WavGCRN

This is the origin Pytorch implementation of WavGCRN together with baselines in DGCRN the following paper: Qipeng Qian, Tanwi Mallick, "Wavelet-Inspired Multiscale Graph Convolutional Recurrent Network for Traffic Forecasting".

Figure 1. Structure of WavGCRN.

Requirements

• Python 3.6
• numpy == 1.19.4
• pandas == 1.1.1
• torch >= 1.1
• mxnet == 1.4.1
• tensorflow >= 2.4.0

Data

• The description of METR-LA dataset and PEMS_BAY dataset please refers to the repository of DCRNN.

Usage

Commands for training model:

python train_WavGCRN.py --model 'model_name' --data 'data_name' >> log.txt 

More parameter information can be found in train_benchmark.py or the file in the directory of corrsponding model. You can refer to these parameters for experiments, and you can also adjust the parameters to obtain better results.

Results

Figure 2. Results of WavGCRN.