{
  "source_file": "0930",
  "source_platform": "技术平台",
  "author": "Ultralytics",
  "title_listed": "Ultralytics YOLO11 文档",
  "keywords": "YOLO11,目标检测,检测",
  "domain": "图像处理",
  "content_type": "官方文档",
  "is_paid_flag": "否",
  "url": "https://docs.ultralytics.com/models/yolo11/",
  "publish_date": "持续更新",
  "corpus_stage": "图像处理",
  "notes": "YOLO11 官方文档",
  "id": "8c41e7f9167d",
  "collected_at": "2026-10-02T18:29:17",
  "title": "Ultralytics YOLO11",
  "body_markdown": "Ultralytics YOLO11\n#\nYOLO11\nultralytics\npublic\n11\nReleased September 2024. Current stable release and the recommended choice for all use cases. Best balance of speed, accuracy, and ease of use across all vision tasks.\n17\n25\nmodels\n1 GB\nMay 21, 2026\nyolo11x-obb\nyolo11m-obb\nyolo11n-obb\n+\n22\nOverview\n#\nYOLO11 was released by Ultralytics on September 27, 2024, delivering excellent\naccuracy\n, speed, and efficiency. Building upon the impressive advancements of previous YOLO versions, YOLO11 introduces significant improvements in architecture and training methods, making it a versatile choice for a wide range of\ncomputer vision\ntasks. For the latest Ultralytics model with end-to-end NMS-free inference and optimized edge deployment, see\nYOLO26\n.\nWatch:\nHow to Use Ultralytics YOLO11 for Object Detection and Tracking | How to Benchmark | YOLO11 RELEASED🚀\nTry on Ultralytics Platform\nExplore and run YOLO11 models directly on\nUltralytics Platform\n.\nKey Features\n#\nEnhanced Feature Extraction:\nYOLO11 employs an improved\nbackbone\nand neck architecture, which enhances\nfeature extraction\ncapabilities for more precise object detection and complex task performance.\nOptimized for Efficiency and Speed:\nYOLO11 introduces refined architectural designs and optimized training pipelines, delivering faster processing speeds and maintaining an optimal balance between accuracy and performance.\nGreater Accuracy with Fewer Parameters:\nWith advancements in model design, YOLO11m achieves a higher\nmean Average Precision\n(mAP) on the COCO dataset while using 22% fewer parameters than YOLOv8m, making it computationally efficient without compromising accuracy.\nAdaptability Across Environments:\nYOLO11 can be seamlessly deployed across various environments, including edge devices, cloud platforms, and systems supporting NVIDIA GPUs, ensuring maximum flexibility.\nBroad Range of Supported Tasks:\nWhether it's object detection, instance segmentation, image classification, pose estimation, or oriented object detection (OBB), YOLO11 is designed to cater to a diverse set of computer vision challenges.\nSupported Tasks and Modes\n#\nYOLO11 builds upon the versatile model range established by earlier Ultralytics YOLO releases, offering enhanced support across various computer vision tasks:\nModel\nFilenames\nTask\nTraining\nValidation\nInference\nExport\nYOLO11\nyolo11n.pt\nyolo11s.pt\nyolo11m.pt\nyolo11l.pt\nyolo11x.pt\nDetection\n✅\n✅\n✅\n✅\nYOLO11-seg\nyolo11n-seg.pt\nyolo11s-seg.pt\nyolo11m-seg.pt\nyolo11l-seg.pt\nyolo11x-seg.pt\nInstance Segmentation\n✅\n✅\n✅\n✅\nYOLO11-cls\nyolo11n-cls.pt\nyolo11s-cls.pt\nyolo11m-cls.pt\nyolo11l-cls.pt\nyolo11x-cls.pt\nClassification\n✅\n✅\n✅\n✅\nYOLO11-pose\nyolo11n-pose.pt\nyolo11s-pose.pt\nyolo11m-pose.pt\nyolo11l-pose.pt\nyolo11x-pose.pt\nPose/Keypoints\n✅\n✅\n✅\n✅\nYOLO11-obb\nyolo11n-obb.pt\nyolo11s-obb.pt\nyolo11m-obb.pt\nyolo11l-obb.pt\nyolo11x-obb.pt\nOriented Detection\n✅\n✅\n✅\n✅\nThis table provides an overview of the YOLO11 model variants, showcasing their applicability in specific tasks and compatibility with operational modes such as Inference, Validation, Training, and Export. This flexibility makes YOLO11 suitable for a wide range of applications in computer vision, from real-time detection to complex segmentation tasks.