Class ZipDataset

monai/data/dataset.py:1272–1319

Zip several PyTorch datasets and output data(with the same index) together in a tuple. If the output of single dataset is already a tuple, flatten it and extend to the result. For example: if datasetA returns (img, imgmeta), datasetB returns (seg, segmeta), finally return (img, imgm

class ZipDataset(Dataset):
    """
    Zip several PyTorch datasets and output data(with the same index) together in a tuple.
    If the output of single dataset is already a tuple, flatten it and extend to the result.
    For example: if datasetA returns (img, imgmeta), datasetB returns (seg, segmeta),
    finally return (img, imgmeta, seg, segmeta).
    And if the datasets don't have same length, use the minimum length of them as the length
    of ZipDataset.
    If passing slicing indices, will return a PyTorch Subset, for example: `data: Subset = dataset[1:4]`,
    for more details, please check: https://pytorch.org/docs/stable/data.html#torch.utils.data.Subset

    Examples::

        >>> zip_data = ZipDataset([[1, 2, 3], [4, 5]])
        >>> print(len(zip_data))
        2
        >>> for item in zip_data:
        >>>    print(item)
        [1, 4]
        [2, 5]

    """

    def __init__(self, datasets: Sequence, transform: Callable | None = None) -> None:
        """
        Args:
            datasets: list of datasets to zip together.
            transform: a callable data transform operates on the zipped item from `datasets`.
        """
        super().__init__(list(datasets), transform=transform)

    def __len__(self) -> int:
        return min(len(dataset) for dataset in self.data)

    def _transform(self, index: int):

        def to_list(x):
            return list(x) if isinstance(x, (tuple, list)) else [x]

        data = []
        for dataset in self.data:
            data.extend(to_list(dataset[index]))

        if self.transform is not None:
            self.transform.map_items = False  # Compose object map_items to false so transform is applied to list
            data = self.transform(data)
        # use tuple instead of list as the default collate_fn callback of MONAI DataLoader flattens nested lists
        return tuple(data)


class ArrayDataset(Randomizable, _TorchDataset):