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

to do when coming back from vacation #39

Open

dalessioluca opened this issue Aug 28, 2020 · 0 comments

Collaborator

dalessioluca commented Aug 28, 2020 •

edited

Loading

I have to:

Increase encoder from 28x28 to 56x56
encode the background in a small latent variable
change factor_balance_range: [0.1, 0.8, 0.9]
Monitor the 3 different term in sparsity
Since I have sparsity (which constraint the number of pixels) maybe I can just sum the KL together without rescaling?!

the real deal is to use multi-objective optimization instead of GECO
test that encoder/decoder are powerfull enough. For that I can create a dataset of isolated cells

use Neptune
reduce channels after UNET to 2 (one should be the original image, the other something else)

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