Implementation codes for Crystal Structure Prediction by Joint Equivariant Diffusion (DiffCSP).
python==3.8.13
torch==1.9.0
torch-geometric==1.7.2
pytorch_lightning==1.3.8
pymatgen==2022.9.21
Rename the .env.template file into .env and specify the following variables.
PROJECT_ROOT: the absolute path of this repo
HYDRA_JOBS: the absolute path to save hydra outputs
WABDB_DIR: the absolute path to save wabdb outputs
For the CSP task
python diffcsp/run.py data=<dataset> expname=<expname>
For the Ab Initio Generation task
python diffcsp/run.py data=<dataset> model=diffusion_w_type expname=<expname>
The <dataset> tag can be selected from perov_5, mp_20, mpts_52 and carbon_24, and the <expname> tag can be an arbitrary name to identify each experiment. Pre-trained checkpoints are provided here.
One sample
python scripts/evaluate.py --model_path <model_path> --dataset <dataset>
python scripts/compute_metrics.py --root_path <model_path> --tasks csp --gt_file data/<dataset>/test.csv
Multiple samples
python scripts/evaluate.py --model_path <model_path> --dataset <dataset> --num_evals 20
python scripts/compute_metrics.py --root_path <model_path> --tasks csp --gt_file data/<dataset>/test.csv --multi_eval
python scripts/generation.py --model_path <model_path> --dataset <dataset>
python scripts/compute_metrics.py --root_path <model_path> --tasks gen --gt_file data/<dataset>/test.csv
python scripts/sample.py --model_path <model_path> --save_path <save_path> --formula <formula> --num_evals <num_evals>
The main framework of this codebase is build upon CDVAE. For the datasets, Perov-5, Carbon-24 and MP-20 are from CDVAE, and MPTS-52 is collected from its original codebase.
Please consider citing our work if you find it helpful:
@article{jiao2023crystal,
title={Crystal structure prediction by joint equivariant diffusion},
author={Jiao, Rui and Huang, Wenbing and Lin, Peijia and Han, Jiaqi and Chen, Pin and Lu, Yutong and Liu, Yang},
journal={arXiv preprint arXiv:2309.04475},
year={2023}
}
If you have any questions, feel free to reach us at:
Rui Jiao: [email protected]
React
Typescript
Django
Laravel
Facebook
Microsoft
Google
Alibaba
D3
Tencent