Training of Locally Optimized Product Quantization (LOPQ) models for approximate nearest neighbor search of high dimensional data in Python and Spark.
562
stars
130
forks
source link
does it need add the distance of query to coarse centroid to the final dis？ #27
Open
5ace opened 4 years ago
https://github.com/yahoo/lopq/blob/0f17655b901e6dfabe5c2aa62b4c8e492f34b05a/python/lopq/search.py#L163； does here only sum the residual‘s l2 distance?