This repository implements a demo of the Human pose estimation via Convolutional Part Heatmap Regression paper.
Lua
Switch branches/tags
Nothing to show
Clone or download
1adrianb Fixed broken link
Thanks FuTao for reporting it
Latest commit 7ad7aa3 Nov 10, 2017
Permalink
Failed to load latest commit information.
.gitignore Initial commit, added the demo Sep 8, 2016
LICENCE Create LICENCE Apr 8, 2017
README.md Update README.md Mar 9, 2017
data.lua Fixed broken link Nov 10, 2017
main.lua Update main.lua Oct 14, 2016
options.lua Update options.lua Oct 14, 2016
transform.lua Fixed a typo Sep 8, 2016

README.md

Human pose estimation via Convolutional Part Heatmap Regression

This repository implements a demo of the Human pose estimation via Convolutional Part Heatmap Regression paper Bulat&Tzimiropoulos.

Note: New code capable of running on devices with limited resources, for Human Pose Estimation and Face Alignment was released. For a demo please check: https://github.com/1adrianb/binary-human-pose-estimation

Requirement

  • Install the latest Torch version
  • Install python 2.7 using the package manager

Torch packages

Most of the listed package can be installed by simple running

luarocks install [packagename]

For sh and fb.python packages please visit their github repositories and carrefully follow the instruction provided by their authors.

Python packages

Trained models

By default, on the first run the scripts will attempt to automatically download the models, however for your convinience they are provided also for separate usage.

Dataset used LSP error MPII error
MPII - 89.7
MPII + LSP 90.7 -

Usage

The provided code comes along with a series of options. In order to list them please run:

th main.lua --help

To run a demo on 10 random images:

th main.lua -dataset lsp 

To evaluate the model on the validation set for LSP/MPII:

th main.lua -dataset lsp -eval

If you have installed cudnn4 or cudnn5 you can run the demo faster:

th main.lua -dataset lsp -eval -usecudnn

The demo doesn't require a GPU, however having one will speed up the process.

Notes

For more details/questions please visit the project page or send an email at adrian.bulat@nottingham.ac.uk

Warning: The script will download by default both the models and the dataset(~15Gb), if you wan't to avoid this or you already have them downloaded please move them in the corresponding folders in datasets/[datasetname]_dataset/. Running the demo for lsp dataset will require only ~700Mb of space.