README

RF-DETR: Real-Time SOTA Object Detection, Instance Segmentation, and Keypoint Detection



    

    









---

RF-DETR is a real-time transformer architecture for object detection, instance segmentation, and keypoint detection (preview) developed by Roboflow. Built on a DINOv2 vision transformer backbone (a PE-Core-T backbone for Atto, Femto and Pico), RF-DETR delivers state-of-the-art accuracy and latency trade-offs on Microsoft COCO and RF100-VL.

RF-DETR supports object detection, instance segmentation, and keypoint detection (preview) in a single, consistent API.

Commercially usable under Apache 2.0. The rfdetr package, RF-DETR Nano, Small, Medium and Large detection, every RF-DETR-Seg size (Nano through 2XLarge), and RF-DETR Keypoint are released under the Apache 2.0 license, so they're commercially usable out of the box: you can ship them in closed-source, commercial products, including self-hosted deployments, without paying a license fee or open-sourcing your code. RF-DETR Atto, Femto, Pico, XL and 2XL detection ship in the optional rfdetr[plus] extension under the Roboflow Platform Model License (PML 1.0): commercial use is included when you deploy on Roboflow, and commercial self-hosting requires the Enterprise add-on. See License.

The published RF-DETR sizes were created with neural architecture search (NAS) — and the same NAS method is now available on the Roboflow platform, so you can discover the best architecture for your own dataset. Learn more in the NAS docs.

https://github.com/user-attachments/assets/add23fd1-266f-4538-8809-d7dd5767e8e6

 Install

To install RF-DETR, install the rfdetr package in a Python=3.10 environment with pip.

bash
pip install rfdetr


pip install rfdetr gives you only Apache 2.0 RF-DETR code and models, so it's commercially usable out of the box. pip install "rfdetr[plus]" adds the Atto, Femto, Pico, XL and 2XL detection models under PML 1.0 (commercial use included on Roboflow; commercial self-hosting requires the Enterprise add-on). See License.


Install from source



By installing RF-DETR from source, you can explore the most recent features and enhancements that have not yet been officially released. Please note that these updates are still in development and may not be as stable as the latest published release.

bash
pip install https://github.com/roboflow/rf-detr/archive/refs/heads/develop.zip




 Benchmarks

RF-DETR achieves state-of-the-art results in both object detection and instance segmentation, with benchmarks reported on Microsoft COCO and RF100-VL (RF100-VL for detection only). The charts and tables below compare RF-DETR against other top real-time models across accuracy and latency for detection and segmentation. All COCO accuracy numbers are measured in-house for every model shown, computed with pycocotools in SAB over the full 5,000-image val2017 split, so every row is directly comparable and may differ from vendor-reported figures. The sole exception is rows marked †, which