pavelkrolevets/face_clustering

Sort similar looking faces to clusters

18
/ 100
Experimental

Uses pretrained FaceNet to generate 128-dimensional face embeddings, then computes a full N×N Euclidean distance matrix and applies KMeans clustering to group similar faces. The pipeline exports embeddings from images, calculates pairwise distances (stored as NumPy arrays), and clusters the resulting vectors with configurable cluster count. Designed for batch processing of image datasets in OpenFace directory format, leveraging TensorFlow and OpenCV.

No commits in the last 6 months.

No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 7 / 25
Maturity 1 / 25
Community 10 / 25

How are scores calculated?

Stars

26

Forks

3

Language

Python

License

Last pushed

Feb 06, 2019

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/embeddings/pavelkrolevets/face_clustering"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.