登录

notebooks

roboflow活跃维护

一套可直接在 Colab 跑的计算机视觉教程合集，覆盖 ResNet 到 RF-DETR、YOLO11、SAM 3、Qwen3-VL 等模型，帮你快速上手训练、微调与推理。

A collection of tutorials on state-of-the-art computer vision models and techniques. Explore everything from foundational architectures like ResNet to cutting-edge models like RF-DETR, YOLO11, SAM 3, and Qwen3-VL.

1.0.0发布于 2022-12-01 22:43 UTC9,742star1,503fork同步于 2026-11-10 11:30 UTC
计算机视觉目标检测图像分割自动标注模型微调
对比 GitHub 官网automatic-labeling-systemcomputer-visiondeep-learningdeep-neural-networksgoogle-colab

怎么上手

由 README 提炼，执行前请确认
原文 
python3 -m venv venv
source venv/bin/activate
pip install notebook
jupyter notebook
硬件要求按 README 说明

README 未说明具体显存或 GPU 型号要求；Notebook 可在 Colab、Kaggle、SageMaker Studio Lab 等云端环境运行，本地运行需自备 Python 环境。

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

Roboflow 官方计算机视觉教程合集，用可运行 Notebook 快速上手 SOTA 模型

一套可直接在 Colab 跑的计算机视觉教程合集，覆盖 ResNet 到 RF-DETR、YOLO11、SAM 3、Qwen3-VL 等模型，帮你快速上手训练、微调与推理。

核心能力

  • 提供 61 个模型教程 Notebook，覆盖检测、分割、姿态与 OCR
  • 涵盖 RF-DETR、YOLO11、SAM 2、Florence-2、Qwen2.5-VL 等模型
  • 每个 Notebook 可一键在 Colab、Kaggle、SageMaker Studio Lab 打开
  • 配套 YouTube 视频、博客文章与论文链接辅助理解
  • 含 RF-DETR 关键点检测微调、ByteTrack 目标跟踪等实战示例

容易踩的坑

Notebook 可能落后于快速迭代的库版本，官方提示如遇报错可提交 bug report；部分教程依赖 Roboflow 账号或在线数据集，需提前准备；大模型类 Notebook 在云端免费环境可能受算力限制。

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1.0.0
全部 release
  1. 1.0.0最新正式版2022-12-01 · 2022-12-01 22:43 UTC

    1.0.0 - 2022-12-01

    First ever release of Roboflow Notebooks 💜!

    🚀 Added

    notebookopen in colab / kaggle / sagemaker studio labcomplementary materialsrepository
    YOLOv7 PyTorch Object DetectionColab KaggleRoboflow YouTubeGitHub
    YOLOv7 PyTorch Object Detection OpenVINO + TorchORTColab KaggleRoboflowGitHub
    MT-YOLOv6 PyTorch Object DetectionColab KaggleRoboflow YouTubeGitHub
    YOLOv5 PyTorch Object DetectionColab KaggleRoboflow [YouTube]

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

    notebooks | inference | autodistill | RF-DETR

    👋 hello

    This repository offers a growing collection of computer vision tutorials. Learn to use SOTA models like YOLOv11, SAM 2, Florence-2, PaliGemma 2, and Qwen2.5-VL for tasks ranging from object detection, segmentation, and pose estimation to data extraction and OCR. Dive in and explore the exciting world of computer vision!

    🚀 model tutorials (61 notebooks)

