U 9%e @sPddlmZddlmZddlmZddgZGdddeZGd ddeZ d S) )Module) functional)Tensor PixelShufflePixelUnshufflecsVeZdZUdZdgZeed<eddfdd Zeeddd Z e d d d Z Z S) ra 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_factorN)r returncst||_dSN)super__init__r )selfr  __class__\/var/www/html/Darija-Ai-API/env/lib/python3.8/site-packages/torch/nn/modules/pixelshuffle.pyr 1s zPixelShuffle.__init__inputr cCst||jSr )FZ pixel_shuffler rrrrrforward5szPixelShuffle.forwardr cCs d|jS)Nzupscale_factor=)r rrrr extra_repr8szPixelShuffle.extra_repr __name__ __module__ __qualname____doc__Z __constants__int__annotations__r rrstrr __classcell__rrrrrs %csVeZdZUdZdgZeed<eddfdd Zeeddd Z e d d d Z Z S) raReverses 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_factorN)r$r cst||_dSr )r r r$)rr$rrrr cs zPixelUnshuffle.__init__rcCst||jSr )rZpixel_unshuffler$rrrrrgszPixelUnshuffle.forwardrcCs d|jS)Nzdownscale_factor=)r$rrrrrjszPixelUnshuffle.extra_reprrrrrrr<s #N) modulerrrZtorchr__all__rrrrrrs   4