-
Clone project
git clone https://github.com/zhengxiangyue/joint_capture.git cd joint_capture
-
Download dataset and model Human36m and put
data
folder injoint_capture
-
Open server
python service.py
-
Open demo in browser
app/index.html
Human3.6M
Pytorch >= 0.3.0
Download the pre-processed Human36m dataset in 3d joints:
unzip human36m.zip
rm h36m.zip
python 3d_pose_detection.py --train
or
python 3d_pose_detection.py --train --resume
python 3d_pose_detection.py --test --load ./checkpoint/best.pth.tar
@inproceedings{martinez_2017_3dbaseline,
title={A simple yet effective baseline for 3d human pose estimation},
author={Martinez, Julieta and Hossain, Rayat and Romero, Javier and Little, James J.},
booktitle={ICCV},
year={2017}
}