https://github.com/1adrianb/binary-human-pose-estimation
This code implements a demo of the Binarized Convolutional Landmark Localizers for Human Pose Estimation and Face Alignment with Limited Resources paper by Adrian Bulat and Georgios Tzimiropoulos.
https://github.com/1adrianb/binary-human-pose-estimation
binary computer-vision deep-learning human-pose-estimation network-binarization torch7
Last synced: 7 months ago
JSON representation
This code implements a demo of the Binarized Convolutional Landmark Localizers for Human Pose Estimation and Face Alignment with Limited Resources paper by Adrian Bulat and Georgios Tzimiropoulos.
- Host: GitHub
- URL: https://github.com/1adrianb/binary-human-pose-estimation
- Owner: 1adrianb
- License: other
- Created: 2017-01-09T16:50:03.000Z (about 9 years ago)
- Default Branch: master
- Last Pushed: 2021-04-27T17:33:28.000Z (almost 5 years ago)
- Last Synced: 2025-03-31T03:09:15.182Z (11 months ago)
- Topics: binary, computer-vision, deep-learning, human-pose-estimation, network-binarization, torch7
- Language: Lua
- Homepage: https://www.adrianbulat.com/binary-human-pose-estimation
- Size: 17.6 KB
- Stars: 212
- Watchers: 19
- Forks: 69
- Open Issues: 7
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# Binarized Convolutional Landmark Localizers for Human Pose Estimation and Face Alignment with Limited Resources
This code implements a demo of the Binarized Convolutional Landmark Localizers for Human Pose Estimation and Face Alignment with Limited Resources paper by Adrian Bulat and Georgios Tzimiropoulos.
**[2021 Update]: PyTorch repo with training code for BNN available here: [https://github.com/1adrianb/binary-networks-pytorch](https://github.com/1adrianb/binary-networks-pytorch)**
**For the Face Alignment demo please check: [https://github.com/1adrianb/binary-face-alignment](https://github.com/1adrianb/binary-face-alignment)**
## Requirements
- Install the latest [Torch7](http://torch.ch/docs/getting-started.html) version (for Windows, please follow the instructions avaialable [here](https://github.com/torch/distro/blob/master/win-files/README.md))
### Packages
- [cutorch](https://github.com/torch/cutorch)
- [nn](https://github.com/torch/nn)
- [cudnn](https://github.com/soumith/cudnn.torch) (cudnn5 preffered)
- [xlua](https://github.com/torch/xlua)
- [image](https://github.com/torch/image)
- [gnuplot](https://github.com/torch/gnuplot)
- [cURL](https://github.com/Lua-cURL/Lua-cURLv3)
- [paths](https://github.com/torch/paths)
## Setup
Clone the github repository
```bash
git clone https://github.com/1adrianb/binary-human-pose-estimation --recursive
cd binary-human-pose-estimation
```
Build and install the BinaryConvolution package
```bash
cd bnn.torch/; luarocks make; cd ..;
```
Install the modified optnet package
```bash
cd optimize-net/; luarocks make rocks/optnet-scm-1.rockspec; cd ..;
```
Run the following command to prepare the files required by the demo. This will download 10 images from the MPII dataset alongside the dataset structure converted to .t7
```bash
th download-content.lua
```
Download the model available bellow and place it in the models folder.
## Usage
In order to run the demo simply type:
```bash
th main.lua
```
## Pretrained models
| Layer type | Model Size | MPII error |
| ------------- | ----------- | ----------- |
| [MPII](https://www.adrianbulat.com/downloads/BinaryHumanPose/human_pose_binary.t7) | 1.3MB |76.0 |
Note: More pretrained models will be added soon
## Notes
For more details/questions please visit the [project page](https://www.adrianbulat.com/binary-cnn-landmarks) or send an email at adrian.bulat@nottingham.ac.uk