Python · AGPL-3.0
lightly-ai/lightly-train
All-in-one training for vision models (YOLO, ViTs, RT-DETR, DINOv3): pretraining, fine-tuning, distillation.
★ 1.7k
Stars
121 forks · 87 open issues
+1.0/wk
Growth · measured
Stars counted between two of our own snapshots roughly a week apart. The repository page gives the exact span.
25.5
Momentum / 100
see the breakdown below
19mo ago
Created
last push 2d ago
Star history
How this score was built
| Component | Weight | Earned | Why |
|---|---|---|---|
| Velocity | 55 | 1.1 | +1.0/wk, log-scaled against a 750/day ceiling |
| Acceleration | 15 | 0.0 | last week ran 0.17× the monthly pace |
| Freshness | 15 | 15.0 | last push 2d ago; decays to zero at 180 days |
| Scale | 15 | 9.4 | 1.7k stars, log-scaled against 150k — stops a 3-star repo topping the board |
| Momentum | 100 | 25.5 | sum of the above |
Detail
| Topics | computer-visioncontrastive-learningdeep-learningdepth-estimationdinov2dinov3distillationembeddingseomtobject-detectionpretrained-modelspythonpytorchreal-timertdetrv2self-supervisedself-supervised-learningsemantic-segmentationvision-transformeryolo |
| Matched on | RAG (embeddings) |
| Short window | +1 stars over 7 days = 0.1/day |
| Long window | +22 stars over 26 days = 0.8/day |
| Lifetime average | 3.01 stars/day over 574 days |
| First seen here | 2026-10-11 |
| Last read | 2d ago |