Skip to content
forked from luokn/ms-gat

Multi-relational Graph Attention Networks for Traffic Interaction Modeling and Prediction

License

Notifications You must be signed in to change notification settings

pursuer0123/ms-gat

 
 

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

99 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

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:

About

Multi-relational Graph Attention Networks for Traffic Interaction Modeling and Prediction

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • Python 100.0%