Skip to content

Online clustering for facial recognition (or any high dimensional features)

Notifications You must be signed in to change notification settings

gerald-ftk/dfclust

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

22 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

An implementation of Efficient Large-Scale Face Clustering Using an Online Mixture of Gaussians

Uses git lfs for the test.npz file. The test.npz contains features generated by insightface's ArcFace with 512d features. HDBSCAN labels are also included in the test.npz for reference.

After setting up your environment and installing requirements, run:

python3 scripts/plot.py

To generate a bokeh graph of the online clustering algorithm.

About

Online clustering for facial recognition (or any high dimensional features)

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages