Skip to content

DatasetConfig

class franken.config.DatasetConfig(name: str | None = None, train_path: str | None = None, test_path: str | None = None, val_path: str | None = None, max_train_samples: int | None = None)

Bases: object

max_train_samples: int | None = None: Randomly subsample the training set to have at most max_train_samples points.

name: str | None = None: Dataset name. Can be either one of the predefined datasets, or a custom one.

test_path: str | None = None: Path to the test dataset. When doing hyperparameter tuning this is never used to determine the best model.

train_path: str | None = None: Path to the training dataset. This should be readable with ase, e.g. xyz files work.

val_path: str | None = None: Path to the validation dataset. Used for hyperparameter tuning if available.