PyTorch implementation of the spatio-temporal graph convolutional network proposed in Spatio-Temporal Graph Convolutional Networks: A Deep Learning Framework for Traffic Forecasting by Bing Yu, Haoteng Yin, Zhanxing Zhu. An example for traffic forecasting is included in this repository.

Alternative implementations using other deep learning frameworks can be found here:

• TensorFlow by PKUAI26
• MXNet by Davidham3

• PyTorch
• NumPy
• Matplotlib

The repository provides a usage example on the METR-LA dataset (original version to be found here). Unfortunately, there is no publicly available standard version of the PeMSD dataset used in the paper.