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

Changing the latent map sizes #61

Open
SURABHI-GUPTA opened this issue Jan 23, 2021 · 3 comments
Open

Changing the latent map sizes #61

SURABHI-GUPTA opened this issue Jan 23, 2021 · 3 comments

Comments

@SURABHI-GUPTA
Copy link

@rosinality Hi. I am looking for a more compact representation, so I tried to reduce the latent map size by half, i.e top one now corresponds to 16x16 and the bottom one corresponds to 32X32. I tried to add more conv layers. I am attaching the screenshot of my model. Can you tell me whether this makes sense?
with_top_ls_16X16_bot_ls_32X32

@rosinality
Copy link
Owner

Why not?

@SURABHI-GUPTA
Copy link
Author

@rosinality I mean the architecture that I have attached above is okay or not?

@rosinality
Copy link
Owner

It seems like that what you have changed is to add 1 more stride 2 conv and conv transpose layers. Then it will be valid. But how it will work is the another problem.

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

2 participants