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
151 lines
4.1 KiB
Python
151 lines
4.1 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 argparse
|
|
import logging
|
|
import os
|
|
|
|
from faiss.benchs.bench_fw.benchmark import Benchmark
|
|
from faiss.benchs.bench_fw.benchmark_io import BenchmarkIO
|
|
from faiss.benchs.bench_fw.descriptors import (
|
|
DatasetDescriptor,
|
|
IndexDescriptorClassic,
|
|
)
|
|
|
|
logging.basicConfig(level=logging.INFO)
|
|
|
|
|
|
def sift1M(bio):
|
|
benchmark = Benchmark(
|
|
num_threads=32,
|
|
training_vectors=DatasetDescriptor(
|
|
namespace="std_d", tablename="sift1M"
|
|
),
|
|
database_vectors=DatasetDescriptor(
|
|
namespace="std_d", tablename="sift1M"
|
|
),
|
|
query_vectors=DatasetDescriptor(namespace="std_q", tablename="sift1M"),
|
|
index_descs=[
|
|
IndexDescriptorClassic(
|
|
factory=f"IVF{2 ** nlist},Flat",
|
|
)
|
|
for nlist in range(8, 15)
|
|
],
|
|
k=1,
|
|
distance_metric="L2",
|
|
)
|
|
benchmark.io = bio
|
|
benchmark.benchmark(
|
|
result_file="result.json",
|
|
local=True,
|
|
train=True,
|
|
reconstruct=False,
|
|
knn=True,
|
|
range=False,
|
|
)
|
|
|
|
|
|
def bigann(bio):
|
|
for scale in [1, 2, 5, 10, 20, 50]:
|
|
benchmark = Benchmark(
|
|
num_threads=32,
|
|
training_vectors=DatasetDescriptor(
|
|
namespace="std_t", tablename="bigann1M"
|
|
),
|
|
database_vectors=DatasetDescriptor(
|
|
namespace="std_d", tablename=f"bigann{scale}M"
|
|
),
|
|
query_vectors=DatasetDescriptor(
|
|
namespace="std_q", tablename="bigann1M"
|
|
),
|
|
index_descs=[
|
|
IndexDescriptorClassic(
|
|
factory=f"IVF{2 ** nlist},Flat",
|
|
)
|
|
for nlist in range(11, 19)
|
|
]
|
|
+ [
|
|
IndexDescriptorClassic(
|
|
factory=f"IVF{2 ** nlist}_HNSW32,Flat",
|
|
construction_params=[
|
|
None,
|
|
{"efConstruction": 200, "efSearch": 40},
|
|
],
|
|
)
|
|
for nlist in range(11, 19)
|
|
],
|
|
k=1,
|
|
distance_metric="L2",
|
|
)
|
|
benchmark.set_io(bio)
|
|
benchmark.benchmark(
|
|
f"result{scale}.json",
|
|
local=False,
|
|
train=True,
|
|
reconstruct=False,
|
|
knn=True,
|
|
range=False,
|
|
)
|
|
|
|
|
|
def ssnpp(bio):
|
|
benchmark = Benchmark(
|
|
num_threads=32,
|
|
training_vectors=DatasetDescriptor(tablename="ssnpp_training_5M.npy"),
|
|
database_vectors=DatasetDescriptor(tablename="ssnpp_database_5M.npy"),
|
|
query_vectors=DatasetDescriptor(tablename="ssnpp_queries_10K.npy"),
|
|
index_descs=[
|
|
IndexDescriptorClassic(
|
|
factory=f"IVF{2 ** nlist},PQ256x4fs,Refine(SQfp16)",
|
|
)
|
|
for nlist in range(9, 16)
|
|
]
|
|
+ [
|
|
IndexDescriptorClassic(
|
|
factory=f"IVF{2 ** nlist},Flat",
|
|
)
|
|
for nlist in range(9, 16)
|
|
]
|
|
+ [
|
|
IndexDescriptorClassic(
|
|
factory=f"PQ256x4fs,Refine(SQfp16)",
|
|
),
|
|
IndexDescriptorClassic(
|
|
factory=f"HNSW32",
|
|
),
|
|
],
|
|
k=1,
|
|
distance_metric="L2",
|
|
)
|
|
benchmark.set_io(bio)
|
|
benchmark.benchmark(
|
|
"result.json",
|
|
local=False,
|
|
train=True,
|
|
reconstruct=False,
|
|
knn=True,
|
|
range=False,
|
|
)
|
|
|
|
|
|
if __name__ == "__main__":
|
|
parser = argparse.ArgumentParser()
|
|
parser.add_argument("experiment")
|
|
parser.add_argument("path")
|
|
args = parser.parse_args()
|
|
assert os.path.exists(args.path)
|
|
path = os.path.join(args.path, args.experiment)
|
|
if not os.path.exists(path):
|
|
os.mkdir(path)
|
|
bio = BenchmarkIO(
|
|
path=path,
|
|
)
|
|
if args.experiment == "sift1M":
|
|
sift1M(bio)
|
|
elif args.experiment == "bigann":
|
|
bigann(bio)
|
|
elif args.experiment == "ssnpp":
|
|
ssnpp(bio)
|