-
Notifications
You must be signed in to change notification settings - Fork 130
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
Have you ever tried batch normalization? #20
Comments
Please also add BN after fc5. I've tried that. It could converge. |
Actually I have tried added BN after fc5 and fc6 (Maybe fc6 is not necessary to normalize), but the loss is still 87.3365. What is your learning rate? I will try to remove the BN after fc6, so keep this issue open:) |
I have added BN after fc5, but the loss is still 87.3365. I also tried to reduce the learning rate to 0.01, but still not work. Any advise? thank you |
ok. it seems that there are some problems with my own folk caffe. Now problem solved. |
@happynear
I tried to add batch normalization on your modified resnet20, but the loss became 87.3365. As far as I know, BN helps learning more quickly, Is it possible to add batch normalization with amsoftmax?
Here is the prototxt
The text was updated successfully, but these errors were encountered: