def __init__(
self,
spatial_dims: int,
in_channels: int,
out_channels: int,
strides: Union[Sequence[int], int] = 1,
kernel_size: Union[Sequence[int], int] = 3,
adn_ordering: str = "NDA",
act: Optional[Union[Tuple, str]] = "PRELU",
norm: Optional[Union[Tuple, str]] = "INSTANCE",
dropout: Optional[Union[Tuple, str, float]] = None,
dropout_dim: Optional[int] = 1,
dilation: Union[Sequence[int], int] = 1,
groups: int = 1,
bias: bool = True,
conv_only: bool = False,
is_transposed: bool = False,
padding: Optional[Union[Sequence[int], int]] = None,
output_padding: Optional[Union[Sequence[int], int]] = None,
dimensions: Optional[int] = None,
) -> None:
super().__init__()
self.dimensions = spatial_dims if dimensions is None else dimensions
self.in_channels = in_channels
self.out_channels = out_channels
self.is_transposed = is_transposed
if padding is None:
padding = same_padding(kernel_size, dilation)
conv_type = Conv[Conv.CONVTRANS if is_transposed else Conv.CONV,
self.dimensions]
conv: nn.Module
if is_transposed:
if output_padding is None:
output_padding = stride_minus_kernel_padding(1, strides)
conv = conv_type(
in_channels,
out_channels,
kernel_size=kernel_size,
stride=strides,
padding=padding,
output_padding=output_padding,
groups=groups,
bias=bias,
dilation=dilation,
)
else:
conv = conv_type(
in_channels,
out_channels,
kernel_size=kernel_size,
stride=strides,
padding=padding,
dilation=dilation,
groups=groups,
bias=bias,
)
self.add_module("conv", conv)
if not conv_only:
self.add_module(
"adn",
ADN(
ordering=adn_ordering,
in_channels=out_channels,
act=act,
norm=norm,
norm_dim=self.dimensions,
dropout=dropout,
dropout_dim=dropout_dim,
),
)
def __init__(
self,
dimensions: int,
in_channels: int,
out_channels: int,
strides: Union[Sequence[int], int] = 1,
kernel_size: Union[Sequence[int], int] = 3,
act: Optional[Union[Tuple, str]] = Act.PRELU,
norm: Union[Tuple, str] = Norm.INSTANCE,
dropout: Optional[Union[Tuple, str, float]] = None,
dropout_dim: int = 1,
dilation: Union[Sequence[int], int] = 1,
groups: int = 1,
bias: bool = True,
conv_only: bool = False,
is_transposed: bool = False,
padding: Optional[Union[Sequence[int], int]] = None,
output_padding: Optional[Union[Sequence[int], int]] = None,
) -> None:
super().__init__()
self.dimensions = dimensions
self.in_channels = in_channels
self.out_channels = out_channels
self.is_transposed = is_transposed
if not padding:
padding = same_padding(kernel_size, dilation)
conv_type = Conv[Conv.CONVTRANS if is_transposed else Conv.CONV, dimensions]
# define the normalisation type and the arguments to the constructor
if norm is not None:
norm_name, norm_args = split_args(norm)
norm_type = Norm[norm_name, dimensions]
else:
norm_type = norm_args = None
# 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]
else:
act_type = act_args = None
if dropout:
# 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": dropout}
else:
drop_name, drop_args = split_args(dropout)
if dropout_dim > dimensions:
raise ValueError(
f"dropout_dim should be no larger than dimensions, got dropout_dim={dropout_dim} and dimensions={dimensions}."
)
drop_type = Dropout[drop_name, dropout_dim]
if is_transposed:
if not output_padding:
output_padding = stride_minus_kernel_padding(1, strides)
conv = conv_type(
in_channels,
out_channels,
kernel_size=kernel_size,
stride=strides,
padding=padding,
output_padding=output_padding,
groups=groups,
bias=bias,
dilation=dilation,
)
else:
conv = conv_type(
in_channels,
out_channels,
kernel_size=kernel_size,
stride=strides,
padding=padding,
dilation=dilation,
groups=groups,
bias=bias,
)
self.add_module("conv", conv)
if not conv_only:
if norm is not None:
self.add_module("norm", norm_type(out_channels, **norm_args))
if dropout:
self.add_module("dropout", drop_type(**drop_args))
if act is not None:
self.add_module("act", act_type(**act_args))
