Skip to content
forked from LeiBAI/AGCRN

Adaptive Graph Convolutional Recurrent Network

Notifications You must be signed in to change notification settings

sanzgadea/AGCRN

 
 

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

7 Commits
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Adaptive Graph Convolutional Recurrent Network for Traffic Forecasting

This folder concludes the code and data of our AGCRN model: Adaptive Graph Convolutional Recurrent Network for Traffic Forecasting, which has been accepted to NeurIPS 2020.

Structure:

  • data: including PEMSD4 and PEMSD8 dataset used in our experiments, which are released by and available at ASTGCN.

  • lib: contains self-defined modules for our work, such as data loading, data pre-process, normalization, and evaluate metrics.

  • model: implementation of our AGCRN model

Requirements

Python 3.6.5, Pytorch 1.1.0, Numpy 1.16.3, argparse and configparser

To replicate the results in PEMSD4 and PEMSD8 datasets, you can run the the codes in the "model" folder directly. If you want to use the model for your own datasets, please load your dataset by revising "load_dataset" in the "lib" folder and remember tuning the learning rate (gradient norm can be used to facilitate the training).

Please cite our work if you find useful.

About

Adaptive Graph Convolutional Recurrent Network

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • Python 100.0%