gmberton/VPR-methods-evaluation

Wrapper for 10+ VPR models. Use any SOTA VPR model just by changing one parameter

48
/ 100
Emerging

Integrates official model implementations and weights from 16+ VPR papers (NetVLAD, CosPlace, EigenPlaces, AnyLoc, MegaLoc, and others) as git submodules, enabling direct comparison with original authors' architectures. Supports both unlabeled image directories and geo-tagged datasets (via UTM coordinates in filenames) to compute standard recall metrics, with optional visualization of top-k predictions and filtering to show only incorrect matches.

181 stars.

No License No Package No Dependents
Maintenance 13 / 25
Adoption 10 / 25
Maturity 8 / 25
Community 17 / 25

How are scores calculated?

Stars

181

Forks

25

Language

Python

License

Last pushed

Mar 15, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/gmberton/VPR-methods-evaluation"

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