Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

img2col计算卷积对比直接计算卷积是否会高效一点？ #48

Closed
aitaoquanyi opened this issue Jul 27, 2017 · 5 comments
Closed

img2col计算卷积对比直接计算卷积是否会高效一点？ #48

aitaoquanyi opened this issue Jul 27, 2017 · 5 comments

Comments

@aitaoquanyi
Copy link

作者你好：
你的工作非常棒，但是在读你代码时，发现卷积计算方式为传统方式，你也提到直接计算卷积会节省内存，我想请教一下，如果按照img2col展开为矩阵乘法的方式是否会计算效率更高一些？谢谢！
@zsffq999
Copy link

哪个卷积类是基类，针对android的卷积派生类是用汇编写的

@ccJia
Copy link

ccJia commented Aug 7, 2017

@aitaoquanyi 在一些传统的模型里面IM2COL+GEMM的效果还不错( 非separate convolution的情景)，但是在新的 像 mobilenet这样的网络里面，IM2COL会占用掉大多数的时间，甚至大于GEMM的时间，感觉还是要根据实际的网络来定的。

@sunjunlishi
Copy link

sunjunlishi commented Feb 28, 2018 •
edited
Loading

是的img2col的话，速度会提高一倍多（不用多指令加速，不用openblas）

@interqhq
Copy link

@ccJia 赞同你的观点，im2col也是要消耗时间的，要根据实际的特点来采用合适的方法

@ronyuzhang ronyuzhang mentioned this issue Oct 16, 2018
Closed
@nihui
Copy link
Member

nihui commented Feb 25, 2020

最新代码已有 im2col + gemm 的实现

@nihui nihui closed this as completed Feb 25, 2020
@jiefly jiefly mentioned this issue May 13, 2020
Closed
@liuguicen liuguicen mentioned this issue Oct 29, 2021
Closed
@zhu-zhaofei zhu-zhaofei mentioned this issue Dec 19, 2021
Merged
@gmagic10 gmagic10 mentioned this issue May 12, 2022
Open
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
6 participants
@nihui @interqhq @zsffq999 @ccJia @sunjunlishi @aitaoquanyi