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

Finetuning #57

Open
Davidyao99 opened this issue Jun 15, 2024 · 1 comment
Open

Finetuning #57

Davidyao99 opened this issue Jun 15, 2024 · 1 comment

Comments

@Davidyao99
Copy link

Hi, I am hoping to finetune the UniDepth model to a specific video. I tried finetuning all layers of the decoder but it is still relatively slow. Do you have any recommendations for which layers to finetune to minimize training time? Thank you!
@lpiccinelli-eth
Copy link
Owner

I think that you can finetune only the latest layers, namely the self.ups in the depth head and the final projections, namely self.depth_mlp (and optionally self.confidence_mlp.

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
2 participants
@Davidyao99 @lpiccinelli-eth