Method __call__

monai/transforms/croppad/array.py:408–425

Apply the transform to `img`, assuming `img` is channel-first and slicing doesn't apply to the channel dim.

(  # type: ignore[override]
        self, img: torch.Tensor, slices: tuple[slice, ...], lazy: bool | None = None
    )

            return ensure_tuple([slice(int(s), int(e)) for s, e in zip(roi_start_t.tolist(), roi_end_t.tolist())])

    def __call__(  # type: ignore[override]
        self, img: torch.Tensor, slices: tuple[slice, ...], lazy: bool | None = None
    ) -> torch.Tensor:
        """
        Apply the transform to `img`, assuming `img` is channel-first and
        slicing doesn't apply to the channel dim.

        """
        slices_ = list(slices)
        sd = len(img.peek_pending_shape() if isinstance(img, MetaTensor) else img.shape[1:])  # spatial dims
        if len(slices_) < sd:
            slices_ += [slice(None)] * (sd - len(slices_))
        # Add in the channel (no cropping)
        slices_ = list([slice(None)] + slices_[:sd])

        img_t: MetaTensor = convert_to_tensor(data=img, track_meta=get_track_meta())
        lazy_ = self.lazy if lazy is None else lazy
        return crop_func(img_t, tuple(slices_), lazy_, self.get_transform_info())

    def inverse(self, img: MetaTensor) -> MetaTensor:
        transform = self.pop_transform(img)