It is recommended to install each necessary package (with appropriate versions mentioned in the symmcd.yaml) file following this order: pytorch, pytorch-lightning, pyg, pyxtal, pymatgen, matminer, einops, hydra-core, symd, dotenv, wandb,p_tqdm,torch_scatter, torch_sparse, smact,chemparse.
- Rename the
.env.templatefile into.envand 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 wandb outputs
WABDB_DIR: the absolute path to save wandb cache outputs
- Create the anaconda environment with the
symmcd.ymlfile (conda env create -f symmcd.yml: creates environment with namesymmcd) - Install
matminerwithcd matminer && pip install -e . - Clone
cdvae repoin the same directory level asconfanddataand install it - You can now execute the training command below without errors. If it throws some package error, please install those (and create a PR).
SymmCD (should now look like this, and the environment should contain cdvae and matminer packages)
├── cdvae
├── conf
├── data
├── symmcd
├── matminer
├── scripts
├── .env
├── .........
Before training, you should change the following in cdvae/cdvae/pl_modules/gnn.py (swish can no longer be imported from torch_geometric.nn.acts):
- Comment out the import:
from torch_geometric.nn.acts import swish - Add the following lines to the script before the
class InteractionPPBlock:
def swish(x):
return x * x.sigmoid()
python symmcd/run.py data=<dataset> model=discrete_diffusion_w_site_symm expname=<expname>
- The
<dataset>tag can be selected frommp_20andmpts_52. - For multiple GPUs, please add
train.pl_trainer.devices=2to above commands (ensure 2 gpus on machine where script launches).
python scripts/generation.py --model_path <model_path> --dataset <dataset>
python scripts/compute_metrics --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>
- Change/Add hyperparameters and their values in the
hyperparam_sweep.yamlfile. wandb sweep --project <project-name> -e <entity-name> hyperparam_sweep.yaml.wandb agent <above-agent-id>.
This codebase was adapted from the DiffCSP repository. We thank the authors for their work and open-sourcing their code.