Eval

metatrain.cli.eval.eval_model(model: MetatensorAtomisticModel | RecursiveScriptModule, options: DictConfig, output: Path | str = 'output.xyz', batch_size: int = 1, check_consistency: bool = False) → None[source]

Evaluate an exported model on a given data set.

If options contains a targets sub-section, RMSE values will be reported. If this sub-section is missing, only a xyz-file with containing the properties the model was trained against is written.

Parameters:

  • model (MetatensorAtomisticModel | RecursiveScriptModule) – Saved model to be evaluated.

  • options (DictConfig) – DictConfig to define a test dataset taken for the evaluation.

  • output (Path | str) – Path to save the predicted values.

  • check_consistency (bool) – Whether to run consistency checks during model evaluation.

  • batch_size (int)

Return type:

None