Infinity provides Python script for sift1m and gist1m dataset benchmark.
git clone https://github.com/infiniflow/infinity.git
cd infinity
Download via wget.
#download sift benchmark
wget ftp://ftp.irisa.fr/local/texmex/corpus/sift.tar.gz
#download gist benchmark
wget ftp://ftp.irisa.fr/local/texmex/corpus/gist.tar.gz
or visit http://corpus-texmex.irisa.fr/ to download manually.
#uncompress and move benchmark file
tar -zxvf sift.tar.gz
mv sift/sift_base.fvecs test/data/benchmark/sift_1m/sift_base.fvecs
mv sift/sift_query.fvecs test/data/benchmark/sift_1m/sift_query.fvecs
mv sift/sift_groundtruth.ivecs test/data/benchmark/sift_1m/sift_groundtruth.ivecs
tar -zxvf gist.tar.gz
mv gist/gist_base.fvecs test/data/benchmark/gist_1m/gist_base.fvecs
mv gist/gist_query.fvecs test/data/benchmark/gist_1m/gist_query.fvecs
mv gist/gist_groundtruth.ivecs test/data/benchmark/gist_1m/gist_groundtruth.ivecs
cd python
pip install -r requirements.txt
python setup.py bdist_wheel
pip install dist/infinity_sdk-0.1.0.dev1-py3-none-any.whl
See the README.md to start Infinity.
cd benchmark
options:
-h, --help show this help message and exit
-d DATA_SET, --data DATA_SET
python remote_benchmark_import.py -d sift_1m
python remote_benchmark_import.py -d gist_1m
options:
-h, --help show this help message and exit
-t THREADS, --threads THREADS
-r ROUNDS, --rounds ROUNDS
-d DATA_SET, --data DATA_SET
# ROUNDS refers to the number of times that Python runs the benchmark. The result is the average time for all runs.
# The following command means run benchmark with one thread, for one time using the sift dataset.
python remote_benchmark.py -t 1 -r 1 -d sift_1m
python remote_benchmark.py -t 1 -r 1 -d gist_1m