71335194f6
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 05:10:35 -08:00
0df3f646fc
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 05:00:42 -08:00
885399767d
set verbose of GpuMultipleClonerOptions to True
2017-11-13 10:08:52 +01:00
f82e8a45bd
Fix for homebrew and support for non-standard python distributions ( #242 )
...
* fixes for homebrew and anaconda python
* remove #/bin/bash
* PR feedback and handle different versions of LLVM
2017-11-06 18:06:45 +01:00
2eb8eb9915
Fix makefile.inc.Mac.brew ( #232 )
...
Accepting this 2-word PR without CLA....
2017-10-27 08:16:30 +02:00
f2598e0e08
Update Index.h
2017-09-18 15:46:18 +02:00
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
3986a8db86
Update README.md
2017-09-08 13:22:17 +02:00
6b3b743986
Update makefile.inc.Linux
2017-09-04 07:07:31 +02:00
021d53f96f
Update README.md
2017-09-01 13:12:53 +02:00
486ec6c6ac
Add LD_PRELOAD update to MKL compile instructions ( #197 )
...
It took me quite some time to get around this error -- it might save others time.
2017-08-31 06:31:33 +02:00
8d0643ae74
make INSTALL a proper markdown file ( #196 )
...
* make INSTALL a proper markdown file
* add clarification to gpu test
* add forgotten parenthesis
2017-08-31 06:27:53 +02:00
54a2abb30d
sync with FB version 2017-08-09 (2)
2017-08-09 11:21:50 -07:00
a5ef16db89
sync with FB version 2017-08-09
2017-08-09 11:13:51 -07:00
384d05c464
Update README.md
2017-07-31 14:22:14 -04:00
8e3dc6f2b0
changed license
2017-07-30 00:18:45 -07:00
2882e89397
forgotten
2017-07-26 03:12:49 -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
fd427873a1
Fix bug in chain training.
2017-07-19 08:12:53 +02:00
12f181ee44
forgotten
2017-07-18 02:55:11 -07:00
01b2224b58
forgotten sources
2017-07-18 02:52:23 -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
602debae7b
sync with FB version 2017-07-18
...
- implemented ScalarQuantizer (without IVF)
- implemented update for IndexIVFFlat
- implemented L2 normalization preproc
2017-07-18 02:43:35 -07:00
47ee2d8de7
Update makefile.inc.Linux
2017-07-11 12:01:57 +02:00
5ca05218c0
move to C++11
2017-06-21 09:35:06 -07:00
3ba41afe8f
Merge branch 'master' of https://github.com/facebookresearch/faiss
2017-06-21 09:02:01 -07:00
13754a74a3
fix cmakelists
2017-06-21 09:01:45 -07:00
2d59917d33
fix GPU compile
2017-06-21 09:01:44 -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
fda9230440
fix cmakelists
2017-06-21 08:56:08 -07:00
97a65c3d0c
fix GPU compile
2017-06-21 08:45:46 -07:00
aa1585cb21
* 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 07:22:50 -07:00
9839b0ae11
Changed rootdir ( #137 )
...
The rootdir in the distribution seems specific to the creators. I just made the rootdir for the fvecs be the suggested directory (sift1M) from the installation guide.
2017-06-15 06:53:26 +02:00
678750113e
add support for Nvidia GPUs with CUDA compute capability 6.1 ( #110 )
2017-05-31 15:52:39 +02:00
cb43614634
Update INSTALL
2017-05-31 15:43:40 +02:00
c056f1d320
mkl support in cmake ( #123 )
2017-05-31 15:41:42 +02:00
d3c84568d5
Update README.md
2017-05-09 18:24:37 +02:00
9e6e1a81c4
Merge pull request #109 from BorisMansencal/nextHighestPowerOf2bug
...
correct utils::nextHighestPowerOf2
2017-05-07 16:03:10 -07:00
5b92eeb285
correct utils::nextHighestPowerOf2
...
The bit shift was done as int and not as current type (size_t for example), thus the computed next highest power of 2 was wrong on large numbers.
2017-05-06 20:36:16 +02:00
80314d9f07
add initial cmake support ( #75 )
...
* add initial cmake support
* update cmake, add cmake instructions to INSTALL
* update findopenmp and INSTALL
* change FindOpenBLAS.cmake to cater for macports
- change cblas.h to openblas_config.h since macports does not ship
cblas.h with openblas.
* revise INSTALL for cmake
2017-05-02 11:04:50 +02:00
7fdbe07b4c
Update INSTALL
...
Added additional notice concerning compute capabilities.
2017-04-24 21:21:47 -04:00
281683100a
Docker improvements ( #88 )
...
* Docker build from local sources rather than Github cloned sources
* Update INSTALL instructions for docker build from Github repo
* Back to generic makefile.inc.Linux and use of env var in Dockerfile
* Back to generic makefile.inc.Linux and use of env var in Dockerfile
2017-04-19 10:22:25 +02:00
6893b9e170
Update README.md
2017-04-13 23:45:09 +02:00
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
1067735fba
Add Dockerfile ( #55 )
...
* Add Dockerfile
* Update documentation with Docker build/run details
2017-03-23 18:25:27 +01:00
0faf794e5e
Update INSTALL
2017-03-21 12:14:03 +01:00
c507707098
sync with FB version. Added:
...
- better selection of training sets for PQ and preprocessing
- GPU parameter object
- IndexIDMap fixed
- fixed redo bug in clustering
2017-03-20 10:48:35 -07:00
acb93857ba
sync with FB version. Added:
...
- better selection of training sets for PQ and preprocessing
- GPU parameter object
- IndexIDMap fixed
- fixed redo bug in clustering
2017-03-20 10:33:21 -07:00
06bec25677
Update INSTALL
2017-03-20 17:08:42 +01:00
cf74971a30
Update INSTALL
2017-03-15 13:25:00 -04:00
matthijs
Jason Gauci
Ivan Lobov
Julieta
Jeff Johnson
Max Strange
Boris Mansencal
Adeykin
Tianwei Shen
Pierre Letessier