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

Confused about the generator strcuture of wgan-gp. #1

Open
Un1nU opened this issue Dec 18, 2019 · 0 comments
Open

Confused about the generator strcuture of wgan-gp. #1

Un1nU opened this issue Dec 18, 2019 · 0 comments

Comments

@Un1nU
Copy link

Un1nU commented Dec 18, 2019

Hello, @antoinelouis02 . Thanks for your nice project.

But I have some question about the network structure.

Why the generator is composed of combinations of Upsampling2D and Conv2dTranspose, like

model.add(UpSampling2D())
model.add(Conv2DTranspose(filters=int(depth/2), kernel_size=5, strides=2, padding="same"))

Both UpSampling and ConvTranspose can increase the output size. Why use them at the same time?

And how to determine the depth = 816? Thank you.
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
@Un1nU