Method __call__

monai/transforms/spatial/array.py:3030–3086

Args: img: shape must be (num_channels, H, W[, D]). distort_steps: This argument is a list of tuples, where each tuple contains the distort steps of the corresponding dimensions (in the order of H, W[, D]). The length of each tuple equals to `num_cell

(
        self,
        img: torch.Tensor,
        distort_steps: Sequence[Sequence] | None = None,
        mode: str | None = None,
        padding_mode: str | None = None,
    )

        self.device = device

    def __call__(
        self,
        img: torch.Tensor,
        distort_steps: Sequence[Sequence] | None = None,
        mode: str | None = None,
        padding_mode: str | None = None,
    ) -> torch.Tensor:
        """
        Args:
            img: shape must be (num_channels, H, W[, D]).
            distort_steps: This argument is a list of tuples, where each tuple contains the distort steps of the
                corresponding dimensions (in the order of H, W[, D]). The length of each tuple equals to `num_cells + 1`.
                Each value in the tuple represents the distort step of the related cell.
            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

        """
        distort_steps = self.distort_steps if distort_steps is None else distort_steps
        if len(img.shape) != len(distort_steps) + 1:
            raise ValueError("the spatial size of `img` does not match with the length of `distort_steps`")

        all_ranges = []
        num_cells = ensure_tuple_rep(self.num_cells, len(img.shape) - 1)
        if isinstance(img, MetaTensor) and img.pending_operations:
            warnings.warn("MetaTensor img has pending operations, transform may return incorrect results.")
        for dim_idx, dim_size in enumerate(img.shape[1:]):
            dim_distort_steps = distort_steps[dim_idx]
            ranges = torch.zeros(dim_size, dtype=torch.float32)
            cell_size = dim_size // num_cells[dim_idx]
            prev = 0
            for idx in range(num_cells[dim_idx] + 1):
                start = int(idx * cell_size)
                end = start + cell_size
                if end > dim_size:
                    end = dim_size
                    cur = dim_size
                else:
                    cur = prev + cell_size * dim_distort_steps[idx]
                ranges[start:end] = torch.linspace(prev, cur, end - start)
                prev = cur
            ranges = ranges - (dim_size - 1.0) / 2.0
            all_ranges.append(ranges)

        coords = meshgrid_ij(*all_ranges)
        grid = torch.stack([*coords, torch.ones_like(coords[0])])

        return self.resampler(img, grid=grid, mode=mode, padding_mode=padding_mode)