Args: spatial_dims: number of spatial dimensions, could be 1, 2 or 3. in_channels: number of input channels. norm: feature normalization type and arguments. kernel_size: convolution kernel size, the value should be an odd number. Defaults to 3
(
self,
spatial_dims: int,
in_channels: int,
norm: tuple | str,
kernel_size: int = 3,
act: tuple | str = ("RELU", {"inplace": True}),
)
| 49 | """ |
| 50 | |
| 51 | def __init__( |
| 52 | self, |
| 53 | spatial_dims: int, |
| 54 | in_channels: int, |
| 55 | norm: tuple | str, |
| 56 | kernel_size: int = 3, |
| 57 | act: tuple | str = ("RELU", {"inplace": True}), |
| 58 | ) -> None: |
| 59 | """ |
| 60 | Args: |
| 61 | spatial_dims: number of spatial dimensions, could be 1, 2 or 3. |
| 62 | in_channels: number of input channels. |
| 63 | norm: feature normalization type and arguments. |
| 64 | kernel_size: convolution kernel size, the value should be an odd number. Defaults to 3. |
| 65 | act: activation type and arguments. Defaults to ``RELU``. |
| 66 | """ |
| 67 | |
| 68 | super().__init__() |
| 69 | |
| 70 | if kernel_size % 2 != 1: |
| 71 | raise AssertionError("kernel_size should be an odd number.") |
| 72 | |
| 73 | self.norm1 = get_norm_layer(name=norm, spatial_dims=spatial_dims, channels=in_channels) |
| 74 | self.norm2 = get_norm_layer(name=norm, spatial_dims=spatial_dims, channels=in_channels) |
| 75 | self.act = get_act_layer(act) |
| 76 | self.conv1 = get_conv_layer( |
| 77 | spatial_dims, in_channels=in_channels, out_channels=in_channels, kernel_size=kernel_size |
| 78 | ) |
| 79 | self.conv2 = get_conv_layer( |
| 80 | spatial_dims, in_channels=in_channels, out_channels=in_channels, kernel_size=kernel_size |
| 81 | ) |
| 82 | |
| 83 | def forward(self, x): |
| 84 | identity = x |
nothing calls this directly
no test coverage detected