Our GitHub project combines the power of PyTorch, AWS services (Sagemaker, S3, Lambda, and Rest API), and a user-friendly React frontend to tackle the challenge of identifying the most violent segments in a video. By leveraging cutting-edge machine learning techniques and the scalability of Amazon Web Services, our application takes an uploaded video as input and then swiftly processes it to pinpoint the most intense moments of violence.
Starting the backend:
> cd backend
> python3 -m venv venv
> ./venv/Scripts/activate.bat
> pip install -r requirements.txt
> flask run
Starting the frontend
> cd backend
> npm install
> npm run dev