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

why does infogan fails to eval? #37

Open
jfojfo opened this issue Jul 24, 2017 · 1 comment
Open

why does infogan fails to eval? #37

jfojfo opened this issue Jul 24, 2017 · 1 comment

Comments

@jfojfo
Copy link

jfojfo commented Jul 24, 2017 •
edited
Loading

I trained on mnist dataset with mnist_info_gan.py, but eval fails to generate proper digit pictures
@jfojfo jfojfo changed the title infogan fails to train without tf.reduce_mean for loss infogan fails to eval without tf.reduce_mean for loss Jul 24, 2017
@jfojfo jfojfo changed the title infogan fails to eval without tf.reduce_mean for loss why does infogan fails to eval? Jul 24, 2017
@jfojfo
Copy link
Author

jfojfo commented Jul 25, 2017

finally found the reason, random_normal should be changed to random_uniform in mnist_info_gan_eval.py!!!

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
1 participant
@jfojfo