mirror of
https://github.com/facebookresearch/faiss.git
synced 2026-10-12 02:13:36 +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
111 lines
2.7 KiB
Python
111 lines
2.7 KiB
Python
# 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 faiss
|
|
import time
|
|
import os
|
|
import multiprocessing as mp
|
|
import numpy as np
|
|
import matplotlib.pyplot as plt
|
|
|
|
try:
|
|
from faiss.contrib.datasets_fb import DatasetSIFT1M
|
|
except ImportError:
|
|
from faiss.contrib.datasets import DatasetSIFT1M
|
|
|
|
|
|
# ds = DatasetDeep1B(10**6)
|
|
# ds = DatasetBigANN(nb_M=1)
|
|
ds = DatasetSIFT1M()
|
|
|
|
xq = ds.get_queries()
|
|
xb = ds.get_database()
|
|
gt = ds.get_groundtruth()
|
|
|
|
xt = ds.get_train()
|
|
|
|
nb, d = xb.shape
|
|
nq, d = xq.shape
|
|
nt, d = xt.shape
|
|
|
|
k = 1
|
|
AQ = faiss.AdditiveQuantizer
|
|
|
|
|
|
def eval_recall(index, name):
|
|
t0 = time.time()
|
|
D, I = index.search(xq, k=k)
|
|
t = time.time() - t0
|
|
speed = t * 1000 / nq
|
|
qps = 1000 / speed
|
|
|
|
corrects = (gt == I).sum()
|
|
recall = corrects / nq
|
|
print(
|
|
f"\tnprobe {index.nprobe:3d}, Recall@{k}: "
|
|
f"{recall:.6f}, speed: {speed:.6f} ms/query"
|
|
)
|
|
|
|
return recall, qps
|
|
|
|
|
|
def eval_and_plot(name, rescale_norm=True, plot=True):
|
|
index = faiss.index_factory(d, name)
|
|
index_path = f"indices/{name}.faissindex"
|
|
|
|
if os.path.exists(index_path):
|
|
index = faiss.read_index(index_path)
|
|
else:
|
|
faiss.omp_set_num_threads(mp.cpu_count())
|
|
index.train(xt)
|
|
index.add(xb)
|
|
faiss.write_index(index, index_path)
|
|
|
|
# search params
|
|
if hasattr(index, "rescale_norm"):
|
|
index.rescale_norm = rescale_norm
|
|
name += f"(rescale_norm={rescale_norm})"
|
|
faiss.omp_set_num_threads(1)
|
|
|
|
data = []
|
|
print(f"======{name}")
|
|
for nprobe in 1, 2, 4, 6, 8, 12, 16, 24, 32, 48, 64, 128:
|
|
index.nprobe = nprobe
|
|
recall, qps = eval_recall(index, name)
|
|
data.append((recall, qps))
|
|
|
|
if plot:
|
|
data = np.array(data)
|
|
plt.plot(data[:, 0], data[:, 1], label=name) # x - recall, y - qps
|
|
|
|
|
|
M, nlist = 32, 1024
|
|
|
|
# just for warmup...
|
|
# eval_and_plot(f"IVF{nlist},PQ{M}x4fs", plot=False)
|
|
|
|
# benchmark
|
|
plt.figure(figsize=(8, 6), dpi=80)
|
|
|
|
# PQ
|
|
eval_and_plot(f"IVF{nlist},PQ{M}x4fs")
|
|
eval_and_plot(f"IVF{nlist},PQ{M}x4fsr")
|
|
|
|
# AQ, by_residual
|
|
eval_and_plot(f"IVF{nlist},LSQ{M-2}x4fsr_Nlsq2x4")
|
|
eval_and_plot(f"IVF{nlist},RQ{M-2}x4fsr_Nrq2x4")
|
|
eval_and_plot(f"IVF{nlist},LSQ{M-2}x4fsr_Nlsq2x4", rescale_norm=False)
|
|
eval_and_plot(f"IVF{nlist},RQ{M-2}x4fsr_Nrq2x4", rescale_norm=False)
|
|
|
|
# AQ, no by_residual
|
|
eval_and_plot(f"IVF{nlist},LSQ{M-2}x4fs_Nlsq2x4")
|
|
eval_and_plot(f"IVF{nlist},RQ{M-2}x4fs_Nrq2x4")
|
|
|
|
plt.title("Indices on SIFT1M")
|
|
plt.xlabel("Recall@1")
|
|
plt.ylabel("QPS")
|
|
plt.legend(bbox_to_anchor=(1.02, 0.1), loc="upper left", borderaxespad=0)
|
|
plt.savefig("bench_ivf_fastscan.png", bbox_inches="tight")
|