YOLOv5mu

yolov5uComing Soon

one-stage detector with CSPDarknet backbone

Parameters25.1M

GFLOPs64.2

Input Size640px

Best mAP48.2%

Licensenon-permissive

Architecture

Type

one-stage

Backbone

CSPDarknet

Neck

PAFPN

Head

Anchor-Free Decoupled

Benchmark Results

Performance on COCO val2017 across different hardware configurations

Hardware	Runtime	mAP@50-95	FPS	Latency	VRAM
NVIDIA Jetson Orin Nano Super 8GB	ONNX Runtime FP32	48.2%	1.6	632.2ms	-
NVIDIA Jetson Orin Nano Super 8GB	PyTorch FP32	48.2%	12.8	77.9ms	142 MB
NVIDIA Jetson Orin Nano Super 8GB	TensorRT FP16	48.2%	27.4	36.5ms	14 MB
Raspberry Pi 5	ncnn FP32	48.2%	3.2	311.9ms	-
Raspberry Pi 5	ONNX Runtime FP32	48.2%	1.2	818.5ms	-
Raspberry Pi 5	PyTorch FP32	48.2%	1.2	824.2ms	-

Speed Breakdown(NVIDIA Jetson Orin Nano Super 8GB)

6.2ms

610.7ms

9.4ms

Preprocess

Inference

Postprocess (NMS)

anchor-freenmsPaper: 49% mAP

Related Models (yolov5u)

YOLOv5nu YOLOv5su YOLOv5lu YOLOv5xu

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