: - messages[0] = (init_role, "\n" + init_msg) - - if self.sep_style == SeparatorStyle.SINGLE: - ret = self.system + self.sep - for role, message in messages: - if message: - if type(message) is tuple: - message, _, _ = message - ret += role + ": " + message + self.sep - else: - ret += role + ":" - elif self.sep_style == SeparatorStyle.TWO: - seps = [self.sep, self.sep2] - ret = self.system + seps[0] - for i, (role, message) in enumerate(messages): - if message: - if type(message) is tuple: - message, _, _ = message - ret += role + ": " + message + seps[i % 2] - else: - ret += role + ":" - elif self.sep_style == SeparatorStyle.MPT: - ret = self.system + self.sep - for role, message in messages: - if message: - if type(message) is tuple: - message, _, _ = message - ret += role + message + self.sep - else: - ret += role - elif self.sep_style == SeparatorStyle.LLAMA_2: - wrap_sys = lambda msg: f"<>\n{msg}\n<>\n\n" - wrap_inst = lambda msg: f"[INST] {msg} [/INST]" - ret = "" - - for i, (role, message) in enumerate(messages): - if i == 0: - assert message, "first message should not be none" - assert role == self.roles[0], "first message should come from user" - if message: - if type(message) is tuple: - message, _, _ = message - if i == 0: message = wrap_sys(self.system) + message - if i % 2 == 0: - message = wrap_inst(message) - ret += self.sep + message - else: - ret += " " + message + " " + self.sep2 - else: - ret += "" - ret = ret.lstrip(self.sep) - elif self.sep_style == SeparatorStyle.PLAIN: - seps = [self.sep, self.sep2] - ret = self.system - for i, (role, message) in enumerate(messages): - if message: - if type(message) is tuple: - message, _, _ = message - ret += message + seps[i % 2] - else: - ret += "" - else: - raise ValueError(f"Invalid style: {self.sep_style}") - - return ret - - def append_message(self, role, message): - self.messages.append([role, message]) - - def get_images(self, return_pil=False): - images = [] - for i, (role, msg) in enumerate(self.messages[self.offset:]): - if i % 2 == 0: - if type(msg) is tuple: - import base64 - from io import BytesIO - from PIL import Image - msg, image, image_process_mode = msg - if image_process_mode == "Pad": - def expand2square(pil_img, background_color=(122, 116, 104)): - width, height = pil_img.size - if width == height: - return pil_img - elif width > height: - result = Image.new(pil_img.mode, (width, width), background_color) - result.paste(pil_img, (0, (width - height) // 2)) - return result - else: - result = Image.new(pil_img.mode, (height, height), background_color) - result.paste(pil_img, ((height - width) // 2, 0)) - return result - image = expand2square(image) - elif image_process_mode in ["Default", "Crop"]: - pass - elif image_process_mode == "Resize": - image = image.resize((336, 336)) - else: - raise ValueError(f"Invalid image_process_mode: {image_process_mode}") - max_hw, min_hw = max(image.size), min(image.size) - aspect_ratio = max_hw / min_hw - max_len, min_len = 800, 400 - shortest_edge = int(min(max_len / aspect_ratio, min_len, min_hw)) - longest_edge = int(shortest_edge * aspect_ratio) - W, H = image.size - if longest_edge != max(image.size): - if H > W: - H, W = longest_edge, shortest_edge - else: - H, W = shortest_edge, longest_edge - image = image.resize((W, H)) - if return_pil: - images.append(image) - else: - buffered = BytesIO() - image.save(buffered, format="PNG") - img_b64_str = base64.b64encode(buffered.getvalue()).decode() - images.append(img_b64_str) - return images - - def to_gradio_chatbot(self): - ret = [] - for i, (role, msg) in enumerate(self.messages[self.offset:]): - if i % 2 == 0: - if