Create a python 3.8 environement, eg:
conda create -n pytorch-openpose python=3.8
conda activate pytorch-openpose
Install torch. (We use torch==2.2.0)
pip install torch torchvision
Install other requirements with pip
pip install -r requirements.txt
*.pth files are pytorch model, you could also download caffemodel file if you want to use caffe as backend.
Download the pytorch models and put them in a directory named model in the project root directory
Run:
python UI.py
to process a video file (requires ffmpeg-python).
Because the openpose does't provide the api of identify the specific person, our project cant't tackle the bug due to a new person or a person leave the screen. You can test with the videos we provide in 'data' dir