Class FromMetaTensord

monai/transforms/meta_utility/dictionary.py:42–86

Dictionary-based transform to convert MetaTensor to a dictionary. If input is `{"a": MetaTensor, "b": MetaTensor}`, then output will have the form `{"a": torch.Tensor, "a_meta_dict": dict, "a_transforms": list, "b": ...}`.

class FromMetaTensord(MapTransform, InvertibleTransform):
    """
    Dictionary-based transform to convert MetaTensor to a dictionary.

    If input is `{"a": MetaTensor, "b": MetaTensor}`, then output will
    have the form `{"a": torch.Tensor, "a_meta_dict": dict, "a_transforms": list, "b": ...}`.
    """

    backend = [TransformBackends.TORCH, TransformBackends.NUMPY, TransformBackends.CUPY]

    def __init__(
        self, keys: KeysCollection, data_type: Sequence[str] | str = "tensor", allow_missing_keys: bool = False
    ):
        """
        Args:
            keys: keys of the corresponding items to be transformed.
                See also: :py:class:`monai.transforms.compose.MapTransform`
            data_type: target data type to convert, should be "tensor" or "numpy".
            allow_missing_keys: don't raise exception if key is missing.
        """
        super().__init__(keys, allow_missing_keys)
        self.as_tensor_output = tuple(d == "tensor" for d in ensure_tuple_rep(data_type, len(self.keys)))

    def __call__(self, data: Mapping[Hashable, NdarrayOrTensor]) -> dict[Hashable, NdarrayOrTensor]:
        d = dict(data)
        for key, t in self.key_iterator(d, self.as_tensor_output):
            im: MetaTensor = d[key]  # type: ignore
            d.update(im.as_dict(key, output_type=torch.Tensor if t else np.ndarray))
            self.push_transform(d, key)
        return d

    def inverse(self, data: Mapping[Hashable, NdarrayOrTensor]) -> dict[Hashable, NdarrayOrTensor]:
        d = dict(data)
        for key in self.key_iterator(d):
            # check transform
            _ = self.get_most_recent_transform(d, key)
            # do the inverse
            im = d[key]
            meta = d.pop(PostFix.meta(key), None)
            transforms = d.pop(PostFix.transforms(key), None)
            im = MetaTensor(im, meta=meta, applied_operations=transforms)  # type: ignore
            d[key] = im
            # Remove the applied transform
            self.pop_transform(d, key)
        return d


class ToMetaTensord(MapTransform, InvertibleTransform):