README.md

metadata

license: apache-2.0

DeepLabCut - Human body pose estimation models

This repository contains weights for DeepLabCut [1] PyTorch models for human pose estimation. The following bodyparts are predicted: ["nose", "left_eye", "right_eye", "left_ear", "right_ear", "left_shoulder", "right_shoulder", "left_elbow", "right_elbow", "left_wrist", "right_wrist", "left_hip", "right_hip", "left_knee", "right_knee", "left_ankle", "right_ankle"]

Models

RTMPose

Weights for RTMPose (Real-Time Multi-Person Pose Estimation based on MMPose) [2] are adapted from the snapshots released with the RTMPose models, trained on 7 public human pose estimation benchmarks.

References

1. Alexander Mathis, Pranav Mamidanna, Kevin M. Cury, Taiga Abe, Venkatesh N. Murthy, Mackenzie W. Mathis, Matthias Bethge. DeepLabCut: markerless pose estimation of user-defined body parts with deep learning. In Nature Neuroscience, 21, 1281–1289 (2018).
2. Tao Jiang, Peng Lu, Li Zhang, Ningsheng Ma, Rui Han, Chengqi Lyu, Yining Li, Kai Chen. RTMPose: Real-Time Multi-Person Pose Estimation based on MMPose. ArXiv, abs/2303.07399, 2023.