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

Is possibile to select which layers to train? #1645

Closed
eric-tc opened this issue Nov 18, 2023 · 1 comment
Closed

Is possibile to select which layers to train? #1645

eric-tc opened this issue Nov 18, 2023 · 1 comment
Labels
3.5.0 Planned The fix is on the roadmap

Comments

@eric-tc
Copy link

eric-tc commented Nov 18, 2023

💡 Your Question

Hi,
thanks for super gradients. I want to know if it is possible to select which layers to train using parameters from a recipe? Like having a list of layers and automatically freezing the other layers not included.

If not can you please give me some hint on how to do this for example with a resnet50 model?
Thanks

Versions

3.4.1
@BloodAxe
Copy link
Contributor

Yes, this will be available in 3.5 release. You can see this PR with a preview what is needed to set this.

@BloodAxe BloodAxe added Planned The fix is on the roadmap 3.5.0 labels Nov 19, 2023
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
3.5.0 Planned The fix is on the roadmap
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
2 participants
@BloodAxe @eric-tc