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

I complete the SN by Keras. welcome to advice #6

Open
Bingohong opened this issue Jul 13, 2018 · 2 comments
Open

I complete the SN by Keras. welcome to advice #6

Bingohong opened this issue Jul 13, 2018 · 2 comments

Comments

@Bingohong
Copy link

location in SN by Keras

@pluo911
Copy link
Collaborator

pluo911 commented Jul 13, 2018

Thanks for your interest. SN benefits from adding 0.5 dropout in the last layer of hidden features, but GN and BN might not. The improvement depends on the generation error (val_err - train_err) of your problem. The training time of SN can be improved by using CUDA. We may release this implementation in the future.

@Bingohong
Copy link
Author

thanks to apply the dropout trick. i expect the CUDA accelerated version.

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