fire717/movenet.pytorch
A Pytorch implementation of MoveNet from Google. Include training code and pre-trained model.
This project helps create custom models that track 17 key points on a human body from images or video frames. You input a dataset of images with labeled body key points, and it outputs a specialized model for pose detection. This is ideal for professionals in fitness, sports analysis, animation, or physical therapy who need tailored body tracking capabilities.
413 stars. No commits in the last 6 months.
Use this if you need to train a fast and accurate body pose detection model using your own specific datasets or if you want to deploy a custom model on CPU-only inference frameworks.
Not ideal if you only need to use Google's pre-trained MoveNet models directly without any customization or if you primarily work within TensorFlow.js or TFLite environments.
Stars
413
Forks
90
Language
Python
License
MIT
Category
Last pushed
Jan 21, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/fire717/movenet.pytorch"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related frameworks
talmolab/sleap
A deep learning framework for multi-animal pose tracking.
kennymckormick/pyskl
A toolbox for skeleton-based action recognition.
open-mmlab/mmaction2
OpenMMLab's Next Generation Video Understanding Toolbox and Benchmark
jgraving/DeepPoseKit
a toolkit for pose estimation using deep learning
kenshohara/3D-ResNets-PyTorch
3D ResNets for Action Recognition (CVPR 2018)