type(msg) is tuple: - import base64 - from io import BytesIO - msg, image, image_process_mode = msg - max_hw, min_hw = max(image.size), min(image.size) - aspect_ratio = max_hw / min_hw - max_len, min_len = 800, 400 - shortest_edge = int(min(max_len / aspect_ratio, min_len, min_hw)) - longest_edge = int(shortest_edge * aspect_ratio) - W, H = image.size - if H > W: - H, W = longest_edge, shortest_edge - else: - H, W = shortest_edge, longest_edge - image = image.resize((W, H)) - buffered = BytesIO() - image.save(buffered, format="JPEG") - img_b64_str = base64.b64encode(buffered.getvalue()).decode() - img_str = f'user upload image' - msg = img_str + msg.replace('', '').strip() - ret.append([msg, None]) - else: - ret.append([msg, None]) - else: - ret[-1][-1] = msg - return ret - - def copy(self): - return Conversation( - system=self.system, - roles=self.roles, - messages=[[x, y] for x, y in self.messages], - offset=self.offset, - sep_style=self.sep_style, - sep=self.sep, - sep2=self.sep2, - version=self.version) - - def dict(self): - if len(self.get_images()) > 0: - return { - "system": self.system, - "roles": self.roles, - "messages": [[x, y[0] if type(y) is tuple else y] for x, y in self.messages], - "offset": self.offset, - "sep": self.sep, - "sep2": self.sep2, - } - return { - "system": self.system, - "roles": self.roles, - "messages": self.messages, - "offset": self.offset, - "sep": self.sep, - "sep2": self.sep2, - } - - -conv_vicuna_v0 = Conversation( - system="A chat between a curious human and an artificial intelligence assistant. " - "The assistant gives helpful, detailed, and polite answers to the human's questions.", - roles=("Human", "Assistant"), - messages=( - ("Human", "What are the key differences between renewable and non-renewable energy sources?"), - ("Assistant", - "Renewable energy sources are those that can be replenished naturally in a relatively " - "short amount of time, such as solar, wind, hydro, geothermal, and biomass. " - "Non-renewable energy sources, on the other hand, are finite and will eventually be " - "depleted, such as coal, oil, and natural gas. Here are some key differences between " - "renewable and non-renewable energy sources:\n" - "1. Availability: Renewable energy sources are virtually inexhaustible, while non-renewable " - "energy sources are finite and will eventually run out.\n" - "2. Environmental impact: Renewable energy sources have a much lower environmental impact " - "than non-renewable sources, which can lead to air and water pollution, greenhouse gas emissions, " - "and other negative effects.\n" - "3. Cost: Renewable energy sources can be more expensive to initially set up, but they typically " - "have lower operational costs than non-renewable sources.\n" - "4. Reliability: Renewable energy sources are often more reliable and can be used in more remote " - "locations than non-renewable sources.\n" - "5. Flexibility: Renewable energy sources are often more flexible and can be adapted to different " - "situations and needs, while non-renewable sources are more rigid and inflexible.\n" - "6. Sustainability: Renewable energy sources are more sustainable over the long term, while " - "non-renewable sources are not, and their depletion can lead to economic and social instability.