# st-gcn-1
**Repository Path**: milo7hao/st-gcn-1
## Basic Information
- **Project Name**: st-gcn-1
- **Description**: ST-GCN-5-25
- **Primary Language**: Unknown
- **License**: BSD-2-Clause
- **Default Branch**: master
- **Homepage**: None
- **GVP Project**: No
## Statistics
- **Stars**: 0
- **Forks**: 0
- **Created**: 2020-08-10
- **Last Updated**: 2020-12-19
## Categories & Tags
**Categories**: Uncategorized
**Tags**: None
## README
# Spatial Temporal Graph Convolutional Networks (ST-GCN)
A graph convolutional network for skeleton based action recognition.
This repository holds the codebase, dataset and models for the paper>
**Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognition** Sijie Yan, Yuanjun Xiong and Dahua Lin, AAAI 2018.
[[Arxiv Preprint]](https://arxiv.org/abs/1801.07455)
## News & Updates
- Feb. 21, 2019 - We provide pretrained models and training scripts on **NTU-RGB+D** and **kinetics-skeleton** datasets. So that you can achieve the performance we mentioned in the paper.
- June. 5, 2018 - A demo for feature visualization and skeleton based action recognition is released.
- June. 1, 2018 - We update our code base and complete the PyTorch 0.4.0 migration.
## Visulization of ST-GCN in Action
Our demo for skeleton based action recognition:
ST-GCN is able to exploit local pattern and correlation from human skeletons.
Below figures show the neural response magnitude of each node in the last layer of our ST-GCN.
 |
 |
 |
 |
 |
| Touch head |
Sitting down |
Take off a shoe |
Eat meal/snack |
Kick other person |
 |
 |
 |
 |
 |
| Hammer throw |
Clean and jerk |
Pull ups |
Tai chi |
Juggling ball |
The first row of above results is from **NTU-RGB+D** dataset, and the second row is from **Kinetics-skeleton**.
## Prerequisites
Our codebase is based on **Python3** (>=3.5). There are a few dependencies to run the code. The major libraries we depend are
- [PyTorch](http://pytorch.org/) (Release version 0.4.0)
- [Openpose@92cdcad](https://github.com/yysijie/openpose) (Optional: for demo only)
- FFmpeg (Optional: for demo only), which can be installed by `sudo apt-get install ffmpeg`
- Other Python libraries can be installed by `pip install -r requirements.txt`
### Installation
```
cd torchlight; python setup.py install; cd ..
```
### Get pretrained models
We provided the pretrained model weithts of our **ST-GCN**. The model weights can be downloaded by running the script
```
bash tools/get_models.sh
```
You can also obtain models from [GoogleDrive](https://drive.google.com/drive/folders/1IYKoSrjeI3yYJ9bO0_z_eDo92i7ob_aF) or [BaiduYun](https://pan.baidu.com/s/1dwKG2TLvG-R1qeIiE4MjeA#list/path=%2FShare%2FAAAI18%2Fst-gcn%2Fmodels&parentPath=%2FShare), and manually put them into ```./models```.
## Demo
To visualize how ST-GCN exploit local correlation and local pattern, we compute the feature vector magnitude of each node in the final spatial temporal graph, and overlay them on the original video. **Openpose** should be ready for extracting human skeletons from videos. The skeleton based action recognition results is also shwon thereon.
Run the demo by this command:
```
python main.py demo --openpose [--video --device ]
```
A video as above will be generated and saved under ```data/demo_result/```.
## Data Preparation
We experimented on two skeleton-based action recognition datasts: **Kinetics-skeleton** and **NTU RGB+D**.
### Kinetics-skeleton
[Kinetics](https://deepmind.com/research/open-source/open-source-datasets/kinetics/) is a video-based dataset for action recognition which only provide raw video clips without skeleton data. Kinetics dataset include To obatin the joint locations, we first resized all videos to the resolution of 340x256 and converted the frame rate to 30 fps. Then, we extracted skeletons from each frame in Kinetics by [Openpose](https://github.com/CMU-Perceptual-Computing-Lab/openpose). The extracted skeleton data we called **Kinetics-skeleton**(7.5GB) can be directly downloaded from [GoogleDrive](https://drive.google.com/open?id=1SPQ6FmFsjGg3f59uCWfdUWI-5HJM_YhZ) or [BaiduYun](https://pan.baidu.com/s/1dwKG2TLvG-R1qeIiE4MjeA#list/path=%2FShare%2FAAAI18%2Fkinetics-skeleton&parentPath=%2FShare).
After uncompressing, rebuild the database by this command:
```
python tools/kinetics_gendata.py --data_path
```
### NTU RGB+D
NTU RGB+D can be downloaded from [their website](http://rose1.ntu.edu.sg/datasets/actionrecognition.asp).
Only the **3D skeletons**(5.8GB) modality is required in our experiments. After that, this command should be used to build the database for training or evaluation:
```
python tools/ntu_gendata.py --data_path
```
where the `````` points to the 3D skeletons modality of NTU RGB+D dataset you download.
## Testing Pretrained Models
To evaluate ST-GCN model pretrained on **Kinetcis-skeleton**, run
```
python main.py recognition -c config/st_gcn/kinetics-skeleton/test.yaml
```
For **cross-view** evaluation in **NTU RGB+D**, run
```
python main.py recognition -c config/st_gcn/ntu-xview/test.yaml
```
For **cross-subject** evaluation in **NTU RGB+D**, run
```
python main.py recognition -c config/st_gcn/ntu-xsub/test.yaml
```
To speed up evaluation by multi-gpu inference or modify batch size for reducing the memory cost, set ```--test_batch_size``` and ```--device``` like:
```
python main.py recognition -c --test_batch_size --device ...
```
### Results
The expected **Top-1** **accuracy** of provided models are shown here:
| Model| Kinetics-
skeleton (%)|NTU RGB+D
Cross View (%) |NTU RGB+D
Cross Subject (%) |
| :------| :------: | :------: | :------: |
|Baseline[1]| 20.3 | 83.1 | 74.3 |
|**ST-GCN** (Ours)| **31.6**| **88.8** | **81.6** |
[1] Kim, T. S., and Reiter, A. 2017. Interpretable 3d human action analysis with temporal convolutional networks. In BNMW CVPRW.
## Training
To train a new ST-GCN model, run
```
python main.py recognition -c config/st_gcn//train.yaml [--work_dir ]
```
where the `````` must be ```ntu-xsub```, ```ntu-xview``` or ```kinetics-skeleton```, depending on the dataset you want to use.
The training results, including **model weights**, configurations and logging files, will be saved under the ```./work_dir``` by default or `````` if you appoint it.
You can modify the training parameters such as ```work_dir```, ```batch_size```, ```step```, ```base_lr``` and ```device``` in the command line or configuration files. The order of priority is: command line > config file > default parameter. For more information, use ```main.py -h```.
Finally, custom model evaluation can be achieved by this command as we mentioned above:
```
python main.py recognition -c config/st_gcn//test.yaml --weights
```
## Citation
Please cite the following paper if you use this repository in your reseach.
```
@inproceedings{stgcn2018aaai,
title = {Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognition},
author = {Sijie Yan and Yuanjun Xiong and Dahua Lin},
booktitle = {AAAI},
year = {2018},
}
```
## Contact
For any question, feel free to contact
```
Sijie Yan : ys016@ie.cuhk.edu.hk
Yuanjun Xiong : bitxiong@gmail.com
```