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

怎么才能快速用几张图片在大概100w张50*50的图片里搜索相似的图 ? #45

Open
jliartem opened this issue Dec 6, 2024 · 3 comments
Open

怎么才能快速用几张图片在大概100w张50*50的图片里搜索相似的图 ? #45

jliartem opened this issue Dec 6, 2024 · 3 comments
Labels
question Further information is requested

Comments

@jliartem
Copy link

jliartem commented Dec 6, 2024

大概试了下，如果直接用ClipSimilarity的similarity()的话大概需要持续运行3天的时间... 有没有什么办法加速?
@jliartem jliartem added the question Further information is requested label Dec 6, 2024
@shibing624
Copy link
Owner

这是计算emb的耗时比较长，你可以用多机多卡的gpu机器跑emb，再用faiss的index检索。

@jliartem
Copy link
Author

jliartem commented Dec 7, 2024

就是在faiss_clip_search_server_demo.py这个demo里的方式吗? 也就是说先预处理图片的emp数据然后创建index, 这样在检索的时候就能比较快速得到结果

@shibing624
Copy link
Owner

是

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
question Further information is requested
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
2 participants
@shibing624 @jliartem