Class RandFlip

monai/transforms/spatial/array.py:1439–1489

Randomly flips the image along axes. Preserves shape. See numpy.flip for additional details. https://docs.scipy.org/doc/numpy/reference/generated/numpy.flip.html This transform is capable of lazy execution. See the :ref:`Lazy Resampling topic ` for more informat

class RandFlip(RandomizableTransform, InvertibleTransform, LazyTransform):
    """
    Randomly flips the image along axes. Preserves shape.
    See numpy.flip for additional details.
    https://docs.scipy.org/doc/numpy/reference/generated/numpy.flip.html

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

    Args:
        prob: Probability of flipping.
        spatial_axis: Spatial axes along which to flip over. Default is None.
        lazy: a flag to indicate whether this transform should execute lazily or not.
            Defaults to False
    """

    backend = Flip.backend

    def __init__(self, prob: float = 0.1, spatial_axis: Sequence[int] | int | None = None, lazy: bool = False) -> None:
        RandomizableTransform.__init__(self, prob)
        LazyTransform.__init__(self, lazy=lazy)
        self.flipper = Flip(spatial_axis=spatial_axis, lazy=lazy)

    @LazyTransform.lazy.setter  # type: ignore
    def lazy(self, val: bool):
        self.flipper.lazy = val
        self._lazy = val

    def __call__(self, img: torch.Tensor, randomize: bool = True, lazy: bool | None = None) -> torch.Tensor:
        """
        Args:
            img: channel first array, must have shape: (num_channels, H[, W, ..., ]),
            randomize: whether to execute `randomize()` function first, default to True.
            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.
        """
        if randomize:
            self.randomize(None)
        lazy_ = self.lazy if lazy is None else lazy
        out = self.flipper(img, lazy=lazy_) if self._do_transform else img
        out = convert_to_tensor(out, track_meta=get_track_meta())
        self.push_transform(out, replace=True, lazy=lazy_)
        return out

    def inverse(self, data: torch.Tensor) -> torch.Tensor:
        transform = self.pop_transform(data)
        if not transform[TraceKeys.DO_TRANSFORM]:
            return data
        data.applied_operations.append(transform[TraceKeys.EXTRA_INFO])  # type: ignore
        return self.flipper.inverse(data)


class RandAxisFlip(RandomizableTransform, InvertibleTransform, LazyTransform):