Class SegResNetDS

monai/networks/nets/segresnet_ds.py:234–441

SegResNetDS based on `3D MRI brain tumor segmentation using autoencoder regularization `_. It is similar to https://monai.readthedocs.io/en/stable/networks.html#segresnet, with several improvements including deep supervision and non-isotropic ke

class SegResNetDS(nn.Module):
    """
    SegResNetDS based on `3D MRI brain tumor segmentation using autoencoder regularization
    <https://arxiv.org/pdf/1810.11654.pdf>`_.
    It is similar to https://monai.readthedocs.io/en/stable/networks.html#segresnet, with several
    improvements including deep supervision and non-isotropic kernel support.

    Args:
        spatial_dims: spatial dimension of the input data. Defaults to 3.
        init_filters: number of output channels for initial convolution layer. Defaults to 32.
        in_channels: number of input channels for the network. Defaults to 1.
        out_channels: number of output channels for the network. Defaults to 2.
        act: activation type and arguments. Defaults to ``RELU``.
        norm: feature normalization type and arguments. Defaults to ``BATCH``.
        blocks_down: number of downsample blocks in each layer. Defaults to ``[1,2,2,4]``.
        blocks_up: number of upsample blocks (optional).
        dsdepth: number of levels for deep supervision. This will be the length of the list of outputs at each scale level.
                 At dsdepth==1,only a single output is returned.
        preprocess: optional callable function to apply before the model&#x27;s forward pass
        resolution: optional input image resolution. When provided, the network will first use non-isotropic kernels to bring
                    image spacing into an approximately isotropic space.
                    Otherwise, by default, the kernel size and downsampling is always isotropic.

                    **Spatial shape constraints**: If ``resolution`` is ``None`` (isotropic mode),
                    each spatial dimension must be divisible by ``2 ** (len(blocks_down) - 1)``.
                    With the default ``blocks_down=(1, 2, 2, 4)``, each dimension must be
                    divisible by 8. If ``resolution`` is provided (anisotropic mode),
                    divisibility can differ per dimension; use :py:meth:`shape_factor` for
                    the exact required factors and :py:meth:`is_valid_shape` to verify a shape.

                    Example::

                        model = SegResNetDS(spatial_dims=3, blocks_down=(1, 2, 2, 4))
                        print(model.shape_factor())  # [8, 8, 8]
                        print(model.is_valid_shape((1, 1, 128, 128, 128)))  # True
                        print(model.is_valid_shape((1, 1, 100, 100, 100)))  # False

    """

    def __init__(
        self,
        spatial_dims: int = 3,
        init_filters: int = 32,
        in_channels: int = 1,
        out_channels: int = 2,
        act: tuple | str = "relu",
        norm: tuple | str = "batch",
        blocks_down: tuple = (1, 2, 2, 4),
        blocks_up: tuple | None = None,
        dsdepth: int = 1,
        preprocess: nn.Module | Callable | None = None,
        upsample_mode: UpsampleMode | str = "deconv",
        resolution: tuple | None = None,
    ):
        super().__init__()

        if spatial_dims not in (1, 2, 3):
            raise ValueError("`spatial_dims` can only be 1, 2 or 3.")