roboflow/rf-detr

GitHub: roboflow/rf-detr

Roboflow 开发的实时 Transformer 目标检测与实例分割模型，在 COCO 上达到 SOTA 水平，支持从边缘到云端的灵活部署和自定义数据集微调。

Stars: 6554 | Forks: 805

# RF-DETR：实时 SOTA 检测与分割 [![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/rfdetr/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://static.pigsec.cn/wp-content/uploads/repos/2026/04/fa591a14fb193851.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) RF-DETR 是由 Roboflow 开发的一种用于目标检测和实例分割的实时 transformer 架构。RF-DETR 基于 DINOv2 视觉 transformer 主干网络构建，在 [Microsoft COCO](https://cocodataset.org/#home) 和 [RF100-VL](https://github.com/roboflow/rf100-vl) 上实现了准确率与延迟之间最先进的权衡。 RF-DETR 使用 DINOv2 视觉 transformer 主干网络，并在单一、一致的 API 中同时支持检测和实例分割。开源的 `rfdetr` 包和 Apache 指定的模型均在 Apache 2.0 下发布，而 Plus 组件（`rfdetr_plus`，包括 RF-DETR-XL/2XL 检测模型）则在 PML 1.0 下授权。 https://github.com/user-attachments/assets/add23fd1-266f-4538-8809-d7dd5767e8e6 ## 安装 要安装 RF-DETR，请在 [**Python>=3.10**](https://www.python.org/) 环境中使用 `pip` 安装 `rfdetr` 包。 ``` pip install rfdetr ```
从源码安装
通过从源码安装 RF-DETR，您可以探索尚未正式发布的最新功能和增强特性。**请注意，这些更新仍在开发中，可能不如最新发布的版本稳定。** ``` pip install https://github.com/roboflow/rf-detr/archive/refs/heads/develop.zip ```
## 基准测试 RF-DETR 在目标检测和实例分割方面均取得了最先进的结果，其在 Microsoft COCO 和 RF100-VL 上的基准测试结果均有报告。下方的图表和表格在检测和分割的准确率和延迟方面将 RF-DETR 与其他顶级实时模型进行了比较。所有延迟数值均在使用 TensorRT、FP16 和 batch size 为 1 的 NVIDIA T4 上进行测量。有关完整的基准测试方法和可复现性详细信息，请参阅 [roboflow/sab](https://github.com/roboflow/single_artifact_benchmarking)。 ### 检测 rf_detr_1-4_latency_accuracy_object_detection
查看目标检测基准测试数据
| Architecture | COCO AP50 | COCO AP50:95 | RF100VL AP50 | RF100VL AP50:95 | Latency (ms) | Params (M) | Resolution | License | | :-----------: | :------------------: | :---------------------: | :---------------------: | :------------------------: | :----------: | :--------: | :--------: | :--------: | | 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 |
### 分割 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 | 362 | 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 |
## 运行模型 ### 检测 RF-DETR 提供从 Nano 到 2XLarge 的多种模型大小。要使用不同的模型大小，请将下方代码片段中的类名替换为表格中的其他类。 ``` 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) ```
使用 Inference 运行 RF-DETR
您也可以使用 Inference 库运行 RF-DETR 模型。要切换模型大小，请从下表中选择相应的 inference 包别名。 ``` 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 | ### 分割 RF-DETR 支持从 Nano 到 2XLarge 的多种模型大小的实例分割。要使用不同的模型大小，请将下方代码片段中的类名替换为表格中的其他类。 ``` 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
您也可以使用 Inference 库运行 RF-DETR-Seg 模型。要切换模型大小，请从下表中选择相应的 inference 包别名。 ``` 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 | ### 训练模型 RF-DETR 支持目标检测和实例分割的训练。您可以在 [Google Colab](https://colab.research.google.com/github/roboflow-ai/notebooks/blob/main/notebooks/how-to-finetune-rf-detr-on-detection-dataset.ipynb) 中或直接在 Roboflow 平台上训练模型。下方是一个循序渐进的微调视频教程。 [![rf-detr-tutorial-banner](https://static.pigsec.cn/wp-content/uploads/repos/2026/04/1fb895c14d193852.png)](https://youtu.be/-OvpdLAElFA) ## 文档 访问我们的[文档网站](https://rfdetr.roboflow.com)以了解更多关于如何使用 RF-DETR 的信息。 ## 许可证 授权因组件而异： - 开源的 `rfdetr` 包和 Apache 指定的模型权重均采用 Apache License 2.0 授权。参见 [`LICENSE`](LICENSE)。 - Plus 组件，包括 `rfdetr_plus` 扩展以及 RF-DETR-XL / RF-DETR-2XL 检测模型，均在 PML 1.0 下授权。 ## 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。感谢他们的作者做出的卓越工作！ ## 引用 如果您觉得我们的工作对您的研究有帮助，请考虑引用以下 BibTeX 条目。 ``` @misc{rf-detr, title={RF-DETR: Neural Architecture Search for Real-Time Detection Transformers}, author={Isaac Robinson and Peter Robicheaux and Matvei Popov and Deva Ramanan and Neehar Peri}, year={2025}, eprint={2511.09554}, archivePrefix={arXiv}, primaryClass={cs.CV}, url={https://arxiv.org/abs/2511.09554}, } ``` ## 贡献 我们欢迎并感谢所有的贡献！如果您注意到任何问题或错误、有任何疑问，或者想提出新功能，请[创建 issue](https://github.com/roboflow/rf-detr/issues/new) 或 pull request。通过分享您的想法和改进，您将帮助所有人打造更好的 RF-DETR。

标签：COCO数据集, DINOv2, Hugging Face, PyTorch, RF-DETR, Roboflow, SOTA模型, Transformer, 凭据扫描, 图像处理, 实例分割, 实时推理, 实时模型, 开源模型, 微调, 机器学习算法, 深度学习, 目标检测, 系统调用监控, 视觉Transformer, 计算机视觉, 逆向工具