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

How can I determine that the number given for the mask_strategy parameter is the best? Are there any methods for this? #373

Closed
White-Friday opened this issue May 7, 2024 · 2 comments
Closed

How can I determine that the number given for the mask_strategy parameter is the best? Are there any methods for this? #373

White-Friday opened this issue May 7, 2024 · 2 comments

Comments

@White-Friday
Copy link

No description provided.

@zhengzangw
Copy link
Collaborator

This is only for training. You can see the report for some preliminary results.

@zhengzangw
Copy link
Collaborator

If you want to finetune an image-based model from an already trained one, I would suggest 0.5 for not masking, and 0.5 for the rest. If you want to train from scratch, 0.1/0.2 is enough.

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
@zhengzangw @White-Friday