RF-DETR

RF-DETR is a state-of-the-art real-time object detection model. RF-DETR outperforms all existing object detection models on real world datasets and is the first real-time model to achieve 60+ mean Average Precision when benchmarked on the COCO dataset. RF-DETR is available under an open source Apache 2.0 license.

We introduce the model in our RF-DETR launch post, and have a guide showing how to train and deploy RF-DETR models with Roboflow Inference.