data.BaseAtomsData

class data.BaseAtomsData(load_properties: List[str] | None = None, load_structure: bool = True, transforms: List[Transform] | None = None, subset_idx: List[int] | None = None)[source]

Base mixin class for atomistic data. Use together with PyTorch Dataset or IterableDataset to implement concrete data formats.

Parameters:

  • load_properties – Set of properties to be loaded and returned. If None, all properties in the ASE dB will be returned.

  • load_structure – If True, load structure properties.

  • transforms – preprocessing transforms (see schnetpack.data.transforms)

  • subset – List of data indices.