Dataset interface

This interface defines a pytorch-like dataset interface for loading, combining and slicing datasets.

class dipm.data.chemical_datasets.dataset.Dataset

Pytorch dataset like base objects.

__getitem__(index: int) → _T_co

__getitem__(index: list | ndarray | slice) → list[_T_co]

__len__() → int

release()

Release resources.

class dipm.data.chemical_datasets.dataset.ConcatDataset(datasets: Sequence[Dataset])

Dataset as a concatenation of multiple datasets. Pytorch-like ConcatDataset.

__init__(datasets: Sequence[Dataset])

Create a concatenated dataset.

Parameters:

datasets (sequence) – List of datasets to concatenate.

__getitem__(index)

__len__() → int

release()

Release dataset file handles.

class dipm.data.chemical_datasets.dataset.Subset(dataset: Dataset, start_or_indices: int | Sequence[int], length: int | None = None)

Subset of a dataset with a given slice.

__init__(dataset: Dataset, start_or_indices: int | Sequence[int], length: int | None = None)

__getitem__(index)

__len__()

release()

Release dataset resources.