tiled_patching

def extract_tiles(
    arr: np.ndarray,
    tile_size: Union[List[int], Tuple[int, ...]],
    overlaps: Union[List[int], Tuple[int, ...]],
) -> Generator[Tuple[np.ndarray, TileInformation], None, None]:
    """Generate tiles from the input array with specified overlap.

    The tiles cover the whole array. The method returns a generator that yields
    tuples of array and tile information, the latter includes whether
    the tile is the last one, the coordinates of the overlap crop, and the coordinates
    of the stitched tile.

    Input array should have shape SC(Z)YX, while the returned tiles have shape C(Z)YX,
    where C can be a singleton.

    Parameters
    ----------
    arr : np.ndarray
        Array of shape (S, C, (Z), Y, X).
    tile_size : Union[List[int], Tuple[int]]
        Tile sizes in each dimension, of length 2 or 3.
    overlaps : Union[List[int], Tuple[int]]
        Overlap values in each dimension, of length 2 or 3.

    Yields
    ------
    Generator[Tuple[np.ndarray, TileInformation], None, None]
        Tile generator, yields the tile and additional information.
    """
    # Iterate over num samples (S)
    for sample_idx in range(arr.shape[0]):
        sample: np.ndarray = arr[sample_idx, ...]

        # Create a list of coordinates for cropping and stitching all axes.
        # [crop coordinates, stitching coordinates, overlap crop coordinates]
        # For axis of size 35 and patch size of 32 compute_crop_and_stitch_coords_1d
        # will output ([(0, 32), (3, 35)], [(0, 20), (20, 35)], [(0, 20), (17, 32)])
        crop_and_stitch_coords_list = [
            _compute_crop_and_stitch_coords_1d(
                sample.shape[i + 1], tile_size[i], overlaps[i]
            )
            for i in range(len(tile_size))
        ]

        # Rearrange crop coordinates from a list of coordinate pairs per axis to a list
        # grouped by type.
        all_crop_coords, all_stitch_coords, all_overlap_crop_coords = zip(
            *crop_and_stitch_coords_list
        )

        # Maximum tile index
        max_tile_idx = np.prod([len(axis) for axis in all_crop_coords]) - 1

        # Iterate over generated coordinate pairs:
        for tile_idx, (crop_coords, stitch_coords, overlap_crop_coords) in enumerate(
            zip(
                itertools.product(*all_crop_coords),
                itertools.product(*all_stitch_coords),
                itertools.product(*all_overlap_crop_coords),
            )
        ):
            # Extract tile from the sample
            tile: np.ndarray = sample[
                (..., *[slice(c[0], c[1]) for c in list(crop_coords)])  # type: ignore
            ]

            # Check if we are at the end of the sample by computing the length of the
            # array that contains all the tiles
            if tile_idx == max_tile_idx:
                last_tile = True
            else:
                last_tile = False

            # create tile information
            tile_info = TileInformation(
                array_shape=sample.shape,
                last_tile=last_tile,
                overlap_crop_coords=overlap_crop_coords,
                stitch_coords=stitch_coords,
                sample_id=sample_idx,
            )

            yield tile, tile_info