CNN architecture for articulated human pose estimation
C++ Python Cuda CMake Matlab Makefile Other
Switch branches/tags
Nothing to show
Clone or download
Eldar Insafutdinov
Eldar Insafutdinov Fix download locations
Latest commit 928bf2f Oct 27, 2017
Failed to load latest commit information.
cmake Version 1.0.0-rc3 Jan 23, 2016
data Add a -c to wget so that it continues interrupted downloads Nov 7, 2015
docs Make the two separate build systems clearer in the documentation Jan 26, 2016
examples Merge pull request #2917 from ajkl/patch-2 Jan 27, 2016
include/caffe Permute training samples May 24, 2016
matlab show Caffe's version from MatCaffe Jan 23, 2016
models Fix download locations Oct 27, 2017
python improved visualization Jul 1, 2016
scripts fix a bug that time duration may be 0 when downloading model binary Nov 11, 2015
src Fix CPU-only build Oct 18, 2016
tools Nicely prints GPU names Feb 3, 2016
.Doxyfile update doxygen config to stop warnings Sep 3, 2014
.gitignore Update example bash scripts to expect .h5, new extensions in .gitignore Aug 7, 2015
.travis.yml Separate IO dependencies Sep 17, 2015
CMakeLists.txt Version 1.0.0-rc3 Jan 23, 2016 [docs] add which will appear on GitHub new Issue/PR p… Jul 30, 2015 clarify the license and copyright terms of the project Aug 7, 2014 installation questions -> caffe-users Oct 19, 2015
LICENSE copyright 2015 Jun 23, 2015
Makefile Merge pull request #3587 from junshi15/distribute_proto Jan 30, 2016
Makefile.config.example Add makefile config option for linking Python 3 libraries Jan 21, 2016 Download script for models. Updated README. Jun 8, 2016 updated readme Jul 20, 2016
caffe.cloc [fix] stop cloc complaint about cu type Sep 4, 2014

DeeperCut Part Detectors

This short documentation describes steps necessary to compile and run CNN-based 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

Installation Instructions

  • This code was developed under Linux (Debian wheezy, 64 bit) and was tested only in this environment.
  • Build Caffe and Python bindings as described in the official documentation. You will have to disable CuDNN support and enable C++ 11.
$ make all pycaffe
  • Install Python Click package (required for demo only)
$ pip install click
  • Set PYTHONPATH variable
$ export PYTHONPATH=`pwd`/python

Download Caffe Models

$ cd models/deepercut
$ ./

Run Demo

$ cd python/pose
$ python ./ image.png --out_name=prediction


	author = {Eldar Insafutdinov and Leonid Pishchulin and Bjoern Andres and Mykhaylo Andriluka and Bernt Schieke},
	title = {DeeperCut: A Deeper, Stronger, and Faster Multi-Person Pose Estimation Model},
	booktitle = {European Conference on Computer Vision (ECCV)},
	year = {2016},
	url = {}
	author = {Leonid Pishchulin and Eldar Insafutdinov and Siyu Tang and Bjoern Andres and Mykhaylo Andriluka and Peter Gehler and Bernt Schiele},
	title = {DeepCut: Joint Subset Partition and Labeling for Multi Person Pose Estimation},
	booktitle = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
	year = {2016},
	url = {}