\nPerformance Metrics\n#\nPerformance\nDetection (COCO)\nSegmentation (COCO)\nClassification (ImageNet)\nPose (COCO)\nOBB (DOTAv1)\nSee\nDetection Docs\nfor usage examples with these models trained on\nCOCO\n, which include 80 pretrained classes.\nModel\nsize\n(pixels)\nmAP\nval\n50-95\nSpeed\nCPU ONNX\n(ms)\nSpeed\nT4 TensorRT10\n(ms)\nparams\n(M)\nFLOPs\n(B)\nYOLO11n\n640\n39.5\n56.1 ± 0.8\n1.5 ± 0.0\n2.6\n6.5\nYOLO11s\n640\n47.0\n90.0 ± 1.2\n2.5 ± 0.0\n9.4\n21.6\nYOLO11m\n640\n51.5\n183.2 ± 2.0\n4.7 ± 0.1\n20.1\n68.1\nYOLO11l\n640\n53.4\n238.6 ± 1.4\n6.2 ± 0.1\n25.3\n87.2\nYOLO11x\n640\n54.7\n462.8 ± 6.7\n11.3 ± 0.2\n56.9\n195.3\nUsage Examples\n#\nThis section provides simple YOLO11 training and inference examples. For full documentation on these and other\nmodes\n, see the\nPredict\n,\nTrain\n,\nVal\n, and\nExport\ndocs pages.\nNote that the example below is for YOLO11\nDetect\nmodels for\nobject detection\n. For additional supported tasks, see the\nSegment\n,\nClassify\n,\nPose\n, and\nOBB\ndocs.\nExample\nPython\nCLI\nPyTorch\npretrained\n*.pt\nmodels as well as configuration\n*.yaml\nfiles can be passed to the\nYOLO()\nclass to create a model instance in Python:\nfrom ultralytics import YOLO\n\n# Load a COCO-pretrained YOLO11n model\nmodel = YOLO(\"yolo11n.pt\")\n\n# Train the model on the COCO8 example dataset for 100 epochs\nresults = model.train(data=\"coco8.yaml\", epochs=100, imgsz=640)\n\n# Run inference with the YOLO11n model on the 'bus.jpg' image\nresults = model(\"path/to/bus.jpg\")\nCitations and Acknowledgments\n#\nUltralytics YOLO11 Publication\nUltralytics has not published a formal research paper for YOLO11 due to the rapidly evolving nature of the models. We focus on advancing the technology and making it easier to use, rather than producing static documentation. For the most up-to-date information on YOLO architecture, features, and usage, please refer to our\nGitHub repository\nand\ndocumentation\n.\nIf you use YOLO11 or any other software from this repository in your work, please cite it using the following format:\nQuote\nBibTeX\n@software{yolo11_ultralytics,\n  author = {Glenn Jocher and Jing Qiu},\n  title = {Ultralytics YOLO11},\n  version = {11.0.0},\n  year = {2024},\n  url = {https://github.com/ultralytics/ultralytics},\n  orcid = {0000-0001-5950-6979, 0000-0003-3783-7069},\n  license = {AGPL-3.0}\n}\nPlease note that the DOI is pending and will be added to the citation once it is available. YOLO11 models are provided under\nAGPL-3.0\nand\nEnterprise\nlicenses.\nFAQ\n#\nWhat are the key improvements in Ultralytics YOLO11 compared to YOLOv8?\nUltralytics YOLO11 introduces several significant advancements over YOLOv8. Key improvements include:\nEnhanced Feature Extraction:\nYOLO11 employs an improved backbone and neck architecture, enhancing\nfeature extraction\ncapabilities for more precise object detection.\nOptimized Efficiency and Speed:\nRefined architectural designs and optimized training pipelines deliver faster processing speeds while maintaining a balance between accuracy and performance.\nGreater Accuracy with Fewer Parameters:\nYOLO11m achieves higher mean Average\nPrecision\n(mAP) on the COCO dataset with 22% fewer parameters than YOLOv8m, making it computationally efficient without compromising accuracy.\nAdaptability Across Environments:\nYOLO11 can be deployed across various environments, including edge devices, cloud platforms, and systems supporting NVIDIA GPUs.\nBroad Range of Supported Tasks:\nYOLO11 supports diverse computer vision tasks such as object detection,\ninstance segmentation\n, image classification, pose estimation, and oriented object detection (OBB).\nHow do I train a YOLO11 model for object detection?