/STGCN-keras

Spatio-Temporal Graph Convolutional Networks: A Deep Learning Framework for Traffic Forecasting implementation with keras

Primary LanguagePythonMIT LicenseMIT

STGCN-keras

This is a Keras implementation of Spatio-Temporal Graph Convolutional Networks(STGCN) model from the paper "Spatio-Temporal Graph Convolutional Networks: A Deep Learning Framework for Traffic Forecasting"

Detailed analysis：STGCN

Model architecture

system_architecture

Requirements:

  • numpy 1.14.2
  • python 3

Usage

$ python main.py

Code Organization

  • 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/STGCN_IJCAI-18

[2] mxnet：Davidham3/STGCN

Follow us

Knowledge-Precipitation-Tribe

qrcode