def get_norm_layer(name: Union[Tuple, str],
spatial_dims: Optional[int] = 1,
channels: Optional[int] = 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.
"""
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 __init__(
self,
ordering: str = "NDA",
in_channels: Optional[int] = None,
act: Optional[Union[Tuple, str]] = "RELU",
norm: Optional[Union[Tuple, str]] = None,
norm_dim: Optional[int] = None,
dropout: Optional[Union[Tuple, str, float]] = None,
dropout_dim: Optional[int] = None,
) -> None:
super().__init__()
op_dict = {"A": None, "D": None, "N": None}
# define the normalization type and the arguments to the constructor
if norm is not None:
if norm_dim is None and dropout_dim is None:
raise ValueError(
"norm_dim or dropout_dim needs to be specified.")
norm_name, norm_args = split_args(norm)
norm_type = Norm[norm_name, norm_dim or dropout_dim]
kw_args = dict(norm_args)
if has_option(norm_type,
"num_features") and "num_features" not in kw_args:
kw_args["num_features"] = in_channels
if has_option(norm_type,
"num_channels") and "num_channels" not in kw_args:
kw_args["num_channels"] = in_channels
op_dict["N"] = norm_type(**kw_args)
# define the activation type and the arguments to the constructor
if act is not None:
act_name, act_args = split_args(act)
act_type = Act[act_name]
op_dict["A"] = act_type(**act_args)
if dropout is not None:
# if dropout was specified simply as a p value, use default name and make a keyword map with the value
if isinstance(dropout, (int, float)):
drop_name = Dropout.DROPOUT
drop_args = {"p": float(dropout)}
else:
drop_name, drop_args = split_args(dropout)
if norm_dim is None and dropout_dim is None:
raise ValueError(
"norm_dim or dropout_dim needs to be specified.")
drop_type = Dropout[drop_name, dropout_dim or norm_dim]
op_dict["D"] = drop_type(**drop_args)
for item in ordering.upper():
if item not in op_dict:
raise ValueError(
f"ordering must be a string of {op_dict}, got {item} in it."
)
if op_dict[item] is not None:
self.add_module(item, op_dict[item]) # type: ignore