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

关于mobilnet v1剪枝的疑问 #5

Open
peterjc123 opened this issue Apr 8, 2021 · 0 comments
Open

关于mobilnet v1剪枝的疑问 #5

peterjc123 opened this issue Apr 8, 2021 · 0 comments

Comments

@peterjc123
Copy link

peterjc123 commented Apr 8, 2021 •
edited
Loading

Hi, 感谢作者分享文章的代码。最近在尝试在mobilnet v1做相关的试验，然后可以看到加载mobilnet模型的函数中，Depthwise Conv是根据接在自己后面的ReLU的输出的秩来选取保留的通道，而普通的Conv则是利用前一个卷积（即Depthwise Conv）的Index来选取输入中的需要保留的通道，而根据接在自己后面的ReLU的输出的秩来选取需保留的输出通道。想问下如此设计的原因是什么？因为我们看到其他的剪枝算法是反过来的，就是Depthwise Conv是根据普通Conv的Index来选取保留的通道。期待您的回答
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
1 participant
@peterjc123