Method __call__

monai/transforms/spatial/array.py:3146–3172

Args: img: shape must be (num_channels, H, W[, D]). mode: {``"bilinear"``, ``"nearest"``} or spline interpolation order 0-5 (integers). Interpolation mode to calculate output values. Defaults to ``self.mode``. See also: https://pytorch

(
        self, img: torch.Tensor, mode: str | None = None, padding_mode: str | None = None, randomize: bool = True
    )

        )

    def __call__(
        self, img: torch.Tensor, mode: str | None = None, padding_mode: str | None = None, randomize: bool = True
    ) -> torch.Tensor:
        """
        Args:
            img: shape must be (num_channels, H, W[, D]).
            mode: {``"bilinear"``, ``"nearest"``} or spline interpolation order 0-5 (integers).
                Interpolation mode to calculate output values. Defaults to ``self.mode``.
                See also: https://pytorch.org/docs/stable/generated/torch.nn.functional.grid_sample.html
                When it's an integer, the numpy (cpu tensor)/cupy (cuda tensor) backends will be used
                and the value represents the order of the spline interpolation.
                See also: https://docs.scipy.org/doc/scipy/reference/generated/scipy.ndimage.map_coordinates.html
            padding_mode: {``"zeros"``, ``"border"``, ``"reflection"``}
                Padding mode for outside grid values. Defaults to ``self.padding_mode``.
                See also: https://pytorch.org/docs/stable/generated/torch.nn.functional.grid_sample.html
                When `mode` is an integer, using numpy/cupy backends, this argument accepts
                {'reflect', 'grid-mirror', 'constant', 'grid-constant', 'nearest', 'mirror', 'grid-wrap', 'wrap'}.
                See also: https://docs.scipy.org/doc/scipy/reference/generated/scipy.ndimage.map_coordinates.html
            randomize: whether to shuffle the random factors using `randomize()`, default to True.
        """
        if randomize:
            if isinstance(img, MetaTensor) and img.pending_operations:
                warnings.warn("MetaTensor img has pending operations, transform may return incorrect results.")
            self.randomize(img.shape[1:])
        if not self._do_transform:
            return convert_to_tensor(img, track_meta=get_track_meta())  # type: ignore
        return self.grid_distortion(img, distort_steps=self.distort_steps, mode=mode, padding_mode=padding_mode)


class GridSplit(Transform, MultiSampleTrait):