test/milvus
1
0
Fork 0
mirror of https://gitee.com/milvus-io/milvus.git synced 2024-12-02 20:09:57 +08:00
Code Issues Actions 12 Packages Projects Releases Wiki Activity

[skip e2e] improve annotation (#14127)

Browse Source 
Signed-off-by: Xieql <qianglong.xie@zilliz.com>
This commit is contained in:
Xieql 2021-12-27 10:24:17 +08:00 committed by GitHub
parent 89f3bbf454
commit b022615b2c
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
internal/core/src/index/thirdparty/faiss/benchs/distributed_ondisk/README.md vendored
View File

@ -125,7 +125,7 @@ This is performed by the script [`make_trained_index.py`](make_trained_index.py)
## Building the index by slices
We call the slices "vslisces" as they are vertical slices of the big matrix, see explanation in the wiki section [Split across datanbase partitions](https://github.com/facebookresearch/faiss/wiki/Indexing-1T-vectors#split-across-database-partitions).
We call the slices "vslisces" as they are vertical slices of the big matrix, see explanation in the wiki section [Split across database partitions](https://github.com/facebookresearch/faiss/wiki/Indexing-1T-vectors#split-across-database-partitions).
The script [make_index_vslice.py](make_index_vslice.py) makes an index for a subset of the vectors of the input data and stores it as an independent index.
There are 200 slices of 5M vectors each for Deep1B.