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.

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

Why choose the top 9 high-confidence categories instead of 5, 6, or any other number? #7

Open
wujiang0156 opened this issue Apr 3, 2024 · 1 comment

Comments

@wujiang0156
Copy link

You retrieved the top 9 high-confidence categories to assemble text prompts for foreground and background features, resulting in better training outcomes. Why choose 9? What would happen if you chose a different number of confidence levels?

Looking forward to your response.

@dyzy41
Copy link
Owner

dyzy41 commented Apr 4, 2024

"I haven't extensively tested the set of 9 here, but in reality, you can try other parameters for comparative experiments. However, I don't think it's necessary because this set of 9 is not the focus of the article, and discovering the optimal N is not an innovative research approach. You should try to design a better scheme for text description of variations."

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants