Closed Dr-Left closed 1 week ago
Any insights? Why this would happen? Did I make it wrong on some parameters?
The index_factory enables polysemous code training by default. You can disable it with "IVF400,PQ8np"
Thank you. I get it.
Btw, what are the advantages of using polysemous code? Will the searching process be accelerated?
Summary
When I build indexes by
faiss.index_factory(n, "IVF400,PQ8")
and do the training byfaiss.train(xb)
, the training process of those are much slower than that of indexes built by ` the indexes built byn
is 128 in my case.Results:
Platform
OS: Linux CPU: AMD EPYC 7742 64-Core Processor x86_64
Faiss version: 1.8.0.post1
Installed from: pip install
Faiss compilation options: Default
Running on:
Interface:
Reproduction instructions
Python 3.9.19 https://gist.github.com/Dr-Left/cb38037ef4784764b600ff669672f4ca