torch.nn.functional.pixel_unshuffle

torch.nn.functional.pixel_unshuffle(input, downscale_factor) → Tensor

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 the downscale_factor.

See PixelUnshuffle for details.

Parameters

• input (Tensor) – the input tensor
• downscale_factor (int) – factor to increase spatial resolution by

Examples:

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