A pytorch implementation of Traffic Transformer for traffic forecasting.
Thank to the authors of Graph WaveNet and DCRNN. My work stands on their basic code and data.
- python 3
- see
requirements.txt
Step1: Download METR-LA data from Google Drive or Baidu Yun links provided by DCRNN.
# Create data directories
mkdir -p data/{METR-LA}
# METR-LA
python generate_training_data.py --output_dir=data/METR-LA --traffic_df_filename=data/metr-la.h5
python train.py
python test.py