mirror of
https://github.com/facebookresearch/faiss.git
synced 2025-06-03 07:50:07 +08:00
a8118acbc5
Changelog: - changed license: BSD+Patents -> MIT - propagates exceptions raised in sub-indexes of IndexShards and IndexReplicas - support for searching several inverted lists in parallel (parallel_mode != 0) - better support for PQ codes where nbit != 8 or 16 - IVFSpectralHash implementation: spectral hash codes inside an IVF - 6-bit per component scalar quantizer (4 and 8 bit were already supported) - combinations of inverted lists: HStackInvertedLists and VStackInvertedLists - configurable number of threads for OnDiskInvertedLists prefetching (including 0=no prefetch) - more test and demo code compatible with Python 3 (print with parentheses) - refactored benchmark code: data loading is now in a single file
58 lines
1.9 KiB
Python
58 lines
1.9 KiB
Python
# Copyright (c) Facebook, Inc. and its affiliates.
|
|
#
|
|
# This source code is licensed under the MIT license found in the
|
|
# LICENSE file in the root directory of this source tree.
|
|
|
|
import numpy as np
|
|
|
|
d = 64 # dimension
|
|
nb = 100000 # database size
|
|
nq = 10000 # nb of queries
|
|
np.random.seed(1234) # make reproducible
|
|
xb = np.random.random((nb, d)).astype('float32')
|
|
xb[:, 0] += np.arange(nb) / 1000.
|
|
xq = np.random.random((nq, d)).astype('float32')
|
|
xq[:, 0] += np.arange(nq) / 1000.
|
|
|
|
import faiss # make faiss available
|
|
|
|
res = faiss.StandardGpuResources() # use a single GPU
|
|
|
|
## Using a flat index
|
|
|
|
index_flat = faiss.IndexFlatL2(d) # build a flat (CPU) index
|
|
|
|
# make it a flat GPU index
|
|
gpu_index_flat = faiss.index_cpu_to_gpu(res, 0, index_flat)
|
|
|
|
gpu_index_flat.add(xb) # add vectors to the index
|
|
print(gpu_index_flat.ntotal)
|
|
|
|
k = 4 # we want to see 4 nearest neighbors
|
|
D, I = gpu_index_flat.search(xq, k) # actual search
|
|
print(I[:5]) # neighbors of the 5 first queries
|
|
print(I[-5:]) # neighbors of the 5 last queries
|
|
|
|
|
|
## Using an IVF index
|
|
|
|
nlist = 100
|
|
quantizer = faiss.IndexFlatL2(d) # the other index
|
|
index_ivf = faiss.IndexIVFFlat(quantizer, d, nlist, faiss.METRIC_L2)
|
|
# here we specify METRIC_L2, by default it performs inner-product search
|
|
|
|
# make it an IVF GPU index
|
|
gpu_index_ivf = faiss.index_cpu_to_gpu(res, 0, index_ivf)
|
|
|
|
assert not gpu_index_ivf.is_trained
|
|
gpu_index_ivf.train(xb) # add vectors to the index
|
|
assert gpu_index_ivf.is_trained
|
|
|
|
gpu_index_ivf.add(xb) # add vectors to the index
|
|
print(gpu_index_ivf.ntotal)
|
|
|
|
k = 4 # we want to see 4 nearest neighbors
|
|
D, I = gpu_index_ivf.search(xq, k) # actual search
|
|
print(I[:5]) # neighbors of the 5 first queries
|
|
print(I[-5:]) # neighbors of the 5 last queries
|