Pattern recognition (psychology)

Graphics

Graphics processing unit

FLOPS

Computer graphics

Operating system

Computer graphics (images)

Parallel computing

Artificial intelligence

Programming language

Object detection

Laptop

CUDA

Computer science

Object (grammar)

General-purpose computing on graphics processing units

Pascal (unit)

This paper focuses on YOLO-LITE, a real-time object detection model developed to run on portable devices such as a laptop or cellphone lacking a Graphics Processing Unit (GPU). The model was first trained on the PASCAL VOC dataset then on the COCO dataset, achieving a mAP of 33.81% and 12.26% respectively. YOLO-LITE runs at about 21 FPS on a non-GPU computer and 10 FPS after implemented onto a website with only 7 layers and 482 million FLOPS. This speed is 3.8 × faster than the fastest state of art model, SSD MobilenetvI. Based on the original object detection algorithm YOLOV2, YOLO-LITE was designed to create a smaller, faster, and more efficient model increasing the accessibility of real-time object detection to a variety of devices.

YOLO-LITE: A Real-Time Object Detection Algorithm Optimized for Non-GPU Computers