Function flip

monai/transforms/spatial/functional.py:275–308

Functional implementation of flip. This function operates eagerly or lazily according to ``lazy`` (default ``False``). Args: img: data to be changed, assuming `img` is channel-first. sp_axes: spatial axes along which to flip over. If None, will flip over

(img, sp_axes, lazy, transform_info)

def flip(img, sp_axes, lazy, transform_info):
    """
    Functional implementation of flip.
    This function operates eagerly or lazily according to
    ``lazy`` (default ``False``).

    Args:
        img: data to be changed, assuming `img` is channel-first.
        sp_axes: spatial axes along which to flip over.
            If 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 that indicates whether the operation should be performed lazily or not
        transform_info: a dictionary with the relevant information pertaining to an applied transform.
    """
    sp_size = img.peek_pending_shape() if isinstance(img, MetaTensor) else img.shape[1:]
    sp_size = convert_to_numpy(sp_size, wrap_sequence=True).tolist()
    extra_info = {"axes": sp_axes}  # track the spatial axes
    axes = monai.transforms.utils.map_spatial_axes(img.ndim, sp_axes)  # use the axes with channel dim
    rank = img.peek_pending_rank() if isinstance(img, MetaTensor) else torch.tensor(3.0, dtype=torch.double)
    # axes include the channel dim
    xform = torch.eye(int(rank) + 1, dtype=torch.double)
    for axis in axes:
        sp = axis - 1
        xform[sp, sp], xform[sp, -1] = xform[sp, sp] * -1, sp_size[sp] - 1
    meta_info = TraceableTransform.track_transform_meta(
        img, sp_size=sp_size, affine=xform, extra_info=extra_info, transform_info=transform_info, lazy=lazy
    )
    out = _maybe_new_metatensor(img)
    if lazy:
        return out.copy_meta_from(meta_info) if isinstance(out, MetaTensor) else meta_info
    out = torch.flip(out, axes)
    return out.copy_meta_from(meta_info) if isinstance(out, MetaTensor) else out


def resize(