The Pytoch implementation of ``Hybrid Directional Graph Neural Network with Learnable Equivariance''. This code is based on OCP. The solutions of issues on installation or dataset may be found in OCP benchmark.
See installation instructions.
Dataset download links and instructions are in DATASET.md.
To train a HDGNN model for the IS2RE task, run:
python -u -m torch.distributed.launch --nproc_per_node=8 main.py --distributed --num-gpus 8 --mode train --config-yml configs/is2re/all/hdgnn.yml
Next, run this model on the test data:
python main.py --mode predict --config-yml configs/is2re/all/hdgnn.yml \
--checkpoint checkpoints/[TIMESTAMP]/checkpoint.pt