Skip to content

Latest commit

 

History

History
49 lines (34 loc) · 2.08 KB

README.md

File metadata and controls

49 lines (34 loc) · 2.08 KB

Multi-correlation Synchronous Graph Attention Networks for Traffic Prediction

Data

  1. Download from:
  2. Unzip and move to ./data/

Usage

  1. Create directories:

    mkdir -p checkpoints/pems{d3,d4,d7,d8,-bay}
  2. Train on a single GPU:

    # PEMSD4
    python3 ./main.py --data data/pemsd4/pemsd4.npz --adj data/pemsd4/pemsd4.csv \
        --checkpoints checkpoints/pemsd4 --nodes 307 --channels 3 --batch 64 \
        --workers 4 --gpu 0
  3. Train on multiple GPUs:

    # PEMSD4
    python3 ./main.py --data data/pemsd4/pemsd4.npz --adj data/pemsd4/pemsd4.csv \
        --checkpoints checkpoints/pemsd4 --nodes 307 --channels 3 --batch 64 \
        --workers 4 --gpus 0,1,2,3

Paper

Citation

...

Checkpoints

  • PEMSD3, 2080TI-11G:
  • PEMSD4, 2080TI-11G:
  • PEMSD7, 2080TI-11G:
  • PEMSD8, 2080TI-11G: