> [!NOTE] > 本文档由 WeHub 基于上游 README 翻译整理，属于社区翻译，非官方中文文档。 > [English](./README.en.md) · [原始项目](https://github.com/roboflow/rf-detr) · [上游 README](https://github.com/roboflow/rf-detr/blob/HEAD/README.md) > 原作者、版权与许可证归属以原始项目及本仓库 LICENSE 文件为准。 # RF-DETR：实时 SOTA 目标检测、实例分割与关键点检测
[![version](https://badge.fury.io/py/rfdetr.svg)](https://badge.fury.io/py/rfdetr) [![downloads](https://img.shields.io/pypi/dm/rfdetr)](https://pypistats.org/packages/rfdetr) [![codecov](https://codecov.io/gh/roboflow/rf-detr/graph/badge.svg?token=K8V4ARR3XV)](https://codecov.io/gh/roboflow/rf-detr) [![python-version](https://img.shields.io/pypi/pyversions/rfdetr)](https://badge.fury.io/py/rfdetr) [![license](https://img.shields.io/badge/license-Apache%202.0-blue)](https://github.com/roboflow/rf-detr/blob/main/LICENSE) [![arXiv](https://img.shields.io/badge/arXiv-2511.09554-b31b1b.svg)](https://arxiv.org/abs/2511.09554) [![hf space](https://img.shields.io/badge/%F0%9F%A4%97%20Hugging%20Face-Spaces-blue)](https://huggingface.co/spaces/SkalskiP/RF-DETR) [![colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/roboflow-ai/notebooks/blob/main/notebooks/how-to-finetune-rf-detr-on-detection-dataset.ipynb) [![roboflow](https://raw.githubusercontent.com/roboflow-ai/notebooks/main/assets/badges/roboflow-blogpost.svg)](https://blog.roboflow.com/rf-detr) [![discord](https://img.shields.io/discord/1159501506232451173?logo=discord&label=discord&labelColor=fff&color=5865f2&link=https%3A%2F%2Fdiscord.gg%2FGbfgXGJ8Bk)](https://discord.gg/GbfgXGJ8Bk) roboflow%2Frf-detr | Trendshift
--- RF-DETR 是 Roboflow 开发的面向目标检测、实例分割与关键点检测（预览版）的实时 Transformer 架构。基于 DINOv2 视觉 Transformer（Vision Transformer）骨干网络，RF-DETR 在 [Microsoft COCO](https://cocodataset.org/#home) 与 [RF100-VL](https://github.com/roboflow/rf100-vl). 上实现了最先进的精度与延迟权衡。 RF-DETR 采用 DINOv2 视觉 Transformer 骨干网络，并通过统一、一致的 API 支持目标检测、实例分割与关键点检测（预览版）。开源的 `rfdetr` 包及 Apache 指定的模型以 Apache 2.0 发布，而 Plus 组件（`rfdetr_plus`，包括 RF-DETR-XL/2XL 检测模型）则采用 PML 1.0 许可。 已发布的 RF-DETR 各规格均通过神经架构搜索（NAS，Neural Architecture Search）创建——同一 NAS 方法现已在 [Roboflow 平台](https://app.roboflow.com/), 提供，你可据此为自有数据集发现最佳架构。详见 [NAS 文档](https://docs.roboflow.com/train/neural-architecture-search). https://github.com/user-attachments/assets/add23fd1-266f-4538-8809-d7dd5767e8e6 ## 安装 要安装 RF-DETR，请在配备 `pip` 的 [**Python>=3.10**](https://www.python.org/)) 环境中安装 `rfdetr` 包。 ```bash pip install rfdetr ```
从源码安装
从源码安装 RF-DETR，可体验尚未正式发布的新功能与改进。**请注意，这些更新仍在开发中，稳定性可能不及最新正式发布版本。** ```bash pip install https://github.com/roboflow/rf-detr/archive/refs/heads/develop.zip ```
## 基准测试 RF-DETR 在目标检测与实例分割上均达到最先进水平，基准测试结果报告于 Microsoft COCO 与 RF100-VL（RF100-VL 仅用于检测）。下图与下表将 RF-DETR 与其他顶尖实时模型在检测与分割的精度、延迟方面进行对比。所有延迟数据均在 NVIDIA T4 上测得，使用 TensorRT、FP16，批大小为 1。完整基准测试方法与可复现性说明，请参阅 [roboflow/sab](https://github.com/roboflow/single_artifact_benchmarking). ### 检测 rf_detr_1-4_latency_accuracy_object_detection
查看目标检测基准数据
| 架构 | COCO AP50 | COCO AP50:95 | RF100VL AP50 | RF100VL AP50:95 | 延迟 (ms) | 参数量 (M) | 分辨率 | 许可证 | | :-----------: | :------------------: | :---------------------: | :---------------------: | :------------------------: | :----------: | :--------: | :--------: | :--------: | | RF-DETR-N | 67.6 | 48.4 | 85.0 | 57.7 | 2.3 | 30.5 | 384x384 | Apache 2.0 | | RF-DETR-S | 72.1 | 53.0 | 86.7 | 60.2 | 3.5 | 32.1 | 512x512 | Apache 2.0 | | RF-DETR-M | 73.6 | 54.7 | 87.4 | 61.2 | 4.4 | 33.7 | 576x576 | Apache 2.0 | | RF-DETR-L | 75.1 | 56.5 | 88.2 | 62.2 | 6.8 | 33.9 | 704x704 | Apache 2.0 | | RF-DETR-XL △ | 77.4 | 58.6 | 88.5 | 62.9 | 11.5 | 126.4 | 700x700 | PML 1.0 | | RF-DETR-2XL △ | 78.5 | 60.1 | 89.0 | 63.2 | 17.2 | 126.9 | 880x880 | PML 1.0 | | YOLO11-N | 52.0 | 37.4 | 81.4 | 55.3 | 2.5 | 2.6 | 640x640 | AGPL-3.0 | | YOLO11-S | 59.7 | 44.4 | 82.3 | 56.2 | 3.2 | 9.4 | 640x640 | AGPL-3.0 | | YOLO11-M | 64.1 | 48.6 | 82.5 | 56.5 | 5.1 | 20.1 | 640x640 | AGPL-3.0 | | YOLO11-L | 64.9 | 49.9 | 82.2 | 56.5 | 6.5 | 25.3 | 640x640 | AGPL-3.0 | | YOLO11-X | 66.1 | 50.9 | 81.7 | 56.2 | 10.5 | 56.9 | 640x640 | AGPL-3.0 | | YOLO26-N | 55.8 | 40.3 | 76.7 | 52.0 | 1.7 | 2.6 | 640x640 | AGPL-3.0 | | YOLO26-S | 64.3 | 47.7 | 82.7 | 57.0 | 2.6 | 9.4 | 640x640 | AGPL-3.0 | | YOLO26-M | 69.7 | 52.5 | 84.4 | 58.7 | 4.4 | 20.1 | 640x640 | AGPL-3.0 | | YOLO26-L | 71.1 | 54.1 | 85.0 | 59.3 | 5.7 | 25.3 | 640x640 | AGPL-3.0 | | YOLO26-X | 74.0 | 56.9 | 85.6 | 60.0 | 9.6 | 56.9 | 640x640 | AGPL-3.0 | | LW-DETR-T | 60.7 | 42.9 | 84.7 | 57.1 | 1.9 | 12.1 | 640x640 | Apache 2.0 | | LW-DETR-S | 66.8 | 48.0 | 85.0 | 57.4 | 2.6 | 14.6 | 640x640 | Apache 2.0 | | LW-DETR-M | 72.0 | 52.6 | 86.8 | 59.8 | 4.4 | 28.2 | 640x640 | Apache 2.0 | | LW-DETR-L | 74.6 | 56.1 | 87.4 | 61.5 | 6.9 | 46.8 | 640x640 | Apache 2.0 | | LW-DETR-X | 76.9 | 58.3 | 87.9 | 62.1 | 13.0 | 118.0 | 640x640 | Apache 2.0 | | D-FINE-N | 60.2 | 42.7 | 84.4 | 58.2 | 2.1 | 3.8 | 640x640 | Apache 2.0 | | D-FINE-S | 67.6 | 50.6 | 85.3 | 60.3 | 3.5 | 10.2 | 640x640 | Apache 2.0 | | D-FINE-M | 72.6 | 55.0 | 85.5 | 60.6 | 5.4 | 19.2 | 640x640 | Apache 2.0 | | D-FINE-L | 74.9 | 57.2 | 86.4 | 61.6 | 7.5 | 31.0 | 640x640 | Apache 2.0 | | D-FINE-X | 76.8 | 59.3 | 86.9 | 62.2 | 11.5 | 62.0 | 640x640 | Apache 2.0 |
### 实例分割（Segmentation） rf_detr_1-4_latency_accuracy_instance_segmentation
查看实例分割基准测试数据
| Architecture | COCO AP50 | COCO AP50:95 | Latency (ms) | Params (M) | Resolution | License | | :-------------: | :------------------: | :---------------------: | :----------: | :--------: | :--------: | :--------: | | RF-DETR-Seg-N | 63.0 | 40.3 | 3.4 | 33.6 | 312x312 | Apache 2.0 | | RF-DETR-Seg-S | 66.2 | 43.1 | 4.4 | 33.7 | 384x384 | Apache 2.0 | | RF-DETR-Seg-M | 68.4 | 45.3 | 5.9 | 35.7 | 432x432 | Apache 2.0 | | RF-DETR-Seg-L | 70.5 | 47.1 | 8.8 | 36.2 | 504x504 | Apache 2.0 | | RF-DETR-Seg-XL | 72.2 | 48.8 | 13.5 | 38.1 | 624x624 | Apache 2.0 | | RF-DETR-Seg-2XL | 73.1 | 49.9 | 21.8 | 38.6 | 768x768 | Apache 2.0 | | YOLOv8-N-Seg | 45.6 | 28.3 | 3.5 | 3.4 | 640x640 | AGPL-3.0 | | YOLOv8-S-Seg | 53.8 | 34.0 | 4.2 | 11.8 | 640x640 | AGPL-3.0 | | YOLOv8-M-Seg | 58.2 | 37.3 | 7.0 | 27.3 | 640x640 | AGPL-3.0 | | YOLOv8-L-Seg | 60.5 | 39.0 | 9.7 | 46.0 | 640x640 | AGPL-3.0 | | YOLOv8-XL-Seg | 61.3 | 39.5 | 14.0 | 71.8 | 640x640 | AGPL-3.0 | | YOLOv11-N-Seg | 47.8 | 30.0 | 3.6 | 2.9 | 640x640 | AGPL-3.0 | | YOLOv11-S-Seg | 55.4 | 35.0 | 4.6 | 10.1 | 640x640 | AGPL-3.0 | | YOLOv11-M-Seg | 60.0 | 38.5 | 6.9 | 22.4 | 640x640 | AGPL-3.0 | | YOLOv11-L-Seg | 61.5 | 39.5 | 8.3 | 27.6 | 640x640 | AGPL-3.0 | | YOLOv11-XL-Seg | 62.4 | 40.1 | 13.7 | 62.1 | 640x640 | AGPL-3.0 | | YOLO26-N-Seg | 54.3 | 34.7 | 2.31 | 2.7 | 640x640 | AGPL-3.0 | | YOLO26-S-Seg | 62.4 | 40.2 | 3.47 | 10.4 | 640x640 | AGPL-3.0 | | YOLO26-M-Seg | 67.8 | 44.0 | 6.32 | 23.6 | 640x640 | AGPL-3.0 | | YOLO26-L-Seg | 69.8 | 45.5 | 7.58 | 28.0 | 640x640 | AGPL-3.0 | | YOLO26-X-Seg | 71.6 | 46.8 | 12.92 | 62.8 | 640x640 | AGPL-3.0 |
### 关键点（Keypoints） RF-DETR Keypoint mAP vs latency chart comparing against YOLO26-pose and YOLO11-pose on MS COCO
查看关键点检测基准测试数据
| Architecture | COCO AP50:95 | Latency (ms) | License | | :------------------------: | :---------------------: | :----------: | :--------: | | RF-DETR Keypoint (Preview) | 71.8 | 9.7 | Apache 2.0 | | YOLO11-pose N | 48.9 | 3.2 | AGPL-3.0 | | YOLO11-pose S | 57.5 | 3.4 | AGPL-3.0 | | YOLO11-pose M | 64.2 | 5.2 | AGPL-3.0 | | YOLO11-pose L | 65.2 | 6.6 | AGPL-3.0 | | YOLO11-pose X | 68.6 | 10.6 | AGPL-3.0 | | YOLO26-pose N | 55.9 | 1.9 | AGPL-3.0 | | YOLO26-pose S | 62.0 | 2.7 | AGPL-3.0 | | YOLO26-pose M | 68.0 | 4.6 | AGPL-3.0 | | YOLO26-pose L | 69.2 | 5.9 | AGPL-3.0 | | YOLO26-pose X | 71.0 | 9.8 | AGPL-3.0 |
> 关键点基准测试报告 AP50:95（基于 OKS）；这是 COCO 关键点对比的标准指标。 ## 运行模型 ### 检测 RF-DETR 提供多种模型尺寸，从 Nano 到 2XLarge。要使用其他模型尺寸，请将下方代码片段中的类名替换为表格中的其他类。 ```python import supervision as sv from rfdetr import RFDETRMedium from rfdetr.assets.coco_classes import COCO_CLASSES model = RFDETRMedium() detections = model.predict("https://media.roboflow.com/dog.jpg", threshold=0.5) labels = [f"{COCO_CLASSES[class_id]}" for class_id in detections.class_id] annotated_image = sv.BoxAnnotator().annotate(detections.metadata["source_image"], detections) annotated_image = sv.LabelAnnotator().annotate(annotated_image, detections, labels) ``` > **注意：** `COCO_CLASSES` 适用于 COCO 预训练模型。对于微调模型，请改用 `detections.data["class_name"]` —— 它会从 checkpoint 解析类名，并适用于 COCO 和自定义数据集。
