Perform conv2 on a batch of images

2015 8 7
2 个回答
回答已采纳
更新时间：2015 8 7
19 次查看（30 天）

0 个投票

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?

请先登录，再回答此问题。

 采纳的回答

David Young
David Young 2015-8-7

1 个投票

convn does exactly what you describe, given a 3-D array and a 2-D kernel.

1 个评论
显示 -1更早的评论 隐藏 -1更早的评论

Jonathan
Jonathan 2015-8-7
编辑：Jonathan 2015-8-7
Yes, thanks, you are correct. From the docs, it sounded like both kernel and array would need to be of the same dimension.

请先登录，再进行评论。

更多回答（1 个）

Walter Roberson
Walter Roberson 2015-8-7

0 个投票

You can use pagefun() with conv2 with a gpuarray

1 个评论
显示 -1更早的评论 隐藏 -1更早的评论

Jonathan
Jonathan 2015-8-7
Does not work yet with pagefun. However, convn does do the same thing.

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

标签

Community Treasure Hunt

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

Start Hunting!

Translated by