YOLOv9

yolov9In LibreYOLO

Academia Sinica · ECCV 2024

Paper Code

Variants4

Parameters2.0M - 25.5M

Best Paper mAP53%

LicenseMIT

Model Variants

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

Model	Params	GFLOPs	Paper mAP	Best FPS
YOLOv9-T	2.0M	4.0	38.3%	72 FPS NVIDIA RTX 5070 Ti · TensorRT FP32	Details
YOLOv9-S	7.2M	13.5	46.8%	75 FPS NVIDIA RTX 5070 Ti · TensorRT FP32	Details
YOLOv9-M	20.1M	38.7	51.4%	78 FPS NVIDIA RTX 5070 Ti · TensorRT FP32	Details
YOLOv9-C	25.5M	51.8	53%	77 FPS NVIDIA RTX 5070 Ti · TensorRT FP32	Details

Architecture

Type

one-stage

Backbone

GELAN

Neck

PGI

Head

Decoupled

anchor-freenmsTrained 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