Debian Codegraph @

tutorial/python/7-PQFastScan.py

raw
1 # Copyright (c) Meta Platforms, Inc. and affiliates.
2 #
3 # This source code is licensed under the MIT license found in the
4 # LICENSE file in the root directory of this source tree.
5
6 import faiss
7 import numpy as np
8
9 d = 64 # dimension
10 nb = 100000 # database size
11 nq = 10000 # nb of queries
12 np.random.seed(1234) # make reproducible
13 xb = np.random.random((nb, d)).astype('float32') # 64-dim *nb queries
14 xb[:, 0] += np.arange(nb) / 1000.
15 xq = np.random.random((nq, d)).astype('float32')
16 xq[:, 0] += np.arange(nq) / 1000.
17
18 m = 8 # 8 specifies that the number of sub-vector is 8
19 k = 4 # number of dimension in extracted vector
20 n_bit = 4 # 4 specifies that each sub-vector is encoded as 4 bits
21 bbs = 32 # build block size ( bbs % 32 == 0 ) for PQ
22 index = faiss.IndexPQFastScan(d, m, n_bit, faiss.METRIC_L2, bbs)
23 # construct FastScan Index
24
25 assert not index.is_trained
26 index.train(xb) # Train vectors data index within mockup database
27 assert index.is_trained
28
29 index.add(xb)
30 D, I = index.search(xb[:5], k) # sanity check
31 print(I)
32 print(D)
33 index.nprobe = 10 # make comparable with experiment above
34 D, I = index.search(xq, k) # search
35 print(I[-5:]) # neighbors of the 5 last queries