Perform conv2 on a batch of images

6 ビュー (過去 30 日間)
Jonathan
Jonathan 2015 年 8 月 7 日
編集済み: Jonathan 2015 年 8 月 7 日
I have a set of 2D images for which I would like to convolve each image separately with a kernel. This is particularly important for GPU acceleration because doing the convolution one at a time with a for loop is much slower.
Ideally, conv2(A,B) would be written such as A can be a 3D matrix (m x n p), where p is the number of separate 2D arrays to perform the convolution with B on.
Is there any way in Matlab to do such a thing currently, or would I need to write my own mex function?

採用された回答

David Young
David Young 2015 年 8 月 7 日
convn does exactly what you describe, given a 3-D array and a 2-D kernel.
  1 件のコメント
Jonathan
Jonathan 2015 年 8 月 7 日
編集済み: Jonathan 2015 年 8 月 7 日
Yes, thanks, you are correct. From the docs, it sounded like both kernel and array would need to be of the same dimension.

サインインしてコメントする。

その他の回答 (1 件)

Walter Roberson
Walter Roberson 2015 年 8 月 7 日
You can use pagefun() with conv2 with a gpuarray
  1 件のコメント
Jonathan
Jonathan 2015 年 8 月 7 日
Does not work yet with pagefun. However, convn does do the same thing.

サインインしてコメントする。

カテゴリ

Help Center および File ExchangeConvert Image Type についてさらに検索

Community Treasure Hunt

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

Start Hunting!

Translated by