bb4c987b5c
Summary: Pull Request resolved: https://github.com/facebookresearch/faiss/pull/2283 This is a demonstration for: - how to use a distance computer to compute query-to-code distances with a residual quantizer - how to construct a ResidualCoarseQuantizer that uses a prefix of residalquantizer codes See related doc https://docs.google.com/document/d/1g97lrMXVYh5FcQzw23v_sUE22ybHfCFxtbHyFJwxKKE/edit?usp=sharing Reviewed By: alexanderguzhva Differential Revision: D34958088 fbshipit-source-id: edb06ee350de67f855e96ae57a3862fbf14f6e54 |
||
|---|---|---|
| .. | ||
| CMakeLists.txt | ||
| README.md | ||
| demo_auto_tune.py | ||
| demo_client_server_ivf.py | ||
| demo_imi_flat.cpp | ||
| demo_imi_pq.cpp | ||
| demo_ivfpq_indexing.cpp | ||
| demo_nndescent.cpp | ||
| demo_ondisk_ivf.py | ||
| demo_residual_quantizer.cpp | ||
| demo_sift1M.cpp | ||
| demo_weighted_kmeans.cpp | ||
README.md
Demos for a few Faiss functionalities
demo_auto_tune.py
Demonstrates the auto-tuning functionality of Faiss
demo_ondisk_ivf.py
Shows how to construct a Faiss index that stores the inverted file data on disk, eg. when it does not fit in RAM. The script works on a small dataset (sift1M) for demonstration and proceeds in stages:
0: train on the dataset
1-4: build 4 indexes, each containing 1/4 of the dataset. This can be done in parallel on several machines
5: merge the 4 indexes into one that is written directly to disk (needs not to fit in RAM)
6: load and test the index