-
Notifications
You must be signed in to change notification settings - Fork 868
update PixelShuffle api #5192
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
update PixelShuffle api #5192
Conversation
|
感谢你贡献飞桨文档,文档预览构建中,Docs-New 跑完后即可预览,预览链接:http://preview-pr-5192.paddle-docs-preview.paddlepaddle.org.cn/documentation/docs/zh/api/index_cn.html |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
整体上没啥问题,改下小问题应该就可以了~
| 给定一个形为 x.shape = [1, 9, 4, 4] 的 4-D 张量 | ||
| 设定:upscale_factor=3 | ||
| 那么输出张量的形为:[1, 1, 12, 12] | ||
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
下同(nn.functional.pixel_shuffle)
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
英文也要改一下~
|
|
||
| .. py:function:: paddle.nn.PixelShuffle(upscale_factor, data_format="NCHW", name=None) | ||
| 该算子将一个形为[N, C, H, W]或是[N, H, W, C]的 Tensor 重新排列成形为 [N, C/r**2, H*r, W*r]或 [N, H*r, W*r, C/r**2] 的 Tensor。这样做有利于实现步长(stride)为 1/r 的高效 sub-pixel(亚像素)卷积。详见 Shi 等人在 2016 年发表的论文 `Real Time Single Image and Video Super Resolution Using an Efficient Sub Pixel Convolutional Neural Network <https://arxiv.org/abs/1609.05158v2>`_ 。 | ||
| 该算子将一个形为 :math:`[N, C, H, W]` 或是 :math:`[N, H, W, C]` 的 Tensor 重新排列成形为 :math:`[N, C/r**2, H*r, W*r]` 或 :math:`[N, H*r, W*r, C/r**2]` 的 Tensor。这样做有利于实现步长(stride)为 :math:`1/r` 的高效 sub-pixel(亚像素)卷积。详见 Shi 等人在 2016 年发表的论文 `Real Time Single Image and Video Super Resolution Using an Efficient Sub Pixel Convolutional Neural Network <https://arxiv.org/abs/1609.05158v2>`_ 。 |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
LGTM~~~~~
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
good job!LGTM
* update PixelShuffle api * udpate format issue * update format issue * udpate format issue * copy-from RReLU Co-authored-by: Ligoml <39876205+Ligoml@users.noreply.github.com>




fix some format issue
PADDLEPADDLE_PR=45423
PADDLEPADDLE_PR : PaddlePaddle/Paddle#45423