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

code for flows on image embeddings #12

Open

saandeepa93 opened this issue Apr 26, 2023 · 0 comments

saandeepa93 commented Apr 26, 2023

Hi, Thanks for your work and code.
Is there any code snippet that reproduces section 8 (figure 5b)?

Currently, if I use EfficientNet embeddings on RealNVPTabular, the log_determinants are very high causing instability in training. Is this an expected behaviour?
Is there any preprocessing required on the image embeddings before feeding it to flow models?

Thanks.

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