Class SubpixelUpsample

monai/networks/blocks/upsample.py:192–293

Upsample via using a subpixel CNN. This module supports 1D, 2D and 3D input images. The module is consisted with two parts. First of all, a convolutional layer is employed to increase the number of channels into: ``in_channels * (scale_factor ** dimensions)``. Secondly, a pixel shuf

class SubpixelUpsample(nn.Module):
    """
    Upsample via using a subpixel CNN. This module supports 1D, 2D and 3D input images.
    The module is consisted with two parts. First of all, a convolutional layer is employed
    to increase the number of channels into: ``in_channels * (scale_factor ** dimensions)``.
    Secondly, a pixel shuffle manipulation is utilized to aggregates the feature maps from
    low resolution space and build the super resolution space.
    The first part of the module is not fixed, a sequential layers can be used to replace the
    default single layer.

    See: Shi et al., 2016, "Real-Time Single Image and Video Super-Resolution
    Using an Efficient Sub-Pixel Convolutional Neural Network."

    See: Aitken et al., 2017, "Checkerboard artifact free sub-pixel convolution".

    The idea comes from:
    https://arxiv.org/abs/1609.05158

    The pixel shuffle mechanism refers to:
    https://pytorch.org/docs/stable/generated/torch.nn.PixelShuffle.html#torch.nn.PixelShuffle.
    and:
    https://github.com/pytorch/pytorch/pull/6340.

    """

    def __init__(
        self,
        spatial_dims: int,
        in_channels: int | None,
        out_channels: int | None = None,
        scale_factor: int = 2,
        conv_block: nn.Module | str | None = "default",
        apply_pad_pool: bool = True,
        bias: bool = True,
    ) -> None:
        """
        Args:
            spatial_dims: number of spatial dimensions of the input image.
            in_channels: number of channels of the input image.
            out_channels: optional number of channels of the output image.
            scale_factor: multiplier for spatial size. Defaults to 2.
            conv_block: a conv block to extract feature maps before upsampling. Defaults to None.

                - When ``conv_block`` is ``"default"``, one reserved conv layer will be utilized.
                - When ``conv_block`` is an ``nn.module``,
                  please ensure the output number of channels is divisible ``(scale_factor ** dimensions)``.

            apply_pad_pool: if True the upsampled tensor is padded then average pooling is applied with a kernel the
                size of `scale_factor` with a stride of 1. This implements the nearest neighbour resize convolution
                component of subpixel convolutions described in Aitken et al.
            bias: whether to have a bias term in the default conv_block. Defaults to True.

        """
        super().__init__()

        if scale_factor <= 0:
            raise ValueError(f"The `scale_factor` multiplier must be an integer greater than 0, got {scale_factor}.")