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
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
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
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
a67190c69c
added benchmarking scripts
2017-02-24 08:32:08 -08:00
c670118a4e
Initial commit
2017-02-22 23:26:44 +01:00
matthijs