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

What do you mean form "Softmax is internally computed." #17

Closed
ghost opened this issue Apr 3, 2017 · 2 comments
Closed

What do you mean form "Softmax is internally computed." #17

ghost opened this issue Apr 3, 2017 · 2 comments

Comments

@ghost
Copy link

ghost commented Apr 3, 2017

Hi,
Thank you for your great tutorial.

Could you please let me know what you meant from "# Softmax is internally computed." in the this file?
@yunjey
Copy link
Owner

yunjey commented Apr 3, 2017 •
edited

You can see here to understand nn.CrossEntropyLoss.

@yunjey yunjey closed this as completed Apr 4, 2017
@ehsanmok
Copy link

Another (more intuitive) option is to return F.log_softmax(self.linear(inputs)) and use criterion=nn.NLLLoss().

@yunjey yunjey mentioned this issue Jul 20, 2017
Closed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
2 participants
@ehsanmok @yunjey