\n") - ), - offset=2, - sep_style=SeparatorStyle.SINGLE, - sep="###", -) - -conv_vicuna_v1 = Conversation( - system="A chat between a curious user and an artificial intelligence assistant. " - "The assistant gives helpful, detailed, and polite answers to the user's questions.", - roles=("USER", "ASSISTANT"), - version="v1", - messages=(), - offset=0, - sep_style=SeparatorStyle.TWO, - sep=" ", - sep2="", -) - -conv_llama_2 = Conversation( - system="""You are a helpful, respectful and honest assistant. Always answer as helpfully as possible, while being safe. Your answers should not include any harmful, unethical, racist, sexist, toxic, dangerous, or illegal content. Please ensure that your responses are socially unbiased and positive in nature. - -If a question does not make any sense, or is not factually coherent, explain why instead of answering something not correct. If you don't know the answer to a question, please don't share false information.""", - roles=("USER", "ASSISTANT"), - version="llama_v2", - messages=(), - offset=0, - sep_style=SeparatorStyle.LLAMA_2, - sep="", - sep2="", -) - -conv_llava_llama_2 = Conversation( - system="You are a helpful language and vision assistant. " - "You are able to understand the visual content that the user provides, " - "and assist the user with a variety of tasks using natural language.", - roles=("USER", "ASSISTANT"), - version="llama_v2", - messages=(), - offset=0, - sep_style=SeparatorStyle.LLAMA_2, - sep="", - sep2="", -) - -conv_mpt = Conversation( - system="""<|im_start|>system -A conversation between a user and an LLM-based AI assistant. The assistant gives helpful and honest answers.""", - roles=("<|im_start|>user\n", "<|im_start|>assistant\n"), - version="mpt", - messages=(), - offset=0, - sep_style=SeparatorStyle.MPT, - sep="<|im_end|>", -) - -conv_llava_plain = Conversation( - system="", - roles=("", ""), - messages=( - ), - offset=0, - sep_style=SeparatorStyle.PLAIN, - sep="\n", -) - -conv_llava_v0 = Conversation( - system="A chat between a curious human and an artificial intelligence assistant. " - "The assistant gives helpful, detailed, and polite answers to the human's questions.", - roles=("Human", "Assistant"), - messages=( - ), - offset=0, - sep_style=SeparatorStyle.SINGLE, - sep="###", -) - -conv_llava_v0_mmtag = Conversation( - system="A chat between a curious user and an artificial intelligence assistant. " - "The assistant is able to understand the visual content that the user provides, and assist the user with a variety of tasks using natural language." - "The visual content will be provided with the following format: visual content.", - roles=("Human", "Assistant"), - messages=( - ), - offset=0, - sep_style=SeparatorStyle.SINGLE, - sep="###", - version="v0_mmtag", -) - -conv_llava_v1 = Conversation( - system="A chat between a curious human and an artificial intelligence assistant. " - "The assistant gives helpful, detailed, and polite answers to the human's questions.", - roles=("USER", "ASSISTANT"), - version="v1", - messages=(), - offset=0, - sep_style=SeparatorStyle.TWO, - sep=" ", - sep2="", -) - -conv_llava_v1_mmtag = Conversation( - system="A chat between a curious user and an artificial intelligence assistant. " - "The assistant is able to understand the visual content that the user provides, and assist the user with a variety of tasks using natural language." - "The visual content will be provided with the following format: visual content.", - roles=("USER", "ASSISTANT"), - messages=(), - offset=0, - sep_style=SeparatorStyle.TWO, - sep=" ", - sep2="", - version="v1_mmtag", -) - -default_conversation = conv_vicuna_v0 -conv_templates = { - "default": conv_vicuna_v0, - "v0": conv_vicuna_v0, - "v1": conv_vicuna_v1, - "vicuna_v1": conv_vicuna_v1, - "llama_2": conv_llama_2, - - "plain": conv_llava_plain, - "v0_plain": conv_llava_plain, - "llava_v0": conv_llava_v0, - "v0_mmtag": conv_llava_v0_mmtag, - "llava_v1": conv_llava_v1, - "v1_mmtag": conv_llava_v1_mmtag, - "llava_llama_2": conv_llava_llama_2, - - "mpt": conv_mpt, -} - - -if __name__ == "__main__": - print(default_conversation.get_prompt()) diff --git a/spaces/yzha/ctc_eval/README.md b/spaces/yzha/ctc_eval/README.md deleted file mode 100644 index 2bcbeb94888bb74c07c2136e04e95cbb6d2fe79b..0000000000000000000000000000000000000000 --- a/spaces/yzha/ctc_eval/README.md +++ /dev/null @@ -1,51 +0,0 @@ ---- -title: CTC_Eval -datasets: -- -tags: -- evaluate -- metric -description: "This repo contains code of an automatic evaluation metric described in the paper -Compression, Transduction, and Creation: A Unified Framework for Evaluating Natural Language Generation" -sdk: gradio -sdk_version: 3.0.2 -app_file: app.py -pinned: false ---- - -# Metric Card for CTC_Eval - -## Metric Description -* Previous work on NLG evaluation has typically focused on a single task and developed individual evaluation metrics based on specific intuitions. -* In this work, we propose a unifying perspective based on the nature of information change in NLG tasks, including compression (e.g., summarization), transduction (e.g., text rewriting), and creation (e.g., dialog). -* A common concept underlying the three broad categories is information alignment, which we define as the extent to which the information in one generation component is grounded in another. -* We adopt contextualized language models to measure information alignment. - -## How to Use -Example: -```python - - >>> ctc_score = evaluate.load("yzha/ctc_eval") - >>> results = ctc_score.compute(references=['hello world'], predictions='hi world') - >>> print(results) - {'ctc_score': 0.5211202502250671} -``` - -### Inputs -- **input_field** - - `references`: The document contains all the information - - `predictions`: NLG model generated text - -### Output Values - -The CTC Score. - -## Citation -@inproceedings{deng2021compression, - title={Compression, Transduction, and Creation: A Unified Framework for Evaluating Natural Language Generation}, - author={Deng, Mingkai and Tan, Bowen and Liu, Zhengzhong and Xing, Eric and Hu, Zhiting}, - booktitle={Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing}, - pages={7580--7605}, - year={2021} -} - diff --git a/spaces/zhang-wei-jian/docker/node_modules/deep-equal/test/cmp.js b/spaces/zhang-wei-jian/docker/node_modules/deep-equal/test/cmp.js deleted file mode 100644 index 2aab5f9642e1988dc5252951805538b39569c4b4..0000000000000000000000000000000000000000 --- a/spaces/zhang-wei-jian/docker/node_modules/deep-equal/test/cmp.js +++ /dev/null @@ -1,95 +0,0 @@ -var test = require('tape'); -var equal = require('../'); -var isArguments = require('../lib/is_arguments.js'); -var objectKeys = require('../lib/keys.js'); - -test('equal', function (t) { - t.ok(equal( - { a : [ 2, 3 ], b : [ 4 ] }, - { a : [ 2, 3 ], b : [ 4 ] } - )); - t.end(); -}); - -test('not equal', function (t) { - t.notOk(equal( - { x : 5, y : [6] }, - { x : 5, y : 6 } - )); - t.end(); -}); - -test('nested nulls', function (t) { - t.ok(equal([ null, null, null ], [ null, null, null ])); - t.end(); -}); - -test('strict equal', function (t) { - t.notOk(equal( - [ { a: 3 }, { b: 4 } ], - [ { a: '3' }, { b: '4' } ], - { strict: true } - )); - t.end(); -}); - -test('non-objects', function (t) { - t.ok(equal(3, 3)); - t.ok(equal('beep', 'beep')); - t.ok(equal('3', 3)); - t.notOk(equal('3', 3, { strict: true })); - t.notOk(equal('3', [3])); - t.end(); -}); - -test('arguments class', function (t) { - t.ok(equal( - (function(){return arguments})(1,2,3), - (function(){return arguments})(1,2,3), - "compares arguments" - )); - t.notOk(equal( - (function(){return