mirrors
/
faiss
mirror of https://github.com/facebookresearch/faiss.git
1
0
Fork 0
Code Issues Projects Releases Wiki Activity
faiss/docs/html/search/all_77.js

12 lines
1.4 KiB
JavaScript
Raw Normal View History

Initial commit
2017-02-23 06:26:44 +08:00
var searchData=
[
Facebook sync (May 2019) + relicense (#838) 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
2019-05-28 22:17:22 +08:00
['waitforthreadexit',['waitForThreadExit',['../classfaiss_1_1WorkerThread.html#a29c8cfced812372adb93440545c05edc',1,'faiss::WorkerThread']]],
Initial commit
2017-02-23 06:26:44 +08:00
['warpselect',['WarpSelect',['../structfaiss_1_1gpu_1_1WarpSelect.html',1,'faiss::gpu']]],
['warpselect_3c_20k_2c_20v_2c_20dir_2c_20comp_2c_201_2c_20numthreadq_2c_20threadsperblock_20_3e',['WarpSelect< K, V, Dir, Comp, 1, NumThreadQ, ThreadsPerBlock >',['../structfaiss_1_1gpu_1_1WarpSelect_3_01K_00_01V_00_01Dir_00_01Comp_00_011_00_01NumThreadQ_00_01ThreadsPerBlock_01_4.html',1,'faiss::gpu']]],
['weights',['weights',['../structfaiss_1_1ReproduceDistancesObjective.html#a982332b44ff32b9ae9694e374acd0aff',1,'faiss::ReproduceDistancesObjective']]],
Synchronization with FB version 2017-06-21 * moved most FAISS_ASSERT calls to C++ exceptions, and adjusted memory allocation to avoid mem leaks * added an IndexIVFScalarQuantizer type that offers an intermediate compression between IVFFlat and IVFPQ * support removal of indices in IndexIDMap / IndexFlat combination * various fixes in GPU code
2017-06-21 21:54:28 +08:00
['what',['what',['../classfaiss_1_1FaissException.html#ab75086632bbd1b8e13f002c8942a7672',1,'faiss::FaissException']]],
Facebook sync (May 2019) + relicense (#838) 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
2019-05-28 22:17:22 +08:00
['workerthread',['WorkerThread',['../classfaiss_1_1WorkerThread.html',1,'faiss']]],
Initial commit
2017-02-23 06:26:44 +08:00
['wp',['wp',['../structfaiss_1_1BufferList.html#af4d7ddcd77f328a12a7da89d8febe5d9',1,'faiss::BufferList']]],
['writeout',['writeOut',['../structfaiss_1_1gpu_1_1WarpSelect.html#a1cd82964e633531a95d5d095e012acb5',1,'faiss::gpu::WarpSelect::writeOut()'],['../structfaiss_1_1gpu_1_1WarpSelect_3_01K_00_01V_00_01Dir_00_01Comp_00_011_00_01NumThreadQ_00_01ThreadsPerBlock_01_4.html#a65f05abb17750d13bd9e03d56cd86fd2',1,'faiss::gpu::WarpSelect< K, V, Dir, Comp, 1, NumThreadQ, ThreadsPerBlock >::writeOut()']]]
];