why do we need to flip kernel before using conv2 in CNN?

2022 7 4
1 个回答
更新时间：2022 7 11
8 次查看（30 天）

0 个投票

We know that function conv2 can prefom convolution (between image and kernel ) and flip kernel before apply convolution to image according to defnition of convolution
y = conv2(image, kernel, 'valid')
.However, in convolution neural network(CNN) ,they flip the kernel before the use conv2
kernel = rot90(kernel, 2);
y = conv2(image, kernel, 'valid');
which means the kernel flip twice and this correlation not convolution why

3 个评论
显示 1更早的评论 隐藏 1更早的评论

Jonas
Jonas 2022-7-4
编辑：Jonas 2022-7-4
not that 90° is not flipped, flipping would be rotation by 180 degress or using flipud(fliplr())
and where exactly did you find this code (file, line number)
Mohammedee
Mohammedee 2022-7-4
function y = Conv(x, W) % % [wrow, wcol, numFilters] = size(W); [xrow, xcol, ~ ] = size(x); yrow = xrow - wrow + 1; ycol = xcol - wcol + 1; y = zeros(yrow, ycol, numFilters); for k = 1:numFilters filter = W(:, :, k); filter = rot90(squeeze(filter), 2); y(:, :, k) = conv2(x, filter, 'valid'); end end
Mohammedee
Mohammedee 2022-7-4
编辑：Mohammedee 2022-7-4
Look to this code..kernel rotated 180 Then pass it to conv2 And we know that conv2 will rotate kernel 180 again... This mean kernel rotated twice 180..

请先登录，再进行评论。

请先登录，再回答此问题。

回答（1 个）

Matt J
Matt J 2022-7-4
编辑：Matt J 2022-7-4

0 个投票

The field of neural networks uses the term "convolution" loosely. There are other differences as well. We also know that in traditional DSP theory, convolution operations don't contain a stride parameter, but in the NN world, they do.

5 个评论
显示 3更早的评论 隐藏 3更早的评论

Matt J
Matt J 2022-7-10
编辑：Matt J 2022-7-10
Basically, neural networks researchers are not using the terminology "convolution" in the classical way. A true convolution in the original sense of the word should include a flip and should never have stride>1. That's the way convolution was originally defined. Without the flip, it should be called correlation, as you say.
Mohammedee
Mohammedee 2022-7-10
编辑：Mohammedee 2022-7-10
http://ufldl.stanford.edu/tutorial/supervised/ExerciseConvolutionAndPooling/
In this link i find other related answer but also not clear they said:
If you use conv2(image, W), MATLAB will first "flip" W, reversing its rows and columns, before convolving W with image, as below:
⎛⎝⎜147258369⎞⎠⎟−→−flip⎛⎝⎜963852741⎞⎠⎟(123456789)→flip(987654321)
If the original layout of W was correct, after flipping, it would be incorrect. For the layout to be correct after flipping, you will have to flip W before passing it into conv2, so that after MATLAB flips W in conv2, the layout will be correct. For conv2, this means reversing the rows and columns, which can be done by rotating W 90 degrees twice with rot90 as shown below:
Mohammedee
Mohammedee 2022-7-10
编辑：Mohammedee 2022-7-10
The answer here but i do understand that W will be not corrected after flipping.. Thus u have to flip before use. Conv2
(If the original layout of W was correct, after flipping, it would be incorrect. For the layout to be correct after flipping, you will have to flip W before passing it into conv2, so that after MATLAB flips W in conv2, the layout will be correct)
Matt J
Matt J 2022-7-11
编辑：Matt J 2022-7-11
Ran in:
Ran in:
If you use conv2(image, W), MATLAB will first "flip" W, reversing its rows and columns
Yes, conv2 will flip W internally and that is the correct thing for it to do, because that is the way convolution is defined. This definition ensures that conv2(1,W) = W. Example:
W=[1 2;3 4]
W = 2×2
1 2 3 4
conv2(1,W)
ans = 2×2
1 2 3 4
If you were to flip W manually, prior to giving it to conv2, it would mess this up:
conv2(1,rot90(W,2))
ans = 2×2
4 3 2 1

请先登录，再进行评论。

类别

在 帮助中心 和 File Exchange 中查找有关 Image Arithmetic 的更多信息

产品

版本

R2021a

标签

编辑：

Matt J
Matt J
2022-7-11

Community Treasure Hunt

Find the treasures in MATLAB Central and discover how the community can help you!

Start Hunting!

Translated by