Skip to content

作者为何不建议直接使用openai 的ViT-B/32 而是要使用laion #104

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

Open
Bruce-W12138 opened this issue Mar 12, 2025 · 1 comment

Comments

@Bruce-W12138
Copy link

非常棒非常优秀的工作,有个问题想向您请假,为什么不直接使用openai的预训练模型而要使用hugging face的ViT-B/32呢?是因为作者有做过相关实验认为如果这样用了效果会没有那么好吗

@Algolzw
Copy link
Owner

Algolzw commented Mar 14, 2025

是的,我们实验发现直接用预训练好的模型提取embedding效果不是很好,具体可以参考论文里figure 9 (c)。

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