使用 Inference 运行 RF-DETR
你也可以使用 Inference 库运行 RF-DETR 模型。要切换模型尺寸，请从下方表格中选择相应的 inference 包别名。 ```python import requests import supervision as sv from PIL import Image from inference import get_model model = get_model("rfdetr-medium") image = Image.open(requests.get("https://media.roboflow.com/dog.jpg", stream=True).raw) predictions = model.infer(image, confidence=0.5)[0] detections = sv.Detections.from_inference(predictions) annotated_image = sv.BoxAnnotator().annotate(image, detections) annotated_image = sv.LabelAnnotator().annotate(annotated_image, detections) ```
| Size | RF-DETR package class | Inference package alias | COCO AP50 | COCO AP50:95 | Latency (ms) | Params (M) | Resolution | License | | :--: | :-------------------: | :---------------------- | :------------------: | :---------------------: | :----------: | :--------: | :--------: | :--------: | | N | `RFDETRNano` | `rfdetr-nano` | 67.6 | 48.4 | 2.3 | 30.5 | 384x384 | Apache 2.0 | | S | `RFDETRSmall` | `rfdetr-small` | 72.1 | 53.0 | 3.5 | 32.1 | 512x512 | Apache 2.0 | | M | `RFDETRMedium` | `rfdetr-medium` | 73.6 | 54.7 | 4.4 | 33.7 | 576x576 | Apache 2.0 | | L | `RFDETRLarge` | `rfdetr-large` | 75.1 | 56.5 | 6.8 | 33.9 | 704x704 | Apache 2.0 | | XL | `RFDETRXLarge` △ | `rfdetr-xlarge` | 77.4 | 58.6 | 11.5 | 126.4 | 700x700 | PML 1.0 | | 2XL | `RFDETR2XLarge` △ | `rfdetr-2xlarge` | 78.5 | 60.1 | 17.2 | 126.9 | 880x880 | PML 1.0 | > △ 需要 `rfdetr_plus` 扩展：`pip install rfdetr[plus]`。详见 [许可证](#license)。 ### 实例分割（Segmentation） RF-DETR 支持实例分割，模型尺寸从 Nano 到 2XLarge。要使用其他模型尺寸，请将下方代码片段中的类名替换为表格中的其他类。 ```python import supervision as sv from rfdetr import RFDETRSegMedium from rfdetr.assets.coco_classes import COCO_CLASSES model = RFDETRSegMedium() detections = model.predict("https://media.roboflow.com/dog.jpg", threshold=0.5) labels = [f"{COCO_CLASSES[class_id]}" for class_id in detections.class_id] annotated_image = sv.MaskAnnotator().annotate(detections.metadata["source_image"], detections) annotated_image = sv.LabelAnnotator().annotate(annotated_image, detections, labels) ```
使用 Inference 运行 RF-DETR-Seg
你也可以使用 Inference 库运行 RF-DETR-Seg 模型。要切换模型尺寸，请从下表中选择相应的 inference 包别名。 ```python import requests import supervision as sv from PIL import Image from inference import get_model model = get_model("rfdetr-seg-medium") image = Image.open(requests.get("https://media.roboflow.com/dog.jpg", stream=True).raw) predictions = model.infer(image, confidence=0.5)[0] detections = sv.Detections.from_inference(predictions) annotated_image = sv.MaskAnnotator().annotate(image, detections) annotated_image = sv.LabelAnnotator().annotate(annotated_image, detections) ```
| Size | RF-DETR package class | Inference package alias | COCO AP50 | COCO AP50:95 | Latency (ms) | Params (M) | Resolution | License | | :--: | :-------------------: | :---------------------- | :------------------: | :---------------------: | :----------: | :--------: | :--------: | :--------: | | N | `RFDETRSegNano` | `rfdetr-seg-nano` | 63.0 | 40.3 | 3.4 | 33.6 | 312x312 | Apache 2.0 | | S | `RFDETRSegSmall` | `rfdetr-seg-small` | 66.2 | 43.1 | 4.4 | 33.7 | 384x384 | Apache 2.0 | | M | `RFDETRSegMedium` | `rfdetr-seg-medium` | 68.4 | 45.3 | 5.9 | 35.7 | 432x432 | Apache 2.0 | | L | `RFDETRSegLarge` | `rfdetr-seg-large` | 70.5 | 47.1 | 8.8 | 36.2 | 504x504 | Apache 2.0 | | XL | `RFDETRSegXLarge` | `rfdetr-seg-xlarge` | 72.2 | 48.8 | 13.5 | 38.1 | 624x624 | Apache 2.0 | | 2XL | `RFDETRSeg2XLarge` | `rfdetr-seg-2xlarge` | 73.1 | 49.9 | 21.8 | 38.6 | 768x768 | Apache 2.0 | ### 关键点 RF-DETR 支持关键点检测（预览版），使用 `RFDETRKeypointPreview`，在 COCO 人体关键点上预训练。 ```python from rfdetr import RFDETRKeypointPreview model = RFDETRKeypointPreview() key_points = model.predict("image.jpg", threshold=0.5) ``` | Size | RF-DETR package class | COCO AP50:95 | Latency (ms) | Params (M) | Resolution | License | | :----------------: | :---------------------: | :---------------------: | :----------: | :--------: | :--------: | :--------: | | Keypoint (Preview) | `RFDETRKeypointPreview` | 71.8 | 9.7 | 126.4 | 576x576 | Apache 2.0 | ### 训练模型 RF-DETR 支持目标检测、实例分割和关键点检测（预览版）的训练。你可以在 [Google Colab](https://colab.research.google.com/github/roboflow-ai/notebooks/blob/main/notebooks/how-to-finetune-rf-detr-on-detection-dataset.ipynb) 中训练模型，或直接在 Roboflow 平台上训练。下方提供了一段分步视频微调教程。 [![rf-detr-tutorial-banner](https://github.com/user-attachments/assets/555a45c3-96e8-4d8a-ad29-f23403c8edfd)](https://youtu.be/-OvpdLAElFA) ## 文档 访问我们的[文档网站](https://rfdetr.roboflow.com)，了解更多关于如何使用 RF-DETR 的信息。 ## 许可证 许可按组件划分： - 开源的 `rfdetr` 包及 Apache 指定的模型权重采用 Apache License 2.0 许可。请参阅 [`LICENSE`](LICENSE)。 - Plus 组件，包括 `rfdetr_plus` 扩展以及 RF-DETR-XL / RF-DETR-2XL 检测模型，采用 PML 1.0 许可。 ## 致谢 我们的工作建立在 [LW-DETR](https://arxiv.org/pdf/2406.03459),、[DINOv2](https://arxiv.org/pdf/2304.07193), 和 [Deformable DETR](https://arxiv.org/pdf/2010.04159). 之上。感谢这些项目的作者出色的工作！ ## 引用 如果你觉得我们的工作对你的研究有帮助，请考虑引用以下 BibTeX 条目。 ```bibtex @inproceedings{robinson2026rfdetr, title = {RF-DETR: Real-Time Detection Transformer}, author = {Robinson, Isaac and Robicheaux, Peter and Popov, Matvei and Ramanan, Deva and Peri, Neehar}, booktitle = {International Conference on Learning Representations (ICLR)}, year = {2026}, url = {https://arxiv.org/abs/2511.09554} } ``` ## 贡献 我们欢迎并感谢所有贡献！如果你发现任何问题或 bug、有疑问，或想建议新功能，请[提交 issue](https://github.com/roboflow/rf-detr/issues/new) 或 pull request。通过分享你的想法和改进，你正在帮助让 RF-DETR 变得更好。