Class RepeatChannel

monai/transforms/utility/array.py:237–259

Repeat channel data to construct expected input shape for models. The `repeats` count includes the origin data, for example: ``RepeatChannel(repeats=2)([[1, 2], [3, 4]])`` generates: ``[[1, 2], [1, 2], [3, 4], [3, 4]]`` Args: repeats: the number of repetitions for each elem

class RepeatChannel(Transform):
    """
    Repeat channel data to construct expected input shape for models.
    The `repeats` count includes the origin data, for example:
    ``RepeatChannel(repeats=2)([[1, 2], [3, 4]])`` generates: ``[[1, 2], [1, 2], [3, 4], [3, 4]]``

    Args:
        repeats: the number of repetitions for each element.
    """

    backend = [TransformBackends.TORCH]

    def __init__(self, repeats: int) -> None:
        if repeats <= 0:
            raise ValueError(f"repeats count must be greater than 0, got {repeats}.")
        self.repeats = repeats

    def __call__(self, img: NdarrayOrTensor) -> NdarrayOrTensor:
        """
        Apply the transform to `img`, assuming `img` is a "channel-first" array.
        """
        repeat_fn = torch.repeat_interleave if isinstance(img, torch.Tensor) else np.repeat
        return convert_to_tensor(repeat_fn(img, self.repeats, 0), track_meta=get_track_meta())  # type: ignore


class RemoveRepeatedChannel(Transform):