Wanli
Re-quantify some models from per_channel mode to per_tensor mode (#90)
2965475
|
raw
history blame
1.12 kB

Hand pose estimation from MediaPipe Handpose

This model estimates 21 hand keypoints per detected hand from palm detector. (The image below is referenced from MediaPipe Hands Keypoints)

MediaPipe Hands Keypoints

This model is converted from Tensorflow-JS to ONNX using following tools:

Demo

Run the following commands to try the demo:

# detect on camera input
python demo.py
# detect on an image
python demo.py -i /path/to/image

Example outputs

webcam demo

License

All files in this directory are licensed under Apache 2.0 License.

Reference