YOLOX

YOLOX is a high-performance object detection model.

Overview

YOLOX (You Only Look One-level eXtended) is an advanced object detection model that builds upon the YOLO (You Only Look Once) series, introducing several innovations to enhance performance and efficiency. Released in July 2021 by Megvii Research, YOLOX transitions to an anchor-free approach, making it more robust and simpler compared to its predecessors.

YOLOX excels in real-time object detection, offering a balance of speed and accuracy suitable for various practical applications such as autonomous driving and video surveillance.

YOLOX achieves state-of-the-art performance in terms of speed and accuracy. For instance, YOLOX-L achieves 50.0% AP on the COCO dataset with a speed of 68.9 FPS on a Tesla V100 GPU, making it highly suitable for real-time applications.

Train and Label your own model using YOLOX

Performance

Model	size	mAP^val 0.5:0.95	mAP^{test 0.5:0.95}	Speed V100 (ms)	Params (M)	FLOPs (G)	weights
YOLOX-s	640	40.5	40.5	9.8	9.0	26.8	github
YOLOX-m	640	46.9	47.2	12.3	25.3	73.8	github
YOLOX-l	640	49.7	50.1	14.5	54.2	155.6	github
YOLOX-x	640	51.1	51.5	17.3	99.1	281.9	github
YOLOX-Darknet53	640	47.7	48.0	11.1	63.7	185.3	github

Use This Model

Label Data Automatically with YOLOX

You can automatically label a dataset using YOLOX with help from Autodistill, an open source package for training computer vision models. You can label a folder of images automatically with only a few lines of code. Below, see our tutorials that demonstrate how to use YOLOX to train a computer vision model.

No items found.