Skip to content

ksmdnl/clrs

 
 

Repository files navigation

Towards Principled Graph Transformers (CLRS-30)

Code to reproduce our results on CLRS-30.

Install

We recommend to use the package manager conda. Once installed run

conda create -n towards-principled-gts python=3.10

conda activate towards-principled-gts

Install all dependencies via:

pip install -e .

Configuration

By default, logging with wandb is disabled. To enable it set --wandb_project in the command line. Optionally, set --wandb_entity and --wandb_name to configure your entity and run name, respectively.

Experiments

To benchmark the ET on e.g., Dijkstra, run

python -m clrs.examples.run --algorithms dijkstra

CLRS-30 Benchmark

For more detailed explanation about the benchmark refer to clrs repository and the CLRS Paper.

About

No description, website, or topics provided.

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • Python 100.0%