daf589d9d2
add bench_all_ivf
2018-12-20 05:43:36 -08:00
323dbf3be3
Facebook sync (Dec 2018). ( #660 )
...
* Add GpuIndexBinaryFlat
* Add IndexBinaryHNSW
2018-12-19 17:48:35 +01:00
76bec0b500
Facebook sync ( #573 )
...
Features:
- automatic tracking of C++ references in Python
- non-intel platforms supported -- some functions optimized for ARM
- override nprobe for concurrent searches
- support for floating-point quantizers in binary indexes
Bug fixes:
- no more segfaults in python (I know it's the same as the first feature but it's important!)
- fix GpuIndexIVFFlat issues for float32 with 64 / 128 dims
- fix sharding of flat indexes on GPU with index_cpu_to_gpu_multiple
2018-08-30 19:38:50 +02:00
6880286ea0
Facebook sync ( #504 )
...
* Facebook sync
* Update swig wrappers.
* Fix comment.
2018-07-06 14:12:11 +02:00
abe2b0fd19
read/write index with std::function wrapper ( #427 )
...
* add access function to IndexIVF;
* - access for IndexIVF;
- write_index/read_index with std::function<...>;
* - fix test compile on mac;
- adjust write/read with std::function;
* replace std::function with IOReader/IOWriter;
* remove IndexIVF::access // tmp
* PFN_WRITE/READ => WRITE;
* revert mac compile fix;
* rename;
* fix compile;
* reset CMakeList;
* format; remove unused function/header;
2018-05-24 10:45:42 +02:00
0c482e54eb
sync with FB version 2018-02-23 ( #347 )
...
- support on-disk IVF
2018-02-23 07:49:45 -08:00
9933892ec9
sync with FB version 2017-01-09
...
- adding HNSW indexing method
- simultaneous search and reconstruction for IndexIVFPQ
2018-01-09 06:42:06 -08:00
250a3d3f18
sync with FB version 2017-11-22
...
various bugfixes from github issues
kmean with some frozen centroids
GPU better tiling for large flat datasets
default AVX for vector ops
2017-11-22 05:11:28 -08:00
d8eeceb883
sync with FB version 2017-09-08
...
fix index_cpu_to_gpu_multiple
fix PCA dimension
2017-09-08 04:39:41 -07:00
8e3dc6f2b0
changed license
2017-07-30 00:18:45 -07:00
ca2ea5097b
Sync with FB version 2017-07-16
...
- access GPU resources
- all Hamming distances of all sizes supported
2017-07-26 03:11:01 -07:00
f7aedbdfc0
sync with FB version 2017-07-18
...
- implemented ScalarQuantizer (without IVF)
- implemented update for IndexIVFFlat
- implemented L2 normalization preproc
2017-07-18 02:51:27 -07:00
784e2facd8
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 09:01:06 -07:00
7abe81b4f6
Better support for low-mem GPUs
...
avoid reading beyond the end of an array in fvec_L2sqr and related functions
2017-04-06 04:33:41 -07:00
c670118a4e
Initial commit
2017-02-22 23:26:44 +01:00
matthijs
Lucas Hosseini
dengos