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

Constant weight scaling? #4

Open

danijar opened this issue Feb 23, 2018 · 0 comments

danijar commented Feb 23, 2018 •

edited

Loading

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

progressive_growing_of_GANs/net.py

Line 42 in 04351d6

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