10000 Model collapse? · Issue #1 · ermongroup/alignflow · GitHub
[go: up one dir, main page]
More Web Proxy on the site http://driver.im/
Skip to content

Model collapse? #1

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

Open
tbuikr opened this issue Feb 25, 2020 · 2 comments
Open

Model collapse? #1

tbuikr opened this issue Feb 25, 2020 · 2 comments

Comments

@tbuikr
Copy link
tbuikr commented Feb 25, 2020

Thanks for your nice work. To run the code, I suggest to correct some typos as bellows:

source activate cflw . --> . source activate aflw

And comment the line

from evaluation.fid import get_fid

I would like to ask you some question related to the project:

  1. Your code implemented "Glow: Generative Flow with Invertible 1×1 Convolutions" , Have you evaluate the performance of generator with different architectures: Glow and RealNVP? I did not find the use case of Glow in the project.

self.g = RealNVP(num_scales=args.num_scales,

  1. I tried to apply cycleflow to the mri brain image with single channel input (gray image). However, the model looks collapse or failure to learning the mapping between domain A and B. The details between regions in the syn. image become blurring, while the cycleGAN still works well. Any suggestion to fix it? Thanks in advance

Screenshot from 2020-02-25 19-00-35
Screenshot from 2020-02-25 19-00-25

@qinglew
Copy link
qinglew commented Nov 15, 2021

How do you group different loss curves into the same group in tensorboardX?

@Moleculebo
Copy link

Do you have solved your mentioned problem? could you give me some suggestions?

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

3 participants
0