Function crop_func

monai/transforms/croppad/functional.py:217–252

Functional implementation of cropping a MetaTensor. This function operates eagerly or lazily according to ``lazy`` (default ``False``). Args: img: data to be transformed, assuming `img` is channel-first and cropping doesn't apply to the channel dim. slices: the crop sli

(img: torch.Tensor, slices: tuple[slice, ...], lazy: bool, transform_info: dict)

def crop_func(img: torch.Tensor, slices: tuple[slice, ...], lazy: bool, transform_info: dict) -> torch.Tensor:
    """
    Functional implementation of cropping a MetaTensor. This function operates eagerly or lazily according
    to ``lazy`` (default ``False``).

    Args:
        img: data to be transformed, assuming `img` is channel-first and cropping doesn't apply to the channel dim.
        slices: the crop slices computed based on specified `center & size` or `start & end` or `slices`.
        lazy: a flag indicating whether the operation should be performed in a lazy fashion or not.
        transform_info: a dictionary with the relevant information pertaining to an applied transform.
    """
    img_size = img.peek_pending_shape() if isinstance(img, MetaTensor) else img.shape[1:]
    spatial_rank = img.peek_pending_rank() if isinstance(img, MetaTensor) else 3
    cropped = np.asarray([[s.indices(o)[0], o - s.indices(o)[1]] for s, o in zip(slices[1:], img_size)])
    extra_info = {"cropped": cropped.flatten().tolist()}
    to_shift = []
    for i, s in enumerate(ensure_tuple(slices)[1:]):
        if s.start is not None:
            to_shift.append(img_size[i] + s.start if s.start < 0 else s.start)
        else:
            to_shift.append(0)
    shape = [s.indices(o)[1] - s.indices(o)[0] for s, o in zip(slices[1:], img_size)]
    meta_info = TraceableTransform.track_transform_meta(
        img,
        sp_size=shape,
        affine=create_translate(spatial_rank, to_shift),
        extra_info=extra_info,
        orig_size=img_size,
        transform_info=transform_info,
        lazy=lazy,
    )
    out = convert_to_tensor(img.as_tensor() if isinstance(img, MetaTensor) else img, track_meta=get_track_meta())
    if lazy:
        return out.copy_meta_from(meta_info) if isinstance(out, MetaTensor) else meta_info  # type: ignore
    out = out[slices]
    return out.copy_meta_from(meta_info) if isinstance(out, MetaTensor) else out  # type: ignore