Class ResBlock

monai/networks/blocks/segresnet_block.py:44–96

ResBlock employs skip connection and two convolution blocks and is used in SegResNet based on `3D MRI brain tumor segmentation using autoencoder regularization `_.

class ResBlock(nn.Module):
    """
    ResBlock employs skip connection and two convolution blocks and is used
    in SegResNet based on `3D MRI brain tumor segmentation using autoencoder regularization
    <https://arxiv.org/pdf/1810.11654.pdf>`_.
    """

    def __init__(
        self,
        spatial_dims: int,
        in_channels: int,
        norm: tuple | str,
        kernel_size: int = 3,
        act: tuple | str = ("RELU", {"inplace": True}),
    ) -> None:
        """
        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.
            act: activation type and arguments. Defaults to ``RELU``.
        """

        super().__init__()

        if kernel_size % 2 != 1:
            raise AssertionError("kernel_size should be an odd number.")

        self.norm1 = get_norm_layer(name=norm, spatial_dims=spatial_dims, channels=in_channels)
        self.norm2 = get_norm_layer(name=norm, spatial_dims=spatial_dims, channels=in_channels)
        self.act = get_act_layer(act)
        self.conv1 = get_conv_layer(
            spatial_dims, in_channels=in_channels, out_channels=in_channels, kernel_size=kernel_size
        )
        self.conv2 = get_conv_layer(
            spatial_dims, in_channels=in_channels, out_channels=in_channels, kernel_size=kernel_size
        )

    def forward(self, x):
        identity = x

        x = self.norm1(x)
        x = self.act(x)
        x = self.conv1(x)

        x = self.norm2(x)
        x = self.act(x)
        x = self.conv2(x)

        x += identity

        return x