faiss/demos
Matthijs Douze 9c51bbb977 Fix faiss_contrib (#1478)
Summary:
Fixes the path issue mentioned in https://github.com/facebookresearch/faiss/issues/1472

Pull Request resolved: https://github.com/facebookresearch/faiss/pull/1478

Reviewed By: LowikC

Differential Revision: D24394529

Pulled By: mdouze

fbshipit-source-id: 5e4261a0f271751c736c562514f2ee8604c50702
2020-10-20 04:35:19 -07:00
..
CMakeLists.txt Move build to CMake (#1313) 2020-08-14 15:03:10 -07:00
README.md
demo_auto_tune.py fbshipit-source-id: 4f3cfa59471d548af93fe118d1b73d45bc648edf 2020-08-04 12:00:38 -07:00
demo_client_server_ivf.py Fix faiss_contrib (#1478) 2020-10-20 04:35:19 -07:00
demo_imi_flat.cpp Get rid of non-portable drand48. (#1349) 2020-08-24 00:42:21 -07:00
demo_imi_pq.cpp Get rid of non-portable drand48. (#1349) 2020-08-24 00:42:21 -07:00
demo_ivfpq_indexing.cpp Get rid of non-portable drand48. (#1349) 2020-08-24 00:42:21 -07:00
demo_ondisk_ivf.py Fix faiss_contrib (#1478) 2020-10-20 04:35:19 -07:00
demo_sift1M.cpp
demo_weighted_kmeans.cpp Sync 20200323. (#1157) 2020-03-24 14:06:48 +01:00

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