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

how to apply in InceptionV3 #11

Open

fuchao01 opened this issue Feb 5, 2021 · 1 comment

fuchao01 commented Feb 5, 2021

how to apply in InceptionV3

Collaborator

nmaac commented Feb 5, 2021

Hi @fuchao01 , the procedure of applying in InceptionV3 is the same as the other networks:

I would not suggest to replace all of them which would not only affect the speed but also cause overfitting problem.
I would suggest to first only replace one ReLU in each bottleneck (e.g.this one) which is supposed to see improvements, then you can gradually add more to achieve an optimum speed-accuracy trade-off.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment