$ pip install scipy scikit-image matplotlib pyyaml easydict

# Download pre-trained model files
cd models/mpii
./download_models.sh
cd -
# Run demo of single person pose estimation
TF_CUDNN_USE_AUTOTUNE=0 python demo/singleperson.py
# Run demo of single person pose estimation for multi-images
TF_CUDNN_USE_AUTOTUNE=0 python demo/singleperson_images.py

export SKELETON2D=~/<path_to_pose-tensorflow>
export POSE_PARAM_PATH=$SKELETON2D
export PATH=$PATH:$SKELETON2D/demo

skeleton2D.py --des /skeleton2D --gpu 0.7

@article{insafutdinov2016deepercut,
    author = {Eldar Insafutdinov and Leonid Pishchulin and Bjoern Andres and Mykhaylo Andriluka and Bernt Schiele},
    url = {https://arxiv.org/abs/1605.03170}
    title = {DeeperCut: A Deeper, Stronger, and Faster Multi-Person Pose Estimation Model},
    year = {2016}
}
@inproceedings{pishchulin16cvpr,
    title = {DeepCut: Joint Subset Partition and Labeling for Multi Person Pose Estimation},
    booktitle = {CVPR'16},
    url = {},
    author = {Leonid Pishchulin and Eldar Insafutdinov and Siyu Tang and Bjoern Andres and Mykhaylo Andriluka and Peter Gehler and Bernt Schiele}
}