arguments})(1,2,3), - [1,2,3], - "differenciates array and arguments" - )); - t.end(); -}); - -test('test the arguments shim', function (t) { - t.ok(isArguments.supported((function(){return arguments})())); - t.notOk(isArguments.supported([1,2,3])); - - t.ok(isArguments.unsupported((function(){return arguments})())); - t.notOk(isArguments.unsupported([1,2,3])); - - t.end(); -}); - -test('test the keys shim', function (t) { - t.deepEqual(objectKeys.shim({ a: 1, b : 2 }), [ 'a', 'b' ]); - t.end(); -}); - -test('dates', function (t) { - var d0 = new Date(1387585278000); - var d1 = new Date('Fri Dec 20 2013 16:21:18 GMT-0800 (PST)'); - t.ok(equal(d0, d1)); - t.end(); -}); - -test('buffers', function (t) { - t.ok(equal(Buffer('xyz'), Buffer('xyz'))); - t.end(); -}); - -test('booleans and arrays', function (t) { - t.notOk(equal(true, [])); - t.end(); -}) - -test('null == undefined', function (t) { - t.ok(equal(null, undefined)) - t.notOk(equal(null, undefined, { strict: true })) - t.end() -}) diff --git a/spaces/zlc99/M4Singer/usr/__init__.py b/spaces/zlc99/M4Singer/usr/__init__.py deleted file mode 100644 index e69de29bb2d1d6434b8b29ae775ad8c2e48c5391..0000000000000000000000000000000000000000 diff --git a/spaces/zomehwh/bert_vits2/attentions.py b/spaces/zomehwh/bert_vits2/attentions.py deleted file mode 100644 index 3ba2407267ecd425d2095a6428015b5b4ebc0bda..0000000000000000000000000000000000000000 --- a/spaces/zomehwh/bert_vits2/attentions.py +++ /dev/null @@ -1,464 +0,0 @@ -import math -import torch -from torch import nn -from torch.nn import functional as F - -import commons -import logging - -logger = logging.getLogger(__name__) - - -class LayerNorm(nn.Module): - def __init__(self, channels, eps=1e-5): - super().__init__() - self.channels = channels - self.eps = eps - - self.gamma = nn.Parameter(torch.ones(channels)) - self.beta = nn.Parameter(torch.zeros(channels)) - - def forward(self, x): - x = x.transpose(1, -1) - x = F.layer_norm(x, (self.channels,), self.gamma, self.beta, self.eps) - return x.transpose(1, -1) - - -@torch.jit.script -def fused_add_tanh_sigmoid_multiply(input_a, input_b, n_channels): - n_channels_int = n_channels[0] - in_act = input_a + input_b - t_act = torch.tanh(in_act[:, :n_channels_int, :]) - s_act = torch.sigmoid(in_act[:, n_channels_int:, :]) - acts = t_act * s_act - return acts - - -class Encoder(nn.Module): - def __init__( - self, - hidden_channels, - filter_channels, - n_heads, - n_layers, - kernel_size=1, - p_dropout=0.0, - window_size=4, - isflow=True, - **kwargs - ): - super().__init__() - self.hidden_channels = hidden_channels - self.filter_channels = filter_channels - self.n_heads = n_heads - self.n_layers = n_layers - self.kernel_size = kernel_size - self.p_dropout = p_dropout - self.window_size = window_size - # if isflow: - # cond_layer = torch.nn.Conv1d(256, 2*hidden_channels*n_layers, 1) - # self.cond_pre = torch.nn.Conv1d(hidden_channels, 2*hidden_channels, 1) - # self.cond_layer = weight_norm(cond_layer, name='weight') - # self.gin_channels = 256 - self.cond_layer_idx = self.n_layers - if "gin_channels" in kwargs: - self.gin_channels = kwargs["gin_channels"] - if self.gin_channels != 0: - self.spk_emb_linear = nn.Linear(self.gin_channels, self.hidden_channels) - # vits2 says 3rd block, so idx is 2 by default - self.cond_layer_idx = ( - kwargs["cond_layer_idx"] if "cond_layer_idx" in kwargs else 2 - ) - logging.debug(self.gin_channels, self.cond_layer_idx) - assert ( - self.cond_layer_idx < self.n_layers - ), "cond_layer_idx should be less than n_layers" - self.drop = nn.Dropout(p_dropout) - self.attn_layers = nn.ModuleList() - self.norm_layers_1 = nn.ModuleList() - self.ffn_layers = nn.ModuleList() - self.norm_layers_2 = nn.ModuleList() - for i in range(self.n_layers): - self.attn_layers.append( - MultiHeadAttention( - hidden_channels, - hidden_channels, - n_heads, - p_dropout=p_dropout, - window_size=window_size, - ) - ) - self.norm_layers_1.append(LayerNorm(hidden_channels)) - self.ffn_layers.append( - FFN( - hidden_channels, - hidden_channels, - filter_channels, - kernel_size, - p_dropout=p_dropout, - ) - ) - self.norm_layers_2.append(LayerNorm(hidden_channels)) - - def forward(self, x, x_mask, g=None): - attn_mask = x_mask.unsqueeze(2) * x_mask.unsqueeze(-1) - x = x * x_mask - for i in range(self.n_layers): - if i == self.cond_layer_idx and g is not None: - g = self.spk_emb_linear(g.transpose(1, 2)) - g = g.transpose(1, 2) - x = x + g - x = x * x_mask - y = self.attn_layers[i](x, x, attn_mask) - y = self.drop(y) - x = self.norm_layers_1[i](x + y) - - y = self.ffn_layers[i](x, x_mask) - y = self.drop(y) - x = self.norm_layers_2[i](x + y) - x = x * x_mask - return x - - -class Decoder(nn.Module): - def __init__( - self, - hidden_channels, - filter_channels, - n_heads, - n_layers, - kernel_size=1, - p_dropout=0.0, - proximal_bias=False, - proximal_init=True, - **kwargs - ): - super().__init__() - self.hidden_channels = hidden_channels - self.filter_channels = filter_channels - self.n_heads = n_heads - self.n_layers = n_layers - self.kernel_size = kernel_size - self.p_dropout = p_dropout - self.proximal_bias = proximal_bias - self.proximal_init = proximal_init - - self.drop = nn.Dropout(p_dropout) - self.self_attn_layers = nn.ModuleList() - self.norm_layers_0 = nn.ModuleList() - self.encdec_attn_layers = nn.ModuleList() - self.norm_layers_1 = nn.ModuleList() - self.ffn_layers = nn.ModuleList() - self.norm_layers_2 = nn.ModuleList() - for i in range(self.n_layers): - self.self_attn_layers.append( - MultiHeadAttention( - hidden_channels, - hidden_channels, - n_heads, - p_dropout=p_dropout, - proximal_bias=proximal_bias, - proximal_init=proximal_init, - ) - ) - self.norm_layers_0.append(LayerNorm(hidden_channels)) - self.encdec_attn_layers.append( - MultiHeadAttention( - hidden_channels, hidden_channels, n_heads, p_dropout=p_dropout - ) - ) - self.norm_layers_1.append(LayerNorm(hidden_channels)) - self.ffn_layers.append( - FFN( - hidden_channels, - hidden_channels, - filter_channels, - kernel_size, - p_dropout=p_dropout, - causal=True, - ) - ) - self.norm_layers_2.append(LayerNorm(hidden_channels)) - - def forward(self, x, x_mask, h, h_mask): - """ - x: decoder input - h: encoder output - """ - self_attn_mask = commons.subsequent_mask(x_mask.size(2)).to( - device=x.device, dtype=x.dtype - ) - encdec_attn_mask = h_mask.unsqueeze(2) * x_mask.unsqueeze(-1) - x = x * x_mask - for i in range(self.n_layers): - y = self.self_attn_layers[i](x, x, self_attn_mask) - y = self.drop(y) - x = self.norm_layers_0[i](x + y) - - y = self.encdec_attn_layers[i](x, h, encdec_attn_mask) - y = self.drop(y) - x = self.norm_layers_1[i](x + y) - - y = self.ffn_layers[i](x, x_mask) - y = self.drop(y) - x = self.norm_layers_2[i](x + y) - x = x * x_mask - return x - - -class MultiHeadAttention(nn.Module): - def __init__( - self, - channels, - out_channels, - n_heads, - p_dropout=0.0, - window_size=None, - heads_share=True, - block_length=None, - proximal_bias=False, - proximal_init=False, - ): - super().