- 13 Nov, 2017 1 commit
-
-
Matthijs Douze authored
-
- 07 Nov, 2017 1 commit
-
-
Jason Gauci authored
* fixes for homebrew and anaconda python * remove #/bin/bash * PR feedback and handle different versions of LLVM
-
- 27 Oct, 2017 1 commit
-
-
Ivan Lobov authored
Accepting this 2-word PR without CLA....
-
- 18 Sep, 2017 1 commit
-
-
Matthijs Douze authored
-
- 08 Sep, 2017 2 commits
-
-
matthijs authored
fix index_cpu_to_gpu_multiple fix PCA dimension
-
Matthijs Douze authored
-
- 04 Sep, 2017 1 commit
-
-
Matthijs Douze authored
-
- 01 Sep, 2017 1 commit
-
-
Matthijs Douze authored
-
- 31 Aug, 2017 2 commits
- 10 Aug, 2017 2 commits
- 01 Aug, 2017 1 commit
-
-
Jeff Johnson authored
-
- 30 Jul, 2017 1 commit
-
-
matthijs authored
-
- 26 Jul, 2017 2 commits
- 19 Jul, 2017 1 commit
-
-
Matthijs Douze authored
-
- 18 Jul, 2017 4 commits
-
-
matthijs authored
-
matthijs authored
-
matthijs authored
- implemented ScalarQuantizer (without IVF) - implemented update for IndexIVFFlat - implemented L2 normalization preproc
-
matthijs authored
- implemented ScalarQuantizer (without IVF) - implemented update for IndexIVFFlat - implemented L2 normalization preproc
-
- 11 Jul, 2017 1 commit
-
-
Matthijs Douze authored
-
- 22 Jun, 2017 5 commits
-
-
matthijs authored
-
-
matthijs authored
-
matthijs authored
-
matthijs authored
* 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
-
- 21 Jun, 2017 3 commits
- 15 Jun, 2017 1 commit
-
-
Max Strange authored
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.
-
- 31 May, 2017 3 commits
-
-
Boris Mansencal authored
-
Matthijs Douze authored
-
Adeykin authored
-
- 10 May, 2017 1 commit
-
-
Matthijs Douze authored
-
- 08 May, 2017 1 commit
-
-
Jeff Johnson authored
correct utils::nextHighestPowerOf2
-
- 07 May, 2017 1 commit
-
-
BorisMansencal authored
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.
-
- 02 May, 2017 1 commit
-
-
Tianwei Shen authored
* 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
-
- 25 Apr, 2017 1 commit
-
-
Jeff Johnson authored
Added additional notice concerning compute capabilities.
-
- 19 Apr, 2017 1 commit
-
-
Pierre Letessier authored
* 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
-