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

end to end training #6

Open
VladKatsman opened this issue Nov 18, 2024 · 0 comments
Open

end to end training #6

VladKatsman opened this issue Nov 18, 2024 · 0 comments

Comments

@VladKatsman
Copy link

VladKatsman commented Nov 18, 2024 •
edited
Loading

Guys, thank you for your paper and code.

The question is, if there any possibility for end to end efficient training. I mean train backbone (feature extractor) as well?

Would you suggest any efficient training scheme like next example:
training backbone first -> freeze backbone -> train g-cmvae -> unfreeze backbone -> finetune everything with smaller lr?
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
@VladKatsman