Skip to content

Readme.md

Latest commit

 

History

History
15 lines (15 loc) · 789 Bytes

Readme.md

File metadata and controls

15 lines (15 loc) · 789 Bytes

Spatial Temporal Net For Traffic Forecasting

A self developed unified training framework for Spatial Temporal Forecasting. It can be used in baseline evaluation and new model development. There are 3 baseline models are included. More models and datasets are in developing progress...

Models included now:

  • FNN
  • Seq2seq with GRU
  • DCRNN (Kernel from [3])

Datasets included now

  • Metr-la

References:

[1]. Yaguang Li, Rose Yu, Cyrus Shahabi, Y. L. (2017). DIFFUSION CONVOLUTIONAL RECURRENT NEURAL NETWORK https://github.com/liyaguang/DCRNN
[2]. Bai, L., Yao, L., Li, C., Wang, X., & Wang, C. (2020). Adaptive Graph Convolutional Recurrent Network for Traffic Forecasting. ArXiv, 1–16. http://arxiv.org/abs/2007.02842
[3]. https://github.com/LeiBAI/DCRNN_Pytorch