Commit Graph

9 Commits (88eabe97f96d0c0964dfa075f74373c64d46da80)

Author SHA1 Message Date
cclauss efa1e3f64f Use print() function in both Python 2 and Python 3 (#1443)
Summary:
Legacy __print__ statements are syntax errors in Python 3 but __print()__ function works as expected in both Python 2 and Python 3.

Pull Request resolved: https://github.com/facebookresearch/faiss/pull/1443

Reviewed By: LowikC

Differential Revision: D24157415

Pulled By: mdouze

fbshipit-source-id: 4ec637aa26b61272e5337d47b7796a330ce25bad
2020-10-08 00:27:29 -07:00
Lucas Hosseini ac74f576f7 fbshipit-source-id: 4f3cfa59471d548af93fe118d1b73d45bc648edf 2020-08-04 12:00:38 -07:00
Lucas Hosseini cd38e82f0c
Facebook sync 2020-07-31 (#1308) 2020-08-03 22:15:02 +02:00
Lucas Hosseini a8118acbc5
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 16:17:22 +02:00
Lucas Hosseini afe0fdc161
Facebook sync (Mar 2019) (#756)
Facebook sync (Mar 2019)

- MatrixStats object
- option to round coordinates during k-means optimization
- alternative option for search in HNSW
- moved stats and imbalance_factor of IndexIVF to InvertedLists object
- range search for IVFScalarQuantizer
- direct unit8 codec in ScalarQuantizer
- renamed IndexProxy to IndexReplicas and moved to main Faiss
- better support for PQ code assignment with external index
- support for IMI2x16 (4B virtual centroids!)
- support for k = 2048 search on GPU (instead of 1024)
- most CUDA mem alloc failures throw exceptions instead of terminating on an assertion
- support for renaming an ondisk invertedlists
- interrupt computations with ctrl-C in python
2019-03-29 16:32:28 +01:00
matthijs 8e3dc6f2b0 changed license 2017-07-30 00:18:45 -07:00
matthijs 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
matthijs 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
matthijs a67190c69c added benchmarking scripts 2017-02-24 08:32:08 -08:00