mirror of
https://github.com/facebookresearch/faiss.git
synced 2026-10-11 22:50:00 +00:00
Tia Lim
0f0f728166
Summary: Pull Request resolved: https://github.com/facebookresearch/faiss/pull/5349 # this is a no-op change Ran `black -l 80` over all tracked Python files under `fbcode/faiss/`, using line length 80 to match faiss's documented coding style (`CONTRIBUTING.md`: "80 character line length (both for C++ and Python)"). 172 files were reformatted; 28 were already compliant. This is a pure-formatting change. `black` runs its AST-equivalence safety check on every file, so no identifiers, string/numeric values, operators, or control flow were altered — only whitespace, indentation, line wrapping, blank lines, trailing commas, and string-quote normalization (single to double quotes). `fbcode/faiss/` is intentionally excluded from Meta's standard Python autoformatter (`arc f` / `arc lint -a` report no formatter for these paths) because it mirrors to public GitHub, so the Python had drifted out of any consistent style. The C++ is already clang-format-clean (0 of 807 files change), so this effort is Python-only. This diff brings the Python to canonical `black` formatting. Excluded `demos/index_pq_flat_separate_codes_from_codebook.py`: it contains a Jupyter `!rm` shell-magic line and is not valid Python, so `black` cannot parse it. This is the base of a 3-diff stack: (1) this black reformat; (2) `.flake8` alignment (max-line-length 80 + black-compatible ignores E203/W503); (3) genuine lint fixes (F401/F403/F841/B011). Reviewed By: mnorris11 Differential Revision: D109736099 fbshipit-source-id: 9a054635766ed11aa3760a788395babd3d198abf
84 lines
2.4 KiB
Python
Executable File
84 lines
2.4 KiB
Python
Executable File
#!/usr/bin/env python3
|
|
# Copyright (c) Meta Platforms, Inc. and affiliates.
|
|
#
|
|
# This source code is licensed under the MIT license found in the
|
|
# LICENSE file in the root directory of this source tree.
|
|
|
|
import sys
|
|
import numpy as np
|
|
import faiss
|
|
from faiss.contrib.ondisk import merge_ondisk
|
|
|
|
#################################################################
|
|
# Small I/O functions
|
|
#################################################################
|
|
|
|
|
|
def ivecs_read(fname):
|
|
a = np.fromfile(fname, dtype="int32")
|
|
d = a[0]
|
|
return a.reshape(-1, d + 1)[:, 1:].copy()
|
|
|
|
|
|
def fvecs_read(fname):
|
|
return ivecs_read(fname).view("float32")
|
|
|
|
|
|
#################################################################
|
|
# Main program
|
|
#################################################################
|
|
|
|
stage = int(sys.argv[1])
|
|
|
|
tmpdir = "/tmp/"
|
|
|
|
if stage == 0:
|
|
# train the index
|
|
xt = fvecs_read("sift1M/sift_learn.fvecs")
|
|
index = faiss.index_factory(xt.shape[1], "IVF4096,Flat")
|
|
print("training index")
|
|
index.train(xt)
|
|
print("write " + tmpdir + "trained.index")
|
|
faiss.write_index(index, tmpdir + "trained.index")
|
|
|
|
|
|
if 1 <= stage <= 4:
|
|
# add 1/4 of the database to 4 independent indexes
|
|
bno = stage - 1
|
|
xb = fvecs_read("sift1M/sift_base.fvecs")
|
|
i0, i1 = int(bno * xb.shape[0] / 4), int((bno + 1) * xb.shape[0] / 4)
|
|
index = faiss.read_index(tmpdir + "trained.index")
|
|
print("adding vectors %d:%d" % (i0, i1))
|
|
index.add_with_ids(xb[i0:i1], np.arange(i0, i1))
|
|
print("write " + tmpdir + "block_%d.index" % bno)
|
|
faiss.write_index(index, tmpdir + "block_%d.index" % bno)
|
|
|
|
if stage == 5:
|
|
|
|
print("loading trained index")
|
|
# construct the output index
|
|
index = faiss.read_index(tmpdir + "trained.index")
|
|
|
|
block_fnames = [tmpdir + "block_%d.index" % bno for bno in range(4)]
|
|
|
|
merge_ondisk(index, block_fnames, tmpdir + "merged_index.ivfdata")
|
|
|
|
print("write " + tmpdir + "populated.index")
|
|
faiss.write_index(index, tmpdir + "populated.index")
|
|
|
|
|
|
if stage == 6:
|
|
# perform a search from disk
|
|
print("read " + tmpdir + "populated.index")
|
|
index = faiss.read_index(tmpdir + "populated.index")
|
|
index.nprobe = 16
|
|
|
|
# load query vectors and ground-truth
|
|
xq = fvecs_read("sift1M/sift_query.fvecs")
|
|
gt = ivecs_read("sift1M/sift_groundtruth.ivecs")
|
|
|
|
D, I = index.search(xq, 5)
|
|
|
|
recall_at_1 = (I[:, :1] == gt[:, :1]).sum() / float(xq.shape[0])
|
|
print("recall@1: %.3f" % recall_at_1)
|