+ &jld^RIHuHt^RIHt^RIHtRR.t!RR]4t !RR]4t R#)NTensor)Module PixelShufflePixelUnshufflecxaa]tRt^ toRtR.tV3RlV3RlltV3RlRltV3RlRltV3R lt R t Vt V;t #) raRearrange 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_factorc$<V^8dQhRS[RR/#)r returnNint)format __classdict__s"u/Users/jameslopez/projects/CWCArchive/cwc-podcast/.venv/lib/python3.14/site-packages/torch/nn/modules/pixelshuffle.py __annotate__PixelShuffle.__annotate__6s--s-t-c0<\SV`4WnR#N)super__init__r )selfr __class__s&&rrPixelShuffle.__init__6s ,rc&<V^8dQhRS[RS[/#r inputr r)rrs"rrr:s;;V;;rc B\P!WP4#z Runs the forward pass. )F pixel_shuffler rrs&&rforwardPixelShuffle.forward:su&9&9::rc <V^8dQhRS[/#r r str)rrs"rrr@s77C7rc RVP 2#)0 Return the extra representation of the module. zupscale_factor=r rs&r extra_reprPixelShuffle.extra_repr@s!!4!4 566rc&<V^8dQh/S[;R&#)r r r )rrs"rrr sTUrr, __name__ __module__ __qualname____firstlineno____doc__ __constants__rr$r.__annotate_func____static_attributes____classdictcell__ __classcell__rrs@@rrr s;&P&&M--;; 77mrcxaa]tRt^GtoRtR.tV3RlV3RlltV3RlRltV3RlRltV3R lt R t Vt V;t #) raReverse 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_factorc$<V^8dQhRS[RR/#)r r>r Nr )rrs"rrPixelUnshuffle.__annotate__qs1111rc0<\SV`4WnR#r)rrr>)rr>rs&&rrPixelUnshuffle.__init__qs  0rc&<V^8dQhRS[RS[/#rr)rrs"rrr@us??V??rc B\P!WP4#r )r!pixel_unshuffler>r#s&&rr$PixelUnshuffle.forwardus  (=(=>>rc <V^8dQhRS[/#r'r()rrs"rrr@{s;;C;rc RVP 2#)r+zdownscale_factor=r>r-s&rr.PixelUnshuffle.extra_repr{s#4#8#8"9::rc&<V^8dQh/S[;R&#)r r>r )rrs"rrr@GsPQrrIr1r<s@@rrrGs;$L((M11?? ;;ir) torch.nn.functionalnn functionalr!torchrmoduler__all__rrrrrSs7 + ,:76:7z8;V8;r