Implements the following baselines that take arbitrary chemical structures as input to predict material properties:

• SchNet
• DimeNet
• Crystal Graph Convolutional Neural Networks (CGCNN).

[last updated December 09, 2020]

The easiest way of installing prerequisites is via conda. After installing conda, run the following commands to create a new environment named ocp-models and install dependencies:

Install conda-merge:

pip install conda-merge

If you're using system pip, then you may want to add the --user flag to avoid using sudo. Check that you can invoke conda-merge by running conda-merge -h.

Instructions are for PyTorch 1.6, CUDA 10.1 specifically.

First, check that CUDA is in your PATH and LD_LIBRARY_PATH, e.g.

$echo $PATH | tr ':' '\n' | grep cuda
/public/apps/cuda/10.1/bin
$echo $LD_LIBRARY_PATH | tr ':' '\n' | grep cuda
/public/apps/cuda/10.1/lib64

The exact paths may differ on your system. Then install the dependencies:

conda-merge env.common.yml env.gpu.yml > env.yml
conda env create -f env.yml

Activate the conda environment with conda activate ocp-models. Install this package with pip install -e .. Finally, install the pre-commit hooks:

pre-commit install

Please skip the following if you completed the with-GPU installation from above.

conda-merge env.common.yml env.cpu.yml > env.yml
conda env create -f env.yml
conda activate ocp-models
pip install -e .
pre-commit install

The project website is opencatalystproject.org. Links to dataset paper and the whitepaper can be found on the website.

Dataset download links can be found at DATASET.md for the S2EF, IS2RS, and IS2RE tasks. IS2* datasets are stored as LMDB files and are ready to be used upon download. S2EF train+val datasets require an additional preprocessing step. For convenience, a self-contained script can be found here to download, preprocess, and organize the data directories to be readily usable by the existing configs:

IS2* datasets: python scripts/download_data.py --task is2re

S2EF datasets:

• train/val splits: python scripts/download_data.py --task s2ef --split SPLIT_SIZE --get-edges --num-workers WORKERS --ref-energy; where
  • --get-edges: includes edge information in LMDBs (~10x storage requirement, ~3-5x slowdown), otherwise, compute edges on the fly (larger GPU memory requirement).
  • --ref-energy: uses referenced energies instead of raw energies.
  • --split: split size to download: "200k", "2M", "20M", "all", "val_id", "val_ood_ads", "val_ood_cat", or "val_ood"both".
  • --num-workers: number of workers to parallelize preprocessing across.
• test splits: python scripts/download_data.py --task s2ef --split test

A detailed description of how to train, predict, and run ML-based relaxations can be found here.

Pretrained models accompanying https://arxiv.org/abs/2010.09990v1 can be found here.

For all non-codebase related questions and to keep up-to-date with the latest OCP announcements, please join the discussion board. All codebase related questions and issues should be posted directly on our issues page.

• This codebase was initially forked from CGCNN by Tian Xie, but has undergone significant changes since.
• A lot of engineering ideas have been borrowed from github.com/facebookresearch/mmf.
• The DimeNet++ implementation is based on the author's Tensorflow implementation and the DimeNet implementation in Pytorch Geometric.

This code is MIT licensed, as found in the LICENSE file.