Class Flip

monai/transforms/spatial/array.py:706–748

Reverses the order of elements along the given spatial axis. Preserves shape. See `torch.flip` documentation for additional details: https://pytorch.org/docs/stable/generated/torch.flip.html This transform is capable of lazy execution. See the :ref:`Lazy Resampling topic<lazy_resam

class Flip(InvertibleTransform, LazyTransform):
    """
    Reverses the order of elements along the given spatial axis. Preserves shape.
    See `torch.flip` documentation for additional details:
    https://pytorch.org/docs/stable/generated/torch.flip.html

    This transform is capable of lazy execution. See the :ref:`Lazy Resampling topic<lazy_resampling>`
    for more information.

    Args:
        spatial_axis: spatial axes along which to flip over. Default is None.
            The default `axis=None` will flip over all of the axes of the input array.
            If axis is negative it counts from the last to the first axis.
            If axis is a tuple of ints, flipping is performed on all of the axes
            specified in the tuple.
        lazy: a flag to indicate whether this transform should execute lazily or not.
            Defaults to False

    """

    backend = [TransformBackends.TORCH]

    def __init__(self, spatial_axis: Sequence[int] | int | None = None, lazy: bool = False) -> None:
        LazyTransform.__init__(self, lazy=lazy)
        self.spatial_axis = spatial_axis

    def __call__(self, img: torch.Tensor, lazy: bool | None = None) -> torch.Tensor:
        """
        Args:
            img: channel first array, must have shape: (num_channels, H[, W, ..., ])
            lazy: a flag to indicate whether this transform should execute lazily or not
                during this call. Setting this to False or True overrides the ``lazy`` flag set
                during initialization for this call. Defaults to None.
        """
        img = convert_to_tensor(img, track_meta=get_track_meta())
        lazy_ = self.lazy if lazy is None else lazy
        return flip(img, self.spatial_axis, lazy=lazy_, transform_info=self.get_transform_info())  # type: ignore

    def inverse(self, data: torch.Tensor) -> torch.Tensor:
        self.pop_transform(data)
        flipper = Flip(spatial_axis=self.spatial_axis)
        with flipper.trace_transform(False):
            return flipper(data)


class Resize(InvertibleTransform, LazyTransform):