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 did not use Conv2DTranspose rather than Conv2D in the generator #24

Open

lestel opened this issue Mar 8, 2018 · 1 comment

lestel commented Mar 8, 2018 •

edited

the related paper all say they use Conv2DTranspose

NagabhushanSN95 commented Jul 31, 2019

Yes. That is one of their key contributions.
They say to

use strided convolutions instead of max-pooling layer
use cond2dTranspose instead of upsampling
use batch normalization layers
use relu activations for intermediate layers

@jacobgil You've implemented none of those. So, this is not DC GAN right?

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment