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
- Install the latest Torch version
- Install python 2.7 using the package manager
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.
- numpy
- matplotlib - required for plotting
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 | - |
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.
For more details/questions please visit the project page or send an email at [email protected]
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.