search

pixelogik / NearPy

Python framework for fast (approximated) nearest neighbour search in large, high-dimensional data sets using different locality-sensitive hashes.
MIT License
759 stars 152 forks source link

Persist hash configurations in storage #15

Closed pixelogik closed 9 years ago

pixelogik commented 9 years ago

This is needed to load hash configurations from storage (projection vectors). Otherwise random hashes are of no use.

pixelogik commented 9 years ago

Also this PCA hashes this way the PCA has only to be done once on the training set.