    notebookopen in colab / kaggle / sagemaker studio labcomplementary materialsrepository / paper
    RF-DETR Keypoint Detection and Fine-TuningColab KaggleGitHub
    Object Detection with Google Gemini 3.5 FlashColab Kaggle
    How to Perform OCR with GLM-OCRColab KaggleYouTubeGitHub arXiv
    How to Track Objects with RF-DETR and ByteTrack TrackerColab KaggleYouTubeGitHub arXiv
    Fine-Tune YOLO26 on Object Detection DatasetColab KaggleRoboflow YouTubeGitHub
    Fine-Tune YOLO26 on Instance Segmentation DatasetColab KaggleRoboflow YouTubeGitHub
    Segment Images with SAM3Colab KaggleRoboflow YouTubeGitHub arXiv
    Segment Videos with SAM3Colab KaggleRoboflow YouTubeGitHub arXiv
    Open Vocabulary Object Detection with Qwen3-VLColab KaggleGitHub
    Fine-Tune RF-DETR Segmentation on Custom DatasetColab KaggleRoboflow YouTubeGitHub arXiv
    Zero-Shot Object Detection and Segmentation with Google Gemini 2.5Colab KaggleRoboflowarXiv
    Fine-Tune RF-DETR on Object Detection DatasetColab KaggleRoboflow YouTubeGitHub arXiv
    Zero-Shot Object Detection and Segmentation with YOLOEColab KaggleRoboflow YouTubeGitHub arXiv
    Fine-Tune YOLOv12 on Object Detection DatasetColab KaggleRoboflowGitHub arXiv
    Zero-Shot Object Detection with Qwen2.5-VLColab KaggleRoboflow YouTubeGitHub arXiv
    Fine-Tune Qwen2.5-VL for JSON Data ExtractionColab KaggleYouTubeGitHub arXiv
    Fine-Tune PaliGemma2 on Object Detection DatasetColab KaggleRoboflowGitHub arXiv
    Fine-Tune PaliGemma2 for JSON Data ExtractionColab KaggleRoboflowGitHub arXiv
    Fine-Tune PaliGemma2 for LaTeX OCRColab KaggleRoboflowGitHub arXiv
    Fine-Tune SAM-2.1Colab KaggleRoboflow YouTubeGitHub
    Fine-Tune GPT-4o on Object Detection DatasetColab KaggleRoboflow YouTube
    Fine-Tune YOLO11 on Object Detection DatasetColab KaggleRoboflow YouTubeGitHub
    Fine-Tune YOLO11 on Instance Segmentation DatasetColab KaggleRoboflow YouTubeGitHub
    Segment Images with SAM2Colab KaggleRoboflow YouTubeGitHub arXiv
    Segment Videos with SAM2Colab KaggleRoboflow YouTubeGitHub arXiv
    Fine-Tune RT-DETR on Object Detection DatasetColab KaggleRoboflowGitHub arXiv
    Fine-Tune Florence-2 on Object Detection DatasetColab KaggleRoboflow YouTubearXiv
    Run Different Vision Tasks with Florence-2Colab KaggleRoboflow YouTubearXiv
    Fine-Tune PaliGemma on Object Detection DatasetColab KaggleRoboflow YouTubeGitHub arXiv
    Fine-Tune YOLOv10 on Object Detection DatasetColab KaggleRoboflowGitHub arXiv
    Zero-Shot Object Detection with YOLO-WorldColab KaggleRoboflow YouTubeGitHub arXiv
    Fine-Tune YOLOv9 on Object Detection DatasetColab KaggleRoboflow YouTubeGitHub arXiv
    Fine-Tune RTMDet on Object Detection DatasetColab KaggleRoboflow YouTubeGitHub arXiv
    Segment Images with FastSAMColab KaggleRoboflow YouTubeGitHub arXiv
    Fine-Tune YOLO-NAS on Object Detection DatasetColab KaggleRoboflow YouTubeGitHub
    Segment Images with Segment Anything Model (SAM)Colab KaggleRoboflow YouTubeGitHub arXiv
    Zero-Shot Object Detection with Grounding DINOColab KaggleRoboflow YouTubeGitHub arXiv
    Fine-Tune DETR Transformer on Object Detection DatasetColab KaggleRoboflow YouTubeGitHub arXiv
    Classify Images with DINOv2Colab KaggleRoboflowGitHub arXiv
    Fine-Tune YOLOv8 on Object Detection DatasetColab KaggleRoboflow YouTubeGitHub
    Fine-Tune YOLOv8 on Pose Estimation DatasetColab KaggleRoboflowGitHub
    Fine-Tune YOLOv8 on Oriented Bounding Boxes (OBB) DatasetColab KaggleRoboflowGitHub
    Fine-Tune YOLOv8 on Instance Segmentation DatasetColab KaggleRoboflow YouTubeGitHub
    Fine-Tune YOLOv8 on Classification DatasetColab KaggleRoboflowGitHub
    Fine-Tune YOLOv7 on Object Detection DatasetColab KaggleRoboflow YouTubeGitHub arXiv
    Fine-Tune YOLOv7 on Instance Segmentation DatasetColab KaggleRoboflow YouTubeGitHub arXiv
    Fine-Tune MT-YOLOv6 on Object Detection DatasetColab KaggleRoboflow YouTubeGitHub arXiv
    Fine-Tune YOLOv5 on Object Detection DatasetColab KaggleRoboflow YouTubeGitHub
    Fine-Tune YOLOv5 on Classification DatasetColab KaggleRoboflow YouTubeGitHub
    Fine-Tune YOLOv5 on Instance Segmentation DatasetColab KaggleRoboflow YouTubeGitHub
    Fine-Tune Faster RCNN on Instance Segmentation DatasetColab KaggleRoboflow YouTubeGitHub arXiv
    Fine-Tune SegFormer on Instance Segmentation DatasetColab KaggleRoboflow YouTubeGitHub arXiv
    Fine-Tune ViT on Classification DatasetColab KaggleRoboflow YouTubeGitHub arXiv
    Fine-Tune Scaled-YOLOv4 on Object Detection DatasetColab KaggleRoboflow YouTubeGitHub arXiv
    Fine-Tune YOLOS on Object Detection DatasetColab KaggleRoboflow YouTubeGitHub arXiv
    Fine-Tune YOLOR on Object Detection DatasetColab KaggleRoboflow YouTubeGitHub arXiv
    Fine-Tune YOLOX on Object Detection DatasetColab KaggleRoboflow YouTubeGitHub arXiv
    Fine-Tune ResNet34 on Classification DatasetColab KaggleRoboflow YouTube
    Image Classification with OpenAI Clip[Colab](https://colab.research.google.com/github/roboflow-ai/notebooks/blob/main/notebooks/how-to-use-openai-clip-classifi

    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
    63270+8712kv8.4.2082026-11-10 09:31 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
    58258+517kv7.02026-11-07 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
    37272+75.2kv1.0.312026-11-07 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
    34980+57.9kv0.62026-10-27 09:21 UTC