powered by
Pixel_shuffle
torch_pixel_shuffle(self, upscale_factor)
(Tensor) the input tensor
(int) factor to increase spatial resolution by
math:(*, C \times r^2, H, W) to a :
(*, C \times r^2, H, W)
Rearranges elements in a tensor of shape \((*, C \times r^2, H, W)\) to a tensor of shape \((*, C, H \times r, W \times r)\).
See ~torch.nn.PixelShuffle for details.
~torch.nn.PixelShuffle
if (torch_is_installed()) { input = torch_randn(c(1, 9, 4, 4)) output = nnf_pixel_shuffle(input, 3) print(output$size()) }
Run the code above in your browser using DataLab