All required Info

read_info.txt

@@ -0,0 +1,36 @@
+# Engagement level detection & Customised Alert System
+
+### Detecting engagement using Yolov5 & responding with an alert message using LLM
+
+By : [Tanishq Selot](https://github.com/tanishq150802)
+
+## Requirements
+* transformers
+* huggingface_hub
+* googletrans==4.0.0-rc1
+* protobuf==3.20
+* torch
+* gradio
+* numpy
+* opencv-python
+* einops
+
+All the Yolov5 fine-tuning code is contained within **Yolov5_finetuning.ipynb**. Image examples can be found below.
+
+### App flow **run.py**
+
+* When the code runs, webcam starts.
+* User can adjust his/her face at the center and press **capture** to capture the image.
+* Yolov5 classifies the image as "looking away", "awake" or "drowsy" & the output is displayed.
+* This response is passed to **https://huggingface.co/microsoft/phi-1_5** LLM endpoint & the alert message is displayed as well.
+
+### Example
+
+Drowsy             |  Looking away |  Awake
+:-------------------------:|:-------------------------: |:-------------------------:
+![image/jpeg](https://cdn-uploads.huggingface.co/production/uploads/649add3c2bcf1c22efa6fe14/_H9QfV4lzThl72QD7rhLt.jpeg) |  ![image/jpeg](https://cdn-uploads.huggingface.co/production/uploads/649add3c2bcf1c22efa6fe14/48SuToqwZuk00Viw-ISOG.jpeg) |  ![image/jpeg](https://cdn-uploads.huggingface.co/production/uploads/649add3c2bcf1c22efa6fe14/Bf9P8IUTCIneqzoaKWdJ4.jpeg)
+
+### References
+
+* [LLM](https://huggingface.co/microsoft/phi-1_5)
+* [Manually annotated data used for finetuning Yolov5](https://app.roboflow.com/indian-institute-of-technology-indore-kbon5/engagement_level/2)