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

9 ビュー (過去 30 日間)
Mohammedee
Mohammedee 2022 年 7 月 4 日
編集済み: Matt J 2022 年 7 月 11 日 22:06
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 件のコメント
Mohammedee
Mohammedee 2022 年 7 月 4 日
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..

サインインしてコメントする。

回答 (1 件)

Matt J
Matt J 2022 年 7 月 4 日
編集済み: Matt J 2022 年 7 月 4 日
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 件のコメント
Matt J
Matt J 2022 年 7 月 11 日 21:55
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

サインインしてコメントする。

製品


リリース

R2021a

Community Treasure Hunt

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

Start Hunting!

Translated by