JoshuaPeddle commited on
Commit
b9d0fcc
·
1 Parent(s): 5ec100d

Fix readme

Browse files
Files changed (1) hide show
  1. README.md +11 -60
README.md CHANGED
@@ -1,60 +1,11 @@
1
- # Image Transfer and Upscaling API
2
- This service provides APIs to perform image upscaling and style transfer (Monet style) using Machine Learning models. The project is built using Flask, a lightweight WSGI web application framework.
3
-
4
-
5
- ```bash
6
- git clone <repository-url>
7
- cd <project-directory>
8
- Install the dependencies using pip.
9
- ```
10
- ```bash
11
- pip install -r requirements.txt
12
- ```
13
- ## Running the Application
14
- Run the application with the following command:
15
-
16
- ```bash
17
- python3 -m flask run --host=0.0.0.0
18
- ```
19
- The application should start and be accessible at localhost:5000.
20
-
21
- ## API Endpoints
22
- The application exposes two API endpoints:
23
-
24
- ```/monet```: POST endpoint which accepts an image file and returns the image stylized in the style of Monet paintings.
25
-
26
- ```/upscale```: POST endpoint which accepts an image file and returns the upscaled version of the image.
27
- #File Structure
28
- ```app.py```: This is the main application file which runs the Flask application and defines the API endpoints.
29
- ```models/models.py```: This file contains the model loading and prediction functions.
30
- ## models/models.py
31
- ```tensor_to_image(tensor)```: Converts a TensorFlow tensor to an image and saves it to 'upscaled_image.jpg'.
32
-
33
- ```request_to_image(request)```: Converts a Flask request object containing an image to a numpy array.
34
-
35
- ```_monet(image, upscale=False)```: Accepts an image as input and returns the image stylized in the style of Monet paintings.
36
-
37
- ```_upscale(image)```: Accepts an image as input and returns the upscaled version of the image.
38
- ## Sending Requests to the API
39
- For both endpoints, the image file should be included in the request as form data with the key 'image'. Here is an example using curl:
40
-
41
- ```bash
42
- Copy code
43
- curl -X POST -F "image=@<image-file-path>" http://localhost:5000/monet
44
- ```
45
- ```bash
46
- Copy code
47
- curl -X POST -F "image=@<image-file-path>" http://localhost:5000/upscale
48
- Replace <image-file-path> with the path to your image file.
49
- ```
50
- ## Notes
51
- The model files for the Monet style transfer (models/monet_generator) are not included in this repository. You need to download them separately and place them in the correct location.
52
- Contributing
53
- Pull requests are welcome. For major changes, please open an issue first to discuss what you would like to change.
54
-
55
- ## License
56
- MIT
57
-
58
- docker buildx build --platform linux/amd64,linux/arm64 -t joshuapeddle/imagetransfer-server:0.0.2 --push .
59
-
60
- docker run -p 5000:5000 joshuapeddle/imagetransfer-server:0.0.2
 
1
+ ---
2
+ title: ImageTransfer Server
3
+ emoji: 🐠
4
+ colorFrom: indigo
5
+ colorTo: indigo
6
+ sdk: docker
7
+ pinned: false
8
+ license: openrail
9
+ ---
10
+
11
+ Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference