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

Explain why tf.nn.softmax isn't used for entropy #13

Closed
mrahtz opened this issue Aug 23, 2017 · 2 comments
Closed

Explain why tf.nn.softmax isn't used for entropy #13

mrahtz opened this issue Aug 23, 2017 · 2 comments

Comments

@mrahtz
Copy link

mrahtz commented Aug 23, 2017

Hello!

Thank you for the wonderful guide! There's one thing I'm confused about: the recipe for entropy uses a manually-defined softmax function instead of tf.nn.softmax. Is there a particular reason for this, or was it just to demonstrate how to implement both numerically-stable softmax and entropy?

Cheers!

@vahidk
Copy link
Owner

vahidk commented Aug 23, 2017

You can use tf.nn.softmax as well, my implementation just allows you to provide a list of dimensions to normalize across instead of a single dim.

@vahidk vahidk closed this as completed Aug 23, 2017
@mrahtz
Copy link
Author

mrahtz commented Aug 24, 2017

Ahh, makes sense. Thanks!

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