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

Batch normalization layer #13

Open
cbovar opened this issue Dec 29, 2016 · 6 comments
Open

Batch normalization layer #13

cbovar opened this issue Dec 29, 2016 · 6 comments
Labels
new feature

Comments

@cbovar
Copy link
Owner

cbovar commented Dec 29, 2016

No description provided.

@cbovar cbovar mentioned this issue May 18, 2017
Open
@lostmsu
Copy link

lostmsu commented May 24, 2017

Just curious, with the current version, can I even do minibatches?

@lostmsu
Copy link

lostmsu commented May 24, 2017

All right, from Classify2DDemo I guess I just need to set the last parameter of Volume's Shape to number of items in the minibatch. Can you confirm that?

@cbovar
Copy link
Owner Author

cbovar commented May 24, 2017

Yes you can do mini batch. And you are correct: the 4th dimension of the Shape is the batch size

@lostmsu
Copy link

lostmsu commented May 24, 2017

@cbovar IMHO, you should mention that in README. Seems like an important detail.

@idow09
Copy link
Contributor

idow09 commented Apr 12, 2020

Any plans on implementing this feature anytime soon?

@cbovar
Copy link
Owner Author

cbovar commented Apr 12, 2020

I'm not planning on implementing it any time soon. But PR are welcome of course :)

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
new feature
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
3 participants
@lostmsu @cbovar @idow09