-
You can download mxnet model and parameters(coco and MPII) from google drive:
https://drive.google.com/drive/folders/0BzffphMuhDDMV0RZVGhtQWlmS1U
or check caffe_to_mxnet folder to download original caffe model and transfer it to mxnet model.
-
Test demo based on model of coco dataset: testModel.ipynb
-
Test demo based on model of MPII dataset: testModel_mpi.ipynb
-
Train demo: TrainWeight.py
-
Evaluation on coco validation dataset : evaluation_coco.py
@article{cao2016realtime,
title={Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields},
author={Zhe Cao and Tomas Simon and Shih-En Wei and Yaser Sheikh},
journal={arXiv preprint arXiv:1611.08050},
year={2016}
}
original caffe training https://github.com/CMU-Perceptual-Computing-Lab/caffe_rtpose
- Test demo
- Train demo
- Add image augmentation: rotation, flip
- Add weight vector
- Train all images
- Train from vgg model
- evaluation code
- image read and augmentation in C++
Original caffe training model https://github.com/CMU-Perceptual-Computing-Lab/caffe_rtpose
Original data preparation https://github.com/ZheC/Realtime_Multi-Person_Pose_Estimation
pytorch https://github.com/tensorboy/pytorch_Realtime_Multi-Person_Pose_Estimation
keras https://github.com/raymon-tian/keras_Realtime_Multi-Person_Pose_Estimation