What metrics does compreface use to compare face similarity? #864
Unanswered
martinenkoEduard
asked this question in
Q&A
Replies: 2 comments 1 reply
-
|
Do I need to use something like faiss.normalize_L2(normalized) |
Beta Was this translation helpful? Give feedback.
1 reply
-
|
I answered it here: |
Beta Was this translation helpful? Give feedback.
0 replies
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Uh oh!
There was an error while loading. Please reload this page.
Uh oh!
There was an error while loading. Please reload this page.
-
What metrics does compreface use to compare face similarity?
Does it use Euclidean distance (L2)? Or something different?
How can I improve search results using milvus?
Is it better to use
Euclidean distance (L2)
or
Inner product (IP)
?
Maybe somehow change vectors(normalize or something else) before inserting to milvus?
What distance metric algorithm compreface uses to compare two faces?
Does it somehow changes vectors?
Beta Was this translation helpful? Give feedback.
All reactions