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

Constant weight scaling? #4

Open
danijar opened this issue Feb 23, 2018 · 0 comments
Open

Constant weight scaling? #4

danijar opened this issue Feb 23, 2018 · 0 comments

Comments

@danijar
Copy link

danijar commented Feb 23, 2018

You are scaling the weights based on the number of incoming activations:

c = tf.constant(np.sqrt(2. / fan_in), dtype=tf.float32)

I think the authors scale adaptively, i.e. change the scale as the learned weights change:

https://github.com/tkarras/progressive_growing_of_gans/blob/3e608722f9588ea135c87e972f2909591e22c3ec/network.py#L281-L284

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

1 participant