PixelUnshuffle

class torch.nn.PixelUnshuffle(downscale_factor)

Reverses the PixelShuffle operation by rearranging elements in a tensor of shape $(*, C, H \times r, W \times r)$ to a tensor of shape $(*, C \times r^2, H, W)$, where r is a downscale factor.

See the paper: Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Network by Shi et. al (2016) for more details.

Parameters

downscale_factor (int) – factor to decrease spatial resolution by

Shape:

• Input: $(*, C_{in}, H_{in}, W_{in})$, where * is zero or more batch dimensions

• Output: $(*, C_{out}, H_{out}, W_{out})$, where

$$C_{out} = C_{in} \times \text{downscale\_factor}^2$$

$$H_{out} = H_{in} \div \text{downscale\_factor}$$

$$W_{out} = W_{in} \div \text{downscale\_factor}$$

Examples:

>>> pixel_unshuffle = nn.PixelUnshuffle(3)
>>> input = torch.randn(1, 1, 12, 12)
>>> output = pixel_unshuffle(input)
>>> print(output.size())
torch.Size([1, 9, 4, 4])