Function create_scale

monai/transforms/utils.py:1015–1039

create a scaling matrix Args: spatial_dims: spatial rank scaling_factor: scaling factors for every spatial dim, defaults to 1. device: device to compute and store the output (when the backend is "torch"). backend: APIs to use, ``numpy`` or ``torch``.

(
    spatial_dims: int,
    scaling_factor: Sequence[float] | float,
    device: torch.device | str | None = None,
    backend=TransformBackends.NUMPY,
)

def create_scale(
    spatial_dims: int,
    scaling_factor: Sequence[float] | float,
    device: torch.device | str | None = None,
    backend=TransformBackends.NUMPY,
) -> NdarrayOrTensor:
    """
    create a scaling matrix

    Args:
        spatial_dims: spatial rank
        scaling_factor: scaling factors for every spatial dim, defaults to 1.
        device: device to compute and store the output (when the backend is "torch").
        backend: APIs to use, ``numpy`` or ``torch``.
    """
    _backend = look_up_option(backend, TransformBackends)
    if _backend == TransformBackends.NUMPY:
        return _create_scale(spatial_dims=spatial_dims, scaling_factor=scaling_factor, array_func=np.diag)
    if _backend == TransformBackends.TORCH:
        return _create_scale(
            spatial_dims=spatial_dims,
            scaling_factor=scaling_factor,
            array_func=lambda x: torch.diag(torch.as_tensor(x, device=device)),
        )
    raise ValueError(f"backend {backend} is not supported")


def _create_scale(spatial_dims: int, scaling_factor: Sequence[float] | float, array_func=np.diag) -> NdarrayOrTensor: