flâneur

matsui528/faiss_tips: Some useful tips for faiss

github.com · 2,651 words · saved by 1 readers

Some useful tips for faiss. Contribute to matsui528/faiss_tips development by creating an account on GitHub.

Faiss tips Some useful tips for faiss We suppose faiss is installed via conda: conda install -c pytorch faiss-cpu conda install -c pytorch -c nvidia faiss-gpu If you want to build faiss from source, see: instruction script example of github actions: [ code ][ result ] If you want to add your class to faiss, see this Nearest neighbor search (CPU) The most basic nearest neighbor search by L2 distance. This is much faster than scipy. You should first try this, especially when the database is relatively small (N<10^6). The search is automatically paralellized. import faiss import numpy as np D = 1

related reading