\nTraining a YOLO11 model for object detection can be done using Python or CLI commands. Below are examples for both methods:\nExample\nPython\nCLI\nfrom ultralytics import YOLO\n\n# Load a COCO-pretrained YOLO11n model\nmodel = YOLO(\"yolo11n.pt\")\n\n# Train the model on the COCO8 example dataset for 100 epochs\nresults = model.train(data=\"coco8.yaml\", epochs=100, imgsz=640)\nFor more detailed instructions, refer to the\nTrain\ndocumentation.\nWhat tasks can YOLO11 models perform?\nYOLO11 models are versatile and support a wide range of computer vision tasks, including:\nObject Detection:\nIdentifying and locating objects within an image.\nInstance Segmentation:\nDetecting objects and delineating their boundaries.\nImage Classification\n:\nCategorizing images into predefined classes.\nPose Estimation:\nDetecting and tracking keypoints on human bodies.\nOriented Object Detection (OBB):\nDetecting objects with rotation for higher precision.\nFor more information on each task, see the\nDetection\n,\nInstance Segmentation\n,\nClassification\n,\nPose Estimation\n, and\nOriented Detection\ndocumentation.\nHow does YOLO11 achieve greater accuracy with fewer parameters?\nYOLO11 achieves greater accuracy with fewer parameters through advancements in model design and optimization techniques. The improved architecture allows for efficient feature extraction and processing, resulting in higher mean Average Precision (mAP) on datasets like COCO while using 22% fewer parameters than YOLOv8m. This makes YOLO11 computationally efficient without compromising on accuracy, making it suitable for deployment on resource-constrained devices.\nCan YOLO11 be deployed on edge devices?\nYes, YOLO11 is designed for adaptability across various environments, including edge devices. Its optimized architecture and efficient processing capabilities make it suitable for deployment on edge devices, cloud platforms, and systems supporting NVIDIA GPUs. This flexibility ensures that YOLO11 can be used in diverse applications, from real-time detection on mobile devices to complex segmentation tasks in cloud environments. For more details on deployment options, refer to the\nExport\ndocumentation.\nContributors\nGL\nglenn-jocher\n18\nRI\nRizwanMunawar\n5\nRA\nraimbekovm\n3\nLA\nLaughing-q\n3\nPD\npderrenger\n3\nY-\nY-T-G\n1\nAM\nambitious-octopus\n1\nCreated\nSep 30, 2024\nUpdated\n2 weeks ago\nComments",
  "metadata": {
    "title": "Ultralytics YOLO11",
    "description": "Discover YOLO11, an advancement in real-time object detection, offering excellent accuracy and efficiency for diverse computer vision tasks.",
    "keywords": "YOLO11,real-time object detection,YOLO series,Ultralytics,computer vision,AI,machine learning,deep learning",
    "author": null,
    "og:title": "Ultralytics YOLO11 | Ultralytics Docs",
    "og:description": "Discover YOLO11, an advancement in real-time object detection, offering excellent accuracy and efficiency for diverse computer vision tasks.",
    "og:url": "https://docs.ultralytics.com/models/yolo11",
    "og:site_name": "Ultralytics Docs",
    "og:locale": "en_US",
    "og:image": "https://raw.githubusercontent.com/ultralytics/assets/refs/heads/main/yolo/performance-comparison.png",
    "og:locale:alternate": "ar_SA",
    "og:type": "article",
    "twitter:card": "summary_large_image",
    "twitter:title": "Ultralytics YOLO11 | Ultralytics Docs",
    "twitter:description": "Discover YOLO11, an advancement in real-time object detection, offering excellent accuracy and efficiency for diverse computer vision tasks.",
    "twitter:image": "https://raw.githubusercontent.com/ultralytics/assets/refs/heads/main/yolo/performance-comparison.png"
  },
  "paywall": {
    "listed_paid": false,
