ultralytics

Ultralytics YOLO27, YOLO26, YOLO11, YOLOv8 — object detection, instance segmentation, semantic segmentation, image classification, pose estimation, object track

What is ultralytics?

Ultralytics YOLO27, YOLO26, YOLO11, YOLOv8 — object detection, instance segmentation, semantic segmentation, image classification, pose estimation, object tracking

Overview of ultralytics

What it is

Ultralytics is a software package that provides cutting-edge, state-of-the-art (SOTA) YOLO models for computer vision tasks. It supports object detection, instance segmentation, semantic segmentation, depth estimation, image classification, pose estimation, oriented object detection, and object tracking across video frames. The repository includes models from early versions like YOLOv3 to the latest YOLO26, with YOLO27 previewed as coming soon.

Key features

  • Supports multiple vision tasks: object detection, instance segmentation, semantic segmentation, depth estimation, image classification, pose estimation, oriented object detection, and tracking.
  • Provides both Command Line Interface (CLI) and Python API for training, validation, prediction, and deployment.
  • Offers a wide range of pretrained models (e.g., YOLO26n, YOLO26s, YOLO26m, YOLO26l, YOLO26x) with performance metrics on COCO, Cityscapes, ImageNet, and other datasets.
  • Models can be exported to formats like ONNX for deployment.
  • The package is designed to be fast, accurate, and easy to use.

Use cases

  • Object detection in images and videos.
  • Instance segmentation and semantic segmentation for detailed scene understanding.
  • Depth estimation from single images.
  • Image classification across 1000+ classes (ImageNet pretrained).
  • Pose estimation for human or animal keypoints.
  • Oriented object detection (OBB) for rotated objects.
  • Object tracking across video frames using detection, segmentation, pose, or OBB models.

Getting started

Install the ultralytics package in a Python>=3.8 environment with PyTorch>=1.8:bashpip install ultralyticsUse the CLI to predict with a pretrained model:bashyolo predict model=yolo26n.pt source='https://ultralytics.com/images/bus.jpg'Or use Python:pythonfrom ultralytics import YOLOmodel = YOLO('yolo26n.pt')results = model('path/to/image.jpg')results[0].show()

License and pricing

The software is licensed under AGPL-3.0. For commercial use, an Enterprise License is required (see Ultralytics Licensing). The package is open source.

Based on the project's public README and repository metadata.

Add this badge to your README

Featured on YunoDB Badge styles & help

Maintain this project? Show that it is featured on YunoDB.

Markdown[![Featured on YunoDB](https://yunodb.com/badge/ultralyticsultralytics.svg)](https://yunodb.com/tools/ultralyticsultralytics?utm_source=github&utm_medium=badge)
HTML<a href="https://yunodb.com/tools/ultralyticsultralytics?utm_source=github&utm_medium=badge"><img src="https://yunodb.com/badge/ultralyticsultralytics.svg" alt="Featured on YunoDB" height="20"></a>