# STGCN-pytorch

**Repository Path**: knowledge-precipitation-tribe/STGCN-pytorch

## Basic Information

- **Project Name**: STGCN-pytorch
- **Description**: STGCN-pytorch
- **Primary Language**: Python
- **License**: MIT
- **Default Branch**: master
- **Homepage**: None
- **GVP Project**: No

## Statistics

- **Stars**: 1
- **Forks**: 0
- **Created**: 2020-08-24
- **Last Updated**: 2021-10-25

## Categories & Tags

**Categories**: Uncategorized

**Tags**: None

## README

# STGCN-pytorch
This is a Pytorch implementation of Spatio-Temporal Graph Convolutional Networks(STGCN) model from the paper "[Spatio-Temporal Graph Convolutional Networks: A Deep Learning Framework for Traffic Forecasting](https://arxiv.org/pdf/1709.04875.pdf)"

> **Detailed analysis：[STGCN](https://github.com/Knowledge-Precipitation-Tribe/STGCN-keras/tree/master/ppt)**

## Model architecture

![system_architecture](https://github.com/Knowledge-Precipitation-Tribe/STGCN-keras/blob/master/images/architecture.png)

## Requirements:

- python 3.6
- pytorch 1.3.1

## Usage

```shell
$ python main.py
```

## Code Organization

- code
    - models
    - utils
    - metr_data
    - main.py

## Reference

Yu B, Yin H, Zhu Z. Spatio-temporal graph convolutional networks: A deep learning framework for traffic forecasting[J]. arXiv preprint arXiv:1709.04875, 2017.



## Other implementations

[1] TensorFlow：[VeritasYin](https://github.com/VeritasYin)/**[STGCN_IJCAI-18](https://github.com/VeritasYin/STGCN_IJCAI-18)**

[2] mxnet：[Davidham3](https://github.com/Davidham3)/**[STGCN](https://github.com/Davidham3/STGCN)**