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

Gradual unfreezing the layers during training. #9677

Closed
2 tasks done
senhorinfinito opened this issue Oct 3, 2022 · 1 comment
Closed
2 tasks done

Gradual unfreezing the layers during training. #9677

senhorinfinito opened this issue Oct 3, 2022 · 1 comment
Labels
enhancement New feature or request

Comments

@senhorinfinito
Copy link
Contributor

Search before asking

  • I have searched the YOLOv5 issues and found no similar feature requests.

Description

In ULMFIT three things they have proposed to the fine-tune the model

  1. Slanted triangular learning rate.
  2. gradual unfreezing
  3. discriminative fine tuning.

I wanted to implement only gradual unfreezing.

Use case

Unfreezing the layers in the middle of training, a specific epoch.

Additional

No response

Are you willing to submit a PR?

  • Yes I'd like to help by submitting a PR!
@senhorinfinito senhorinfinito added the enhancement New feature or request label Oct 3, 2022
@glenn-jocher
Copy link
Member

glenn-jocher commented Oct 3, 2022 •
edited
Loading

@senhorinfinito see Transfer Learning with Frozen Layers tutorial below.

Tutorials

Good luck 🍀 and let us know if you have any other questions!

@senhorinfinito senhorinfinito mentioned this issue Oct 3, 2022
Closed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
enhancement New feature or request
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
2 participants
@glenn-jocher @senhorinfinito