__init__() - assert channels % n_heads == 0 - - self.channels = channels - self.out_channels = out_channels - self.n_heads = n_heads - self.p_dropout = p_dropout - self.window_size = window_size - self.heads_share = heads_share - self.block_length = block_length - self.proximal_bias = proximal_bias - self.proximal_init = proximal_init - self.attn = None - - self.k_channels = channels // n_heads - self.conv_q = nn.Conv1d(channels, channels, 1) - self.conv_k = nn.Conv1d(channels, channels, 1) - self.conv_v = nn.Conv1d(channels, channels, 1) - self.conv_o = nn.Conv1d(channels, out_channels, 1) - self.drop = nn.Dropout(p_dropout) - - if window_size is not None: - n_heads_rel = 1 if heads_share else n_heads - rel_stddev = self.k_channels**-0.5 - self.emb_rel_k = nn.Parameter( - torch.randn(n_heads_rel, window_size * 2 + 1, self.k_channels) - * rel_stddev - ) - self.emb_rel_v = nn.Parameter( - torch.randn(n_heads_rel, window_size * 2 + 1, self.k_channels) - * rel_stddev - ) - - nn.init.xavier_uniform_(self.conv_q.weight) - nn.init.xavier_uniform_(self.conv_k.weight) - nn.init.xavier_uniform_(self.conv_v.weight) - if proximal_init: - with torch.no_grad(): - self.conv_k.weight.copy_(self.conv_q.weight) - self.conv_k.bias.copy_(self.conv_q.bias) - - def forward(self, x, c, attn_mask=None): - q = self.conv_q(x) - k = self.conv_k(c) - v = self.conv_v(c) - - x, self.attn = self.attention(q, k, v, mask=attn_mask) - - x = self.conv_o(x) - return x - - def attention(self, query, key, value, mask=None): - # reshape [b, d, t] -> [b, n_h, t, d_k] - b, d, t_s, t_t = (*key.size(), query.size(2)) - query = query.view(b, self.n_heads, self.k_channels, t_t).transpose(2, 3) - key = key.view(b, self.n_heads, self.k_channels, t_s).transpose(2, 3) - value = value.view(b, self.n_heads, self.k_channels, t_s).transpose(2, 3) - - scores = torch.matmul(query / math.sqrt(self.k_channels), key.transpose(-2, -1)) - if self.window_size is not None: - assert ( - t_s == t_t - ), "Relative attention is only available for self-attention." - key_relative_embeddings = self._get_relative_embeddings(self.emb_rel_k, t_s) - rel_logits = self._matmul_with_relative_keys( - query / math.sqrt(self.k_channels), key_relative_embeddings - ) - scores_local = self._relative_position_to_absolute_position(rel_logits) - scores = scores + scores_local - if self.proximal_bias: - assert t_s == t_t, "Proximal bias is only available for self-attention." - scores = scores + self._attention_bias_proximal(t_s).to( - device=scores.device, dtype=scores.dtype - ) - if mask is not None: - scores = scores.masked_fill(mask == 0, -1e4) - if self.block_length is not None: - assert ( - t_s == t_t - ), "Local attention is only available for self-attention." - block_mask = ( - torch.ones_like(scores) - .triu(-self.block_length) - .tril(self.block_length) - ) - scores = scores.masked_fill(block_mask == 0, -1e4) - p_attn = F.softmax(scores, dim=-1) # [b, n_h, t_t, t_s] - p_attn = self.drop(p_attn) - output = torch.matmul(p_attn, value) - if self.window_size is not None: - relative_weights = self._absolute_position_to_relative_position(p_attn) - value_relative_embeddings = self._get_relative_embeddings( - self.emb_rel_v, t_s - ) - output = output + self._matmul_with_relative_values( - relative_weights, value_relative_embeddings - ) - output = ( - output.transpose(2, 3).contiguous().view(b, d, t_t) - ) # [b, n_h, t_t, d_k] -> [b, d, t_t] - return output, p_attn - - def _matmul_with_relative_values(self, x, y): - """ - x: [b, h, l, m] - y: [h or 1, m, d] - ret: [b, h, l, d] - """ - ret = torch.matmul(x, y.unsqueeze(0)) - return ret - - def _matmul_with_relative_keys(self, x, y): - """ - x: [b, h, l, d] - y: [h or 1, m, d] - ret: [b, h, l, m] - """ - ret = torch.matmul(x, y.unsqueeze(0).transpose(-2, -1)) - return ret - - def _get_relative_embeddings(self, relative_embeddings, length): - 2 * self.window_size + 1 - # Pad first