
lightly-train
by lightly-ai (organization)
All-in-one training for vision models (YOLO, ViTs, RT-DETR, DINOv3): pretraining, fine-tuning, distillation. (description from the project’s GitHub page)
Repository facts
- Stars
- 1,715
- Forks
- 119
- Open issues and pull requests
- 82
- Primary language
- Python
- License
- GNU Affero General Public License v3.0 (AGPL-3.0)
- Owner
- lightly-ai · Organization
- Created
- Apr 10, 2025
- Last push
- Oct 12, 2026
Topics
Related projects
Projects that share this one’s GitHub topics.
Rank 87: ultralytics/ultralytics
Ultralytics YOLO27, YOLO26, YOLO11, YOLOv8 — object detection, instance segmentation, semantic segmentation, image classification, pose estimation, object tracking
62,613 starsPythonAGPL-3.0Last push Oct 18, 2026
Rank 1,277: KevinMusgrave/pytorch-metric-learning
The easiest way to use deep metric learning in your application. Modular, flexible, and extensible. Written in PyTorch.
6,342 starsPythonMITLast push Aug 17, 2025
Rank 2,076: lightly-ai/lightly
A python library for self-supervised learning on images.
3,821 starsPythonMITLast push Oct 15, 2026
Rank 5,919: qqlu/Entity
EntitySeg Toolbox: Towards Open-World and High-Quality Image Segmentation
1,051 starsJupyter NotebookOther licenseLast push Nov 30, 2023
Rank 3,727: alibaba/EasyCV
An all-in-one toolkit for computer vision
1,954 starsPythonApache-2.0Last push May 9, 2025
Rank 474: cvat-ai/cvat
CVAT is a leading data annotation platform for image, video, audio, and 3D datasets. It offers open-source, cloud, and enterprise products, as well as labeling services, with AI-a…
16,949 starsPythonMITLast push Oct 18, 2026