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
Wrong searching result #784
Labels
Comments
Why the distance caluclated in faiss not same with L2 calculated in python?
the distance will never be 6.2 since they are all less than 1... |
Even using sum of square, the result still not the same |
You messed up the array indexing. When you display the result vector it should be
|
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
I test with a tiny example, search the closest 5 records from 10000 database of 3 to query records, the codes like this:
It gives me result, 3 to query records all got top 5 searching result, but when I calculate their distance between to query and result, they are not quite well sorted:
Abviously, the distance are not the closest, the distance I calculate is simply norm distance (L2 norm which is Euclidian distance).
What could be the problem?
The text was updated successfully, but these errors were encountered: