Function get_norm_layer

monai/networks/layers/utils.py:22–50

Create a normalization layer instance. For example, to create normalization layers: .. code-block:: python from monai.networks.layers import get_norm_layer g_layer = get_norm_layer(name=("group", {"num_groups": 1})) n_layer = get_norm_layer(name="instance", s

(name: tuple | str, spatial_dims: int | None = 1, channels: int | None = 1)

def get_norm_layer(name: tuple | str, spatial_dims: int | None = 1, channels: int | None = 1):
    """
    Create a normalization layer instance.

    For example, to create normalization layers:

    .. code-block:: python

        from monai.networks.layers import get_norm_layer

        g_layer = get_norm_layer(name=("group", {"num_groups": 1}))
        n_layer = get_norm_layer(name="instance", spatial_dims=2)

    Args:
        name: a normalization type string or a tuple of type string and parameters.
        spatial_dims: number of spatial dimensions of the input.
        channels: number of features/channels when the normalization layer requires this parameter
            but it is not specified in the norm parameters.
    """
    if name == "":
        return torch.nn.Identity()
    norm_name, norm_args = split_args(name)
    norm_type = Norm[norm_name, spatial_dims]
    kw_args = dict(norm_args)
    if has_option(norm_type, "num_features") and "num_features" not in kw_args:
        kw_args["num_features"] = channels
    if has_option(norm_type, "num_channels") and "num_channels" not in kw_args:
        kw_args["num_channels"] = channels
    return norm_type(**kw_args)


def get_act_layer(name: tuple | str):