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.

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

About SE Reduction ratio? #33

Open
H-YunHui opened this issue Apr 22, 2020 · 1 comment
Open

About SE Reduction ratio? #33

H-YunHui opened this issue Apr 22, 2020 · 1 comment

Comments

@H-YunHui
Copy link

In the original Squeeze-and-Excitation Networks, the author found through experiments that when reduction = 16, precision and complexity are well balanced, and in your module, reduction is set to the current number of bneck output channels , what is the reason for this setting? Did it come from the experiment?

@wangh09
Copy link

wangh09 commented May 4, 2020

In chapter5.3, the original mobilenetv3 paper, it says that the reduction ratio is set to 1/4 (namely 4), as well as in the current implementation

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants