faiss/demos
Lucas Hosseini ac74f576f7 fbshipit-source-id: 4f3cfa59471d548af93fe118d1b73d45bc648edf 2020-08-04 12:00:38 -07:00
..
Makefile Facebook sync (May 2019) + relicense (#838) 2019-05-28 16:17:22 +02:00
README.md
demo_auto_tune.py fbshipit-source-id: 4f3cfa59471d548af93fe118d1b73d45bc648edf 2020-08-04 12:00:38 -07:00
demo_client_server_ivf.py Facebook sync 2020-07-31 (#1308) 2020-08-03 22:15:02 +02:00
demo_imi_flat.cpp Facebook sync (May 2019) + relicense (#838) 2019-05-28 16:17:22 +02:00
demo_imi_pq.cpp Facebook sync (May 2019) + relicense (#838) 2019-05-28 16:17:22 +02:00
demo_ivfpq_indexing.cpp Facebook sync (2019-09-10) (#943) 2019-09-20 18:59:10 +02:00
demo_ondisk_ivf.py fbshipit-source-id: 4f3cfa59471d548af93fe118d1b73d45bc648edf 2020-08-04 12:00:38 -07:00
demo_sift1M.cpp Update demo_sift1M.cpp 2019-11-19 11:18:47 +01:00
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