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

7 views (last 30 days)
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 Comments
Mohammedee
Mohammedee on 4 Jul 2022
Edited: Mohammedee on 4 Jul 2022
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..

Sign in to comment.

Answers (1)

Matt J
Matt J on 4 Jul 2022
Edited: Matt J on 4 Jul 2022
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 Comments
Matt J
Matt J on 11 Jul 2022
Edited: Matt J on 11 Jul 2022
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

Sign in to comment.

Products


Release

R2021a

Community Treasure Hunt

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

Start Hunting!