before slice to avoid using cond ops. - pad_length = max(length - (self.window_size + 1), 0) - slice_start_position = max((self.window_size + 1) - length, 0) - slice_end_position = slice_start_position + 2 * length - 1 - if pad_length > 0: - padded_relative_embeddings = F.pad( - relative_embeddings, - commons.convert_pad_shape([[0, 0], [pad_length, pad_length], [0, 0]]), - ) - else: - padded_relative_embeddings = relative_embeddings - used_relative_embeddings = padded_relative_embeddings[ - :, slice_start_position:slice_end_position - ] - return used_relative_embeddings - - def _relative_position_to_absolute_position(self, x): - """ - x: [b, h, l, 2*l-1] - ret: [b, h, l, l] - """ - batch, heads, length, _ = x.size() - # Concat columns of pad to shift from relative to absolute indexing. - x = F.pad(x, commons.convert_pad_shape([[0, 0], [0, 0], [0, 0], [0, 1]])) - - # Concat extra elements so to add up to shape (len+1, 2*len-1). - x_flat = x.view([batch, heads, length * 2 * length]) - x_flat = F.pad( - x_flat, commons.convert_pad_shape([[0, 0], [0, 0], [0, length - 1]]) - ) - - # Reshape and slice out the padded elements. - x_final = x_flat.view([batch, heads, length + 1, 2 * length - 1])[ - :, :, :length, length - 1 : - ] - return x_final - - def _absolute_position_to_relative_position(self, x): - """ - x: [b, h, l, l] - ret: [b, h, l, 2*l-1] - """ - batch, heads, length, _ = x.size() - # pad along column - x = F.pad( - x, commons.convert_pad_shape([[0, 0], [0, 0], [0, 0], [0, length - 1]]) - ) - x_flat = x.view([batch, heads, length**2 + length * (length - 1)]) - # add 0's in the beginning that will skew the elements after reshape - x_flat = F.pad(x_flat, commons.convert_pad_shape([[0, 0], [0, 0], [length, 0]])) - x_final = x_flat.view([batch, heads, length, 2 * length])[:, :, :, 1:] - return x_final - - def _attention_bias_proximal(self, length): - """Bias for self-attention to encourage attention to close positions. - Args: - length: an integer scalar. - Returns: - a Tensor with shape [1, 1, length, length] - """ - r = torch.arange(length, dtype=torch.float32) - diff = torch.unsqueeze(r, 0) - torch.unsqueeze(r, 1) - return torch.unsqueeze(torch.unsqueeze(-torch.log1p(torch.abs(diff)), 0), 0) - - -class FFN(nn.Module): - def __init__( - self, - in_channels, - out_channels, - filter_channels, - kernel_size, - p_dropout=0.0, - activation=None, - causal=False, - ): - super().__init__() - self.in_channels = in_channels - self.out_channels = out_channels - self.filter_channels = filter_channels - self.kernel_size = kernel_size - self.p_dropout = p_dropout - self.activation = activation - self.causal = causal - - if causal: - self.padding = self._causal_padding - else: - self.padding = self._same_padding - - self.conv_1 = nn.Conv1d(in_channels, filter_channels, kernel_size) - self.conv_2 = nn.Conv1d(filter_channels, out_channels, kernel_size) - self.drop = nn.Dropout(p_dropout) - - def forward(self, x, x_mask): - x = self.conv_1(self.padding(x * x_mask)) - if self.activation == "gelu": - x = x * torch.sigmoid(1.702 * x) - else: - x = torch.relu(x) - x = self.drop(x) - x = self.conv_2(self.padding(x * x_mask)) - return x * x_mask - - def _causal_padding(self, x): - if self.kernel_size == 1: - return x - pad_l = self.kernel_size - 1 - pad_r = 0 - padding = [[0, 0], [0, 0], [pad_l, pad_r]] - x = F.pad(x, commons.convert_pad_shape(padding)) - return x - - def _same_padding(self, x): - if self.kernel_size == 1: - return x - pad_l = (self.kernel_size - 1) // 2 - pad_r = self.kernel_size // 2 - padding = [[0, 0], [0, 0], [pad_l, pad_r]] - x = F.pad(x, commons.convert_pad_shape(padding)) - return x