Face API with Docker, Tensorflow and PyTorch.
- Face Detection - TensorFlow (SSD-Mobilenet)
- Facial Emotion Recognition - PyTorch (Resnet50)
- Age and Gender Estimation - Keras (WideResnet)
- Facial Recognition - PyTorch (VGGFace2)
- Docker with Nvidia Support Nvidia-Docker
- CUDA 9 Guide
Make sure the models and images are inside their respective folders.
Build and run the Dockers in parallel:
bash runmodels.sh
Stop Docker containers:
bash stopmodels.sh
Test the APIs by running:
python test_api.py
This demo calls the API to make predictions using the webcam.
To run the demo use:
python demo.py