Convolutional neural network optimization and rapid target detection method and device

Abstract

The invention discloses a convolutional neural network optimization and rapid target detection method and device. The optimization method comprises the steps of obtaining a first convolutional model trained by adopting floating point type sample image data; wherein a BN layer operation in the first convolution model is located behind convolution layer operation and is used for normalizing a numerical value obtained after the convolution layer operation to a preset data range; adjusting parameters of a convolutional layer according to the parameters of the BN layer; deleting the BN layer to obtain an adjusted second convolution model; adding a quantization layer before the convolution operation of the convolution layer in the second convolution model to obtain a third convolution model; wherein the quantization layer is used for quantizing input data