登录

notebooks

ultralyticsAGPL-3.0活跃维护

Ultralytics 官方 YOLO 教程合集，提供可直接在 Colab、Kaggle、SageMaker 上运行的 Notebook，覆盖训练、推理、导出及检测、分割、姿态估计等视觉任务。

Ultralytics YOLO tutorials for Colab, Kaggle, and SageMaker covering training, inference, export, and vision tasks.

v0.0.0发布于 2025-03-27 03:16 UTC248star58fork同步于 2026-11-10 18:04 UTC
YOLO教程目标检测实例分割姿态估计模型导出
对比 GitHub 官网computer-visionexamplesgoogle-colabjupyter-notebookkaggle

怎么上手

由 README 提炼，执行前请确认
原文 
无需本地安装，直接在浏览器打开对应 Notebook：https://colab.research.google.com/github/ultralytics/notebooks/blob/main/notebooks/how-to-train-ultralytics-yolo-on-carparts-segmentation-dataset.ipynb
硬件要求按 README 说明

README 未说明具体显存或 GPU 型号要求；Notebook 面向 Google Colab、Kaggle、SageMaker Studio Lab 等云端环境运行。

支持 Apple Silicon
下载：源码 zip·GitHub Releases（安装包）本站不镜像安装包

项目说明

由 README 自动翻译提炼
没人工点评？写下你的经验

Ultralytics YOLO 官方 Notebook 合集，在 Colab、Kaggle、SageMaker 上直接跑训练、推理和导出

Ultralytics 官方 YOLO 教程合集，提供可直接在 Colab、Kaggle、SageMaker 上运行的 Notebook，覆盖训练、推理、导出及检测、分割、姿态估计等视觉任务。

核心能力

  • 提供开箱即用的 Colab Notebook，一键搭好 YOLO 运行环境
  • 覆盖检测、分割、语义、深度、分类、姿态、OBB 等视觉任务
  • 包含训练、验证、推理、导出全流程示例
  • Notebook 目录由 docs/notebooks-data.yml 自动生成，与官方链接保持同步
  • 同时提供 Kaggle 与 SageMaker Studio Lab 打开入口

容易踩的坑

Notebook 依赖云端环境，本地运行需自行安装 ultralytics 及依赖；部分示例需额外下载对应数据集（如 Carparts 分割数据集）；README 表格由 docs/notebooks-data.yml 自动生成，直接改 README 会被覆盖

内容由模型根据 README 生成，可能不完整或不准确，以官方文档为准。看原文 README

最近发版

1 个版本v0.0.0
全部 release
  1. v0.0.0v0 - Initial Release最新正式版2025-03-27 · 2025-03-27 03:16 UTC

    What's Changed

用户点评

登录用户的真实使用记录，可按版本和硬件筛选
共 0 条

    还没有人点评。第一个说出真实体验的人最有价值。

    README 原文

    未翻译
    在 GitHub 打开

    中文 | 한국어 | 日本語 | Русский | Deutsch | Français | Español | Português | Türkçe | Tiếng Việt | العربية

    📚 Ultralytics Notebooks

    Welcome to Ultralytics Notebooks! This repository provides ready-to-use Google Colab notebooks that streamline the testing and execution of computer vision projects using Ultralytics YOLO models. These resources make it easy to set up environments, run models quickly, and experiment with various features offered by the Ultralytics ecosystem, including training, validation, inference, and export, often integrated with tools like Ultralytics Platform.

    Explore YOLO tasks including Detect, Segment, Semantic, Depth, Classify, Pose, and OBB in the Ultralytics Docs.

    The notebook catalog below is generated from docs/notebooks-data.yml, so the README stays aligned with the published Colab, Kaggle, and SageMaker Studio Lab links.

