Python · MIT
KevinMusgrave/pytorch-metric-learning
Train and evaluate embeddings for similarity search with PyTorch. Includes contrastive losses, hard example mining, samplers, and retrieval metrics.
★ 6.3k
Stars
663 forks · 3 open issues
−2.0/wk
Growth · measured
Stars counted between two of our own snapshots roughly a week apart. The repository page gives the exact span.
25.7
Momentum / 100
see the breakdown below
7y ago
Created
last push 7d ago
Star history
How this score was built
| Component | Weight | Earned | Why |
|---|---|---|---|
| Velocity | 55 | 0.0 | −2.0/wk, log-scaled against a 750/day ceiling |
| Acceleration | 15 | 0.0 | needs 7-day and 30-day rates side by side |
| Freshness | 15 | 14.7 | last push 7d ago; decays to zero at 180 days |
| Scale | 15 | 11.0 | 6.3k stars, log-scaled against 150k — stops a 3-star repo topping the board |
| Momentum | 100 | 25.7 | sum of the above |
Detail
| Topics | computer-visioncontrastive-learningdeep-learningdeep-metric-learningembeddingsimage-retrievalmachine-learningmetric-learningpytorchself-supervised-learning |
| Matched on | RAG (embeddings) Computer Vision (computer-vision) |
| Short window | +-2 stars over 7 days = -0.3/day |
| Long window | +-1 stars over 26 days = 0.0/day |
| Lifetime average | 2.47 stars/day over 2,570 days |
| First seen here | 2026-10-11 |
| Last read | 2d ago |