assets

(★ 660)

Shared Ultralytics logos, media, sample images, pretrained model weights, dataset artifacts, and release assets.

Owner Repos

ultralytics ★ 60,836

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

Python
yolov5 ★ 57,917

Ultralytics YOLOv5 in PyTorch for object detection, instance segmentation, classification, training, and export.

Python
yolov3 ★ 10,594

PyTorch implementation of YOLOv3, YOLOv3-SPP, and YOLOv3-tiny for real-time object detection with training, validation, inference, and multi-format export.

Python
JSON2YOLO ★ 1,230

Legacy JSON-to-YOLO dataset converter for COCO, LabelMe, Labelbox, VoTT, INFOLKS, and ATH annotations. Superseded by convert_coco() in the Ultralytics package.

Python
yolo-ios-app ★ 505

Ultralytics YOLO iOS app and Swift package for real-time Core ML inference across major computer vision tasks.

Swift
yolo-flutter-app ★ 477

Official Ultralytics YOLO Flutter plugin for real-time inference on Android and iOS across major vision tasks.

Dart

File Explorer

ZIP Download
  • .gitignore
  • AGENTS.md
  • CLAUDE.md
  • LICENSE
  • README.md
  • README.zh-CN.md

# Use via CDN

jsDelivr

jsDelivr serves any public GitHub repository as a CDN with zero setup. Pick a version and a file to get a ready-to-paste link and snippet.

Link
Example

Command Glossary

Commands referenced in this DOCs, explained below.

🔍

mkdocs

View Details ▼

Project documentation with Markdown.

mkdocs new {{project_name}}

Create a new mkdocs project:

mkdocs serve

Serve the project in the current directory using the mkdocs dev-server:

mkdocs build

Build the documentation in the current directory:

🔍

yolo

View Details ▼

Train, validate, or infer models on various tasks and versions.

yolo task=init

Create a copy of the default configuration in your current working directory:

yolo task={{detect|segment|classify}} mode=train cfg={{path/to/config.yaml}}

Train the object detection, instance segment, or classification model with the specified configuration file:

// repository documentation