This is a pytorch version of Realtime_Multi-Person_Pose_Estimation, origin code is here https://github.com/ZheC/Realtime_Multi-Person_Pose_Estimation
Code repo for reproducing 2017 CVPR Oral paper using pytorch.
- Pytorch
- Caffe is required if you want convert caffe model to a pytorch model.
- pip install pycocotools
- pip install tensorboardX
- pip install torch-encoding
- Download converted pytorch model.
cd network/caffe_to_pytorch; python convert.py
to convert a trained caffe model to pytorch model. The converted model have relative error less than 1e-6, and will be located in./network/weight
after convert.python demo/picture_demo.py
to run the picture demo.python demo/web_demo.py
to run the web demo.
python evaluate/evaluation.py
cd training; bash getData.sh
to obtain the COCO images indataset/COCO/images/
, keypoints annotations indataset/COCO/annotations/
- Download the mask of the unlabeled person at Dropbox
- Download the official training format at Dropbox
python train.py --batch_size 100 --logdir {where to store tensorboardX logs}
- CVPR'16, Convolutional Pose Machines.
- CVPR'17, Realtime Multi-Person Pose Estimation.
Please cite the paper in your publications if it helps your research:
@InProceedings{cao2017realtime,
title = {Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields},
author = {Zhe Cao and Tomas Simon and Shih-En Wei and Yaser Sheikh},
booktitle = {The IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
year = {2017}
}