    NotebookOpen in colab / kaggle / sagemaker studioSupporting materialsDocumentation / arXiv / Repository
    Car Parts Segmentation using Ultralytics YOLOOpen in Colab Open in Kaggle Open in SageMaker Studio LabWatch on YouTube Ultralytics Dataset Ultralytics BlogRead Documentation GitHub
    High Resolution Tiling using Ultralytics YOLOOpen in Colab Open in Kaggle Open in SageMaker Studio Lab-Read Documentation GitHub
    Medical Pills Detection using Ultralytics YOLOOpen in Colab Open in Kaggle Open in SageMaker Studio LabWatch on YouTube Ultralytics Dataset Ultralytics BlogRead Documentation
    Brain Tumor Detection using Ultralytics YOLOOpen in Colab Open in Kaggle Open in SageMaker Studio LabWatch on YouTube Ultralytics Dataset Ultralytics BlogRead Documentation
    Object Counting using Ultralytics YOLOOpen in Colab Open in Kaggle Open in SageMaker Studio LabWatch on YouTubeRead Documentation
    Google Gemini Model for Object Detection, Image Captioning and OCR with Ultralytics UtilitiesOpen in Colab Open in Kaggle Open in SageMaker Studio LabWatch on YouTube Ultralytics BlogRead arXiv paper Read Documentation GitHub
    Automatic Number Plate Recognition with Ultralytics YOLO and OpenAI GPT-4oOpen in Colab Open in Kaggle Open in SageMaker Studio LabWatch on YouTube Ultralytics BlogRead Documentation
    Microsoft Florence-2 for Object Detection, Image Captioning, OCR and Segmentation with Ultralytics PackageOpen in Colab Open in Kaggle Open in SageMaker Studio LabWatch on YouTube Ultralytics BlogRead arXiv paper
    Export Validation Results in Pandas Dataframe, CSV, SQL and Other FormatsOpen in Colab Open in Kaggle Open in SageMaker Studio LabWatch on YouTubeRead Documentation
    HomeObjects-3K Dataset for Everyday Object DetectionOpen in Colab Open in Kaggle Open in SageMaker Studio LabWatch on YouTube Ultralytics DatasetRead Documentation
    Generate Heatmaps using Ultralytics YOLOOpen in Colab Open in Kaggle Open in SageMaker Studio LabWatch on YouTube Ultralytics BlogRead Documentation
    Monitor Your Workouts using Ultralytics YOLOOpen in Colab Open in Kaggle Open in SageMaker Studio LabWatch on YouTube Ultralytics BlogRead Documentation
    Package Segmentation using Ultralytics YOLOOpen in Colab Open in Kaggle Open in SageMaker Studio LabWatch on YouTube Ultralytics Dataset Ultralytics BlogRead Documentation
    Track Objects in a Zone using Ultralytics YOLOOpen in Colab Open in Kaggle Open in SageMaker Studio LabWatch on YouTubeRead Documentation
    Inference using SAM, SAM2 and SAM3 with UltralyticsOpen in Colab Open in Kaggle Open in SageMaker Studio LabWatch on YouTube Ultralytics BlogRead arXiv paper GitHub
    Crack Segmentation using Ultralytics YOLOOpen in Colab Open in Kaggle Open in SageMaker Studio LabWatch on YouTube Ultralytics Dataset Ultralytics BlogRead Documentation
    Queue Management using Ultralytics SolutionsOpen in Colab Open in Kaggle Open in SageMaker Studio LabWatch on YouTube Ultralytics BlogRead Documentation
    Construction-PPE Detection using Ultralytics YOLOOpen in Colab Open in Kaggle Open in SageMaker Studio LabWatch on YouTube Ultralytics Dataset Ultralytics BlogRead Documentation
    Object Detection with KITTI using Ultralytics YOLOOpen in Colab Open in Kaggle Open in SageMaker Studio LabWatch on YouTube Ultralytics DatasetRead Documentation

    💡 Contribute

    Ultralytics thrives on community collaboration, and we deeply value your involvement in our open-source projects! We encourage you to explore our Contributing Guide for detailed insights on how you can participate. Please share your feedback with us by contributing to our Survey. A heartfelt thank you 🙏 goes out to everyone who has already contributed!

    Ultralytics open-source contributors

    📄 License

    Ultralytics offers two distinct licensing options to accommodate various use cases:

    • AGPL-3.0 License: This official OSI-approved open-source license is ideal for students, enthusiasts, and researchers who value open collaboration and knowledge sharing. See the LICENSE file for details.
    • Enterprise License: Designed for commercial use, this license permits the seamless integration of Ultralytics software and AI models into commercial products and services, bypassing the open-source requirements of AGPL-3.0. If your scenario involves commercial deployment, please contact us through Ultralytics Licensing.

    📮 Contact

    For bug reports or feature suggestions related to this notebooks repository, please submit an issue via GitHub Issues. You are also welcome to join our Discord community for discussions, questions, and collaboration with other users and the Ultralytics team. For general inquiries, visit the Ultralytics website.

    相关项目

    同分类里 star 最高的项目
    对比全部 →
    ultralytics
    ultralytics·Python

    YOLO 系列官方实现库，一套 PyTorch 代码覆盖目标检测、实例与语义分割、图像分类、姿态估计和目标跟踪，训练到部署全流程打通。

    目标检测+4检测 / 分割
    63281+9812kv8.4.2082026-11-10 15:51 UTC
    yolov5
    ultralytics·Python

    基于 PyTorch 的目标检测全家桶，覆盖训练、推理、实例分割、图像分类和模型导出，开箱即用，适合快速落地视觉任务。

    目标检测+4检测 / 分割
    58260+717kv7.02026-11-07 16:59 UTC
    pytorch-image-models
    huggingface·Python

    收录最全的 PyTorch 图像骨干网络合集，涵盖 ResNet、ViT、ConvNeXt 等主流模型，自带训练、评估、推理和导出脚本及预训练权重，省去自己搭网络和找权重的麻烦。

    图像分类+4检测 / 分割
    37273+85.2kv1.0.312026-11-07 23:22 UTC
    detectron2
    facebookresearch·Python

    Detectron2 是 Facebook 开源的目标检测与分割平台，提供模块化架构和丰富预训练模型，方便快速搭建和训练视觉识别任务。

    目标检测+4检测 / 分割
    34981+67.9kv0.62026-10-27 09:21 UTC