comp-chem/cp2k
1
0
Fork 0
mirror of https://github.com/cp2k/cp2k.git synced 2026-07-21 06:25:15 -04:00
Code Issues Projects Releases Packages Wiki Activity Actions
cp2k/tools/pao-ml
History
Exact
dependabot[bot] 9111030217
Bump torch from 2.11.0 to 2.13.0 in /tools/pao-ml (#5604) 
Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
2026-07-17 23:04:52 +02:00
..
pao PAO-ML: Add pao-diff.py tool (#5577) 2026-07-10 16:55:19 +02:00
example.pao PAO-ML: Add scripts for training an equivariant model 2025-01-07 23:16:10 +01:00
pao-diff.py PAO-ML: Add pao-diff.py tool (#5577) 2026-07-10 16:55:19 +02:00
pao-retrain.py PAO-ML: Pin versions of all Python packages 2026-02-18 11:45:48 +01:00
pao-train.py PAO-ML: Pin versions of all Python packages 2026-02-18 11:45:48 +01:00
pao-validate.py PAO-ML: Split samples into training and validation set 2026-02-08 18:37:33 +01:00
README.md PAO-ML: Migrate to NequIP framework 2025-10-01 16:25:41 +02:00
requirements.txt Bump torch from 2.11.0 to 2.13.0 in /tools/pao-ml (#5604) 2026-07-17 23:04:52 +02:00

README.md

PAO-ML training

These are the scripts for training an equivariant PAO-ML model. To create a new model, follow these steps:

  1. Create and activate a virtual Python environment:

    python3 -m venv ./venv
source ./venv/bin/activate

  2. Install the required Python packages:

    pip3 install -r requirements.txt

  3. Train a new model:

    ./pao-train.py --kind=H training_data1.pao training_data2.pao...

  4. Retrain the model on some more taining data:

    ./pao-retrain.py --model="DZVP-MOLOPT-GTH-PAO4-H.pt" training_data100.pao training_data101.pao...

  5. Validate the model against test data:

    ./pao-validate.py --model="DZVP-MOLOPT-GTH-PAO4-H.pt" test_data1.pao test_data2.pao...

  6. Use the model in a CP2K run by setting the PAO_MODEL_FILE keyword in the kind section:

    &KIND H
  BASIS_SET DZVP-MOLOPT-GTH
  PAO_BASIS_SIZE 4
  PAO_MODEL_FILE DZVP-MOLOPT-GTH-PAO4-H.pt
&END KIND