RT-DETR

rtdetrIn LibreYOLO

Baidu · CVPR 2024

Paper Code

Variants7

Parameters20.0M - 76.0M

Best Paper mAP54.8%

LicenseApache-2.0

Model Variants

All variants benchmarked on COCO val2017. Click any variant for the full hardware breakdown.

Model	Params	GFLOPs	Paper mAP	Best FPS
RT-DETR-R18	20.0M	60.0	46.5%	121 FPS NVIDIA RTX 5070 Ti · TensorRT FP32	Details
RT-DETR-R34	31.0M	91.0	48.5%	108 FPS NVIDIA RTX 5070 Ti · TensorRT FP16	Details
RT-DETR-L	32.0M	110.0	53%	122 FPS NVIDIA RTX 5070 Ti · TensorRT FP16	Details
RT-DETR-R50m	36.6M	0.0	-	110 FPS NVIDIA RTX 5070 Ti · TensorRT FP16	Details
RT-DETR-R50	42.0M	136.0	53.1%	97 FPS NVIDIA RTX 5070 Ti · TensorRT FP16	Details
RT-DETR-X	67.0M	234.0	54.8%	82 FPS NVIDIA RTX 5070 Ti · TensorRT FP16	Details
RT-DETR-R101	76.0M	259.0	54.3%	88 FPS NVIDIA RTX 5070 Ti · TensorRT FP16	Details

Architecture

Type

transformer

Backbone

ResNet-18

Neck

HybridEncoder

Head

DETR

detrnms-freeTrained on COCO train2017

Run any model with one line

LibreYOLO has the best catalogue of state-of-the-art detectors, all behind one MIT-licensed Python API.

from libreyolo import LibreYOLO, SAMPLE_IMAGE # LibreYOLO has the best catalogue of state-of-the-art models. model = LibreYOLO("LibreRFDETRl.pt") # RF-DETR-L (transformer flagship) results = model(SAMPLE_IMAGE, save=True) # run inference, save the annotated image # Swap in any other model, same one-line API (weights auto-download): # LibreYOLO("LibreYOLO9c.pt") # YOLO9-C # LibreYOLO("LibreYOLOXx.pt") # YOLOX-X # LibreYOLO("LibreDFINEx.pt") # D-FINE-X # LibreYOLO("LibreRTDETRr50.pt") # RT-DETR-R50