    "detected": false,
    "marker": "",
    "public_only": false,
    "policy": "付费/会员内容只保留页面公开可见部分，不绕过付费墙"
  },
  "crawl": {
    "success": true,
    "status_code": 200,
    "error": ""
  },
  "code_blocks": [
    {
      "file": "attachments/8c41e7f9167d/code/body-000.txt",
      "chars": 320,
      "language": "text"
    },
    {
      "file": "attachments/8c41e7f9167d/code/body-001.txt",
      "chars": 273,
      "language": "text"
    },
    {
      "file": "attachments/8c41e7f9167d/code/body-002.txt",
      "chars": 222,
      "language": "text"
    }
  ],
  "images": [
    {
      "status": "ok",
      "url": "https://raw.githubusercontent.com/ultralytics/assets/refs/heads/main/yolo/performance-comparison.png",
      "bytes": 249803,
      "reused": true,
      "local_path": "attachments/8c41e7f9167d/images/000.png",
      "src": "https://raw.githubusercontent.com/ultralytics/assets/refs/heads/main/yolo/performance-comparison.png",
      "alt": "Ultralytics YOLO11 Comparison Plots",
      "downloaded": true
    }
  ],
  "audio": [],
  "videos": [
    {
      "url": "https://www.youtube.com/watch?v=-JXwa-WlkU8",
      "src": "https://www.youtube-nocookie.com/embed/-JXwa-WlkU8",
      "status": "ok",
      "kind": "single_video",
      "local_path": "attachments/8c41e7f9167d/videos/repair--JXwa-WlkU8.mp4",
      "bytes": 33802960,
      "valid": true,
      "height": 1080,
      "width": 1920,
      "duration": "511.381000",
      "reused": true,
      "reused_from": "xinxing-zimeiti-corpus/attachments/c0a86fefcdd4/videos/-JXwa-WlkU8.mp4"
    }
  ],
  "links": [
    {
      "href": "https://github.com/ultralytics/ultralytics/blob/main/docs/en/models/yolo11.md",
      "label": "",
      "type": "a"
    },
    {
      "href": "https://platform.ultralytics.com/ultralytics/yolo11?utm_source=docs&utm_medium=card",
      "label": "YOLO11 ultralytics public 11 Released September 2024. Current stable release and the recommended choice for all use case",
      "type": "a"
    },
    {
      "href": "https://www.ultralytics.com/glossary/accuracy",
      "label": "accuracy",
      "type": "a"
    },
    {
      "href": "https://www.ultralytics.com/glossary/computer-vision-cv",
      "label": "computer vision",
      "type": "a"
    },
    {
      "href": "https://docs.ultralytics.com/models/yolo26",
      "label": "YOLO26",
      "type": "a"
    },
    {
      "href": "https://www.youtube-nocookie.com/embed/-JXwa-WlkU8",
      "label": "",
      "type": "iframe"
    },
    {
      "href": "https://platform.ultralytics.com/ultralytics/yolo11",
      "label": "Ultralytics Platform",
      "type": "a"
    },
    {
      "href": "https://www.ultralytics.com/glossary/backbone",
      "label": "backbone",
      "type": "a"
    },
    {
      "href": "https://www.ultralytics.com/glossary/feature-extraction",
      "label": "feature extraction",
      "type": "a"
    },
    {
      "href": "https://www.ultralytics.com/glossary/mean-average-precision-map",
      "label": "mean Average Precision",
      "type": "a"
    },
    {
      "href": "https://docs.ultralytics.com/tasks/detect",
      "label": "Detection",
      "type": "a"
    },
    {
      "href": "https://docs.ultralytics.com/tasks/segment",
      "label": "Instance Segmentation",
      "type": "a"
    },
    {
      "href": "https://docs.ultralytics.com/tasks/classify",
      "label": "Classification",
      "type": "a"
    },
    {
      "href": "https://docs.ultralytics.com/tasks/pose",
      "label": "Pose/Keypoints",
      "type": "a"
    },
    {
      "href": "https://docs.ultralytics.com/tasks/obb",
      "label": "Oriented Detection",
      "type": "a"
    },
    {
      "href": "https://docs.ultralytics.com/datasets/detect/coco",
      "label": "COCO",
      "type": "a"
    },
    {
      "href": "https://platform.ultralytics.com/ultralytics/yolo11/yolo11n",
      "label": "YOLO11n",
      "type": "a"
    },
    {
      "href": "https://platform.ultralytics.com/ultralytics/yolo11/yolo11s",
      "label": "YOLO11s",
      "type": "a"
    },
    {
      "href": "https://platform.ultralytics.com/ultralytics/yolo11/yolo11m",
      "label": "YOLO11m",
      "type": "a"
    },
    {
      "href": "https://platform.ultralytics.com/ultralytics/yolo11/yolo11l",
      "label": "YOLO11l",
      "type": "a"
    },
    {
      "href": "https://platform.ultralytics.com/ultralytics/yolo11/yolo11x",
      "label": "YOLO11x",
      "type": "a"
    },
    {
      "href": "https://docs.ultralytics.com/modes",
      "label": "modes",
      "type": "a"
    },
    {
      "href": "https://docs.ultralytics.com/modes/predict",
      "label": "Predict",
      "type": "a"
    },
    {
      "href": "https://docs.ultralytics.com/modes/train",
      "label": "Train",
      "type": "a"
    },
    {
      "href": "https://docs.ultralytics.com/modes/val",
      "label": "Val",
      "type": "a"
    },
    {
      "href": "https://docs.ultralytics.com/modes/export",
      "label": "Export",
      "type": "a"
    },
    {
      "href": "https://www.ultralytics.com/glossary/object-detection",
      "label": "object detection",
      "type": "a"
    },
    {
      "href": "https://www.ultralytics.com/glossary/pytorch",
      "label": "PyTorch",
      "type": "a"
    },
    {
      "href": "https://github.com/ultralytics/ultralytics",
      "label": "GitHub repository",
      "type": "a"
    },
    {
      "href": "https://docs.ultralytics.com/",
      "label": "documentation",
      "type": "a"
    },
    {
      "href": "https://github.com/ultralytics/ultralytics/blob/main/LICENSE",
      "label": "AGPL-3.0",
      "type": "a"
    },
    {
      "href": "https://www.ultralytics.com/license",
      "label": "Enterprise",
      "type": "a"
    },
    {
      "href": "https://www.ultralytics.com/glossary/precision",
      "label": "Precision",
      "type": "a"
    },
    {
      "href": "https://www.ultralytics.com/glossary/instance-segmentation",
      "label": "instance segmentation",
      "type": "a"
    },
    {
      "href": "https://www.ultralytics.com/glossary/image-classification",
      "label": "Image Classification",
      "type": "a"
    },
    {
      "href": "https://github.com/glenn-jocher",
      "label": "GL glenn-jocher 18",
      "type": "a"
    },
    {
      "href": "https://github.com/RizwanMunawar",
      "label": "RI RizwanMunawar 5",
      "type": "a"
    },
    {
      "href": "https://github.com/raimbekovm",
      "label": "RA raimbekovm 3",
      "type": "a"
    },
    {
      "href": "https://github.com/Laughing-q",
      "label": "LA Laughing-q 3",
      "type": "a"
    },
    {
      "href": "https://github.com/pderrenger",
      "label": "PD pderrenger 3",
      "type": "a"
    },
    {
      "href": "https://github.com/Y-T-G",
      "label": "Y- Y-T-G 1",
      "type": "a"
    },
    {
      "href": "https://github.com/ambitious-octopus",
      "label": "AM ambitious-octopus 1",
      "type": "a"
    }
  ],
  "repair_version": 2,
  "repaired_at": "2026-10-14T10:54:54Z",
  "source_url": "https://docs.ultralytics.com/models/yolo11/",
  "papers": [],
  "actual_video_files": [],
  "body_chars": 9129,
  "expected_body_images": 1,
  "discovery_status": "ok",
  "delivery_status": "ok",
  "missing_reason": "",
  "raw_html": "attachments/8c41e7f9167d/pages/source.html",
  "local_html": "attachments/8c41e7f9167d/pages/article.html",
  "body_base_path": "attachments/8c41e7f9167d/pages/",
  "body_markdown_path": "attachments/8c41e7f9167d/pages/article.md"
}