Repository · GitHub

lightly-ai/lightly-train

All-in-one training for vision models (YOLO, ViTs, RT-DETR, DINOv3): pretraining, fine-tuning, distillation.

Owner	lightly-ai
License (as declared)	AGPL-3.0
Stars	1,713
Forks	119
Main language	Python
Created	10 April 2025
Last updated at source	12 October 2026

pythoncomputer-visioncontrastive-learningdeep-learningdepth-estimationdinov2dinov3distillationembeddingseomtobject-detectionpretrained-modelspytorchreal-timertdetrv2self-supervisedself-supervised-learningsemantic-segmentationvision-transformeryolo

Embed this entry

<iframe src="https://silytics.si/embed/item/fb40ea8c-6d93-407f-ab80-059f1bf10265" width="420" height="190" style="border:0" loading="lazy" title="Silytics entry"></iframe>

Free, no tracking. More about feeds and embeds.

More from lightly-ai

lightlyRepository

Silytics shows public metadata from GitHub and links to the original. Information may be incomplete or out of date. Last refreshed 15 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.