!EilbSSKJs Jr SSKJr SSKJr SS/r"SS\5r "SS\5r g) N)Tensor)Module PixelShufflePixelUnshufflecj^\rSrSr%SrS/r\\S'S\SS4U4SjjrS\ S\ 4Sjr S\ 4S jr S r U=r$) r aRearrange elements in a tensor according to an upscaling factor. Rearranges elements in a tensor of shape :math:`(*, C \times r^2, H, W)` to a tensor of shape :math:`(*, C, H \times r, W \times r)`, where r is an upscale factor. This is useful for implementing efficient sub-pixel convolution with a stride of :math:`1/r`. See the paper: `Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Network`_ by Shi et al. (2016) for more details. Args: upscale_factor (int): factor to increase spatial resolution by Shape: - Input: :math:`(*, C_{in}, H_{in}, W_{in})`, where * is zero or more batch dimensions - Output: :math:`(*, C_{out}, H_{out}, W_{out})`, where .. math:: C_{out} = C_{in} \div \text{upscale\_factor}^2 .. math:: H_{out} = H_{in} \times \text{upscale\_factor} .. math:: W_{out} = W_{in} \times \text{upscale\_factor} Examples:: >>> pixel_shuffle = nn.PixelShuffle(3) >>> input = torch.randn(1, 9, 4, 4) >>> output = pixel_shuffle(input) >>> print(output.size()) torch.Size([1, 1, 12, 12]) .. _Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Network: https://arxiv.org/abs/1609.05158 upscale_factorreturnNc.>[TU]5 XlgN)super__init__r )selfr __class__s Z/home/mande/repo/quber/.venv/lib/python3.13/site-packages/torch/nn/modules/pixelshuffle.pyrPixelShuffle.__init__6s ,inputcB[R"XR5$z Runs the forward pass. )F pixel_shuffler rrs rforwardPixelShuffle.forward:su&9&9::rc SUR3$)0 Return the extra representation of the module. zupscale_factor=r rs r extra_reprPixelShuffle.extra_repr@s!!4!4 566rr__name__ __module__ __qualname____firstlineno____doc__ __constants__int__annotations__rrrstrr!__static_attributes__ __classcell__rs@rrr sP&P&&M-s-t-;V;; 7C77rcj^\rSrSr%SrS/r\\S'S\SS4U4SjjrS\ S\ 4Sjr S\ 4S jr S r U=r$) rGaReverse the PixelShuffle operation. Reverses the :class:`~torch.nn.PixelShuffle` operation by rearranging elements in a tensor of shape :math:`(*, C, H \times r, W \times r)` to a tensor of shape :math:`(*, 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. Args: downscale_factor (int): factor to decrease spatial resolution by Shape: - Input: :math:`(*, C_{in}, H_{in}, W_{in})`, where * is zero or more batch dimensions - Output: :math:`(*, C_{out}, H_{out}, W_{out})`, where .. math:: C_{out} = C_{in} \times \text{downscale\_factor}^2 .. math:: H_{out} = H_{in} \div \text{downscale\_factor} .. math:: 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]) .. _Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Network: https://arxiv.org/abs/1609.05158 downscale_factorr Nc.>[TU]5 Xlgr )rrr2)rr2rs rrPixelUnshuffle.__init__qs  0rrcB[R"XR5$r)rpixel_unshuffler2rs rrPixelUnshuffle.forwardus  (=(=>>rc SUR3$)rzdownscale_factor=r2r s rr!PixelUnshuffle.extra_repr{s#4#8#8"9::rr9r#r/s@rrrGsP$L((M111?V?? ;C;;r) torch.nn.functionalnn functionalrtorchrmoduler__all__rrrrrBs7 + ,:76:7z8;V8;r