From 7e2c4b69abbacbb4f86b8d13200c59e1c56d56ee Mon Sep 17 00:00:00 2001 From: Wei Wu Date: Thu, 15 Jun 2017 11:31:40 +0800 Subject: Create simple.md --- doc/simple.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/doc/simple.md b/doc/simple.md index 0fa467b..e18e15d 100755 --- a/doc/simple.md +++ b/doc/simple.md @@ -1548,7 +1548,7 @@ C = model:forward(A) -- C will be of size `b x m` ## PixelShuffle ## ```module = nn.PixelShuffle(r)``` -Rearranges elements in a tensor of shape `[C*r, H, W]` to a tensor of shape `[C, H*r, W*r]`. This is useful for implementing efficient sub-pixel convolution with a stride of `1/r` (see [Shi et. al](https://arxiv.org/abs/1609.05158)). Below we show how the `PixelShuffle` module can be used to learn upscaling filters to transform a low-resolution input to a high resolution one, with a 3x upscale factor. This is useful for tasks such as super-resolution, see ["Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Network" - Shi et al.](https://arxiv.org/abs/1609.05158) for further details. +Rearranges elements in a tensor of shape `[C*r*r, H, W]` to a tensor of shape `[C, H*r, W*r]`. This is useful for implementing efficient sub-pixel convolution with a stride of `1/r` (see [Shi et. al](https://arxiv.org/abs/1609.05158)). Below we show how the `PixelShuffle` module can be used to learn upscaling filters to transform a low-resolution input to a high resolution one, with a 3x upscale factor. This is useful for tasks such as super-resolution, see ["Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Network" - Shi et al.](https://arxiv.org/abs/1609.05158) for further details. ``` upscaleFactor = 3 -- cgit v1.2.3