based on mediapipe human Estimation project for pytorch, provide function(face_mesh,iris,pose,hand)
#搬砖不易,记得star oo~
For work reasons, open source can only go so far
based on https://github.com/zmurez/MediaPipePyTorch
1.1 Face detector (BlazeFace)
1.2 Face landmarks
1.3 Palm detector
1.4 Hand landmarks
1.5 Iris detector
pip -r install requirements
(reference this repo:https://github.com/mmmmmm44/VTuber-Python-Unity)
python demo.py --source sample\tesla.mp4 --detect_face --detect_iris --save_file
python demo.py --source sample\tesla.mp4 --detect_face --connect --debug --port 5066
Recently will first, collate blazeface magic modified SSD training code,waiting~
1. https://github.com/zmurez/MediaPipePyTorch
2. https://github.com/hollance/BlazeFace-PyTorch
3. https://github.com/mmmmmm44/VTuber-Python-Unity