Human Pose Estimation with TensorFlow

这是pose-tensorflow的注释加强版，便于自己理解用，此外还添加了一些好用的功能

欢迎提问题一起讨论，下面给出作者的信息

Here you can find the implementation of the CNN-based human body part detectors,
presented in the DeeperCut paper:

Eldar Insafutdinov, Leonid Pishchulin, Bjoern Andres, Mykhaylo Andriluka, and Bernt Schiele
DeeperCut: A Deeper, Stronger, and Faster Multi-Person Pose Estimation Model
In European Conference on Computer Vision (ECCV), 2016
For more information visit http://pose.mpi-inf.mpg.de

Python 3 is required to run this code.
First of all, you should install TensorFlow as described in the
official documentation.
We recommended to use virtualenv.

You will also need to install the following Python packages:

$ pip install scipy scikit-image matplotlib pyyaml easydict

When running training or prediction scripts, please make sure to set the environment variable
TF_CUDNN_USE_AUTOTUNE to 0 (see this ticket
for explanation).

If your machine has multiple GPUs, you can select which GPU you want to run on
by setting the environment variable, eg. CUDA_VISIBLE_DEVICES=0.

Demo code

# 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

Training models

Please follow these instructions

Citation

Please cite Deep(er)Cut in your publications if it helps your research:

@article{insafutdinov2016deepercut,
    author = {Eldar Insafutdinov and Leonid Pishchulin and Bjoern Andres and Mykhaylo Andriluka and Bernt Schiele},
    url = {http://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}
}