# Spatio-Temporal Graph Convolutional Networks
[![issues](https://img.shields.io/github/issues/hazdzz/STGCN)](https://github.com/hazdzz/STGCN/issues)
[![forks](https://img.shields.io/github/forks/hazdzz/STGCN)](https://github.com/hazdzz/STGCN/network/members)
[![stars](https://img.shields.io/github/stars/hazdzz/STGCN)](https://github.com/hazdzz/STGCN/stargazers)
[![License](https://img.shields.io/github/license/hazdzz/STGCN)](./LICENSE)
## About
The PyTorch implementation of STGCN was implemented for the paper titled *Spatio-Temporal Graph Convolutional Networks:
A Deep Learning Framework for Traffic Forecasting*.
## Paper
https://arxiv.org/abs/1709.04875
## Citation
```
@inproceedings{10.5555/3304222.3304273,
author = {Yu, Bing and Yin, Haoteng and Zhu, Zhanxing},
title = {Spatio-Temporal Graph Convolutional Networks: A Deep Learning Framework for Traffic Forecasting},
year = {2018},
isbn = {9780999241127},
publisher = {AAAI Press},
booktitle = {Proceedings of the 27th International Joint Conference on Artificial Intelligence},
pages = {3634–3640},
numpages = {7},
series = {IJCAI'18}
}
```
## Related works
1. TCN: [*An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modeling*](https://arxiv.org/abs/1803.01271)
2. GLU and GTU: [*Language Modeling with Gated Convolutional Networks*](https://arxiv.org/abs/1612.08083)
3. ChebNet: [*Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering*](https://arxiv.org/abs/1606.09375)
4. GCN: [*Semi-Supervised Classification with Graph Convolutional Networks*](https://arxiv.org/abs/1609.02907)
## Related code
1. TCN: https://github.com/locuslab/TCN
2. ChebNet: https://github.com/mdeff/cnn_graph
3. GCN: https://github.com/tkipf/pygcn
## Dataset
### Source
1. METR-LA: [DCRNN author's Google Drive](https://drive.google.com/file/d/1pAGRfzMx6K9WWsfDcD1NMbIif0T0saFC/view?usp=sharing)
2. PEMS-BAY: [DCRNN author's Google Drive](https://drive.google.com/file/d/1wD-mHlqAb2mtHOe_68fZvDh1LpDegMMq/view?usp=sharing)
3. PeMSD7(M): [STGCN author's GitHub repository](https://github.com/VeritasYin/STGCN_IJCAI-18/blob/master/data_loader/PeMS-M.zip)
### Preprocessing
Using the formula from [ChebNet](https://arxiv.org/abs/1606.09375):
<img src="./figure/weighted_adjacency_matrix.png" style="zoom:100%" />
## Model structure
<img src="./figure/stgcn_model_structure.png" style="zoom:100%" />
## Differents of code between mine and author's
1. Fix bugs
2. Add Early Stopping approach
3. Add Dropout approach
4. Offer a different set of hyperparameters
5. Offer config files for two different categories graph convolution (ChebyGraphConv and GraphConv)
6. Add datasets METR-LA and PEMS-BAY
7. Adopt a different data preprocessing method
## Requirements
To install requirements:
```console
pip3 install -r requirements.txt
```
The PyTorch implementation of STGCN.STGCN-main.zip
需积分: 5 91 浏览量
2024-05-22
07:52:00
上传
评论
收藏 40.94MB ZIP 举报
![avatar](https://profile-avatar.csdnimg.cn/d229e61f6bf0440280908180a7424584_mrluo735.jpg!1)
流华追梦
- 粉丝: 5611
- 资源: 2507
最新资源
- 【后端开发框架】教程&案例&相关项目
- setup asdfasfd
- 信号与系统、数字信号处理、通信原理等课程内容及相关实验项目
- 简鹿视频格式转换器 1.0 离线包.zip
- 《javascript网页编程》项目考试要求.doc
- 基于python实现的机器学习算法
- yolov8实战第十天-pyqt5-yolov8实现数据结构化、yolov8目标跟踪、过线检测计数系统(参考论文完整部署代码)
- C# opencvsharp对Mat数据进行序列化或者反序列化以及格式化输出演示源码.7z
- 主机性能指标采集器,感兴趣的运维小伙伴们可以下载试试
- 计算机网络和现代通信组网是信息科学和电子工程领域的重要分支,涉及大量的理论知识和实践技能 以下是一些学习资源和项目思路,可以帮助
资源上传下载、课程学习等过程中有任何疑问或建议,欢迎提出宝贵意见哦~我们会及时处理!
点击此处反馈
![feedback](https://img-home.csdnimg.cn/images/20220527035711.png)
![feedback](https://img-home.csdnimg.cn/images/20220527035711.png)
![feedback-tip](https://img-home.csdnimg.cn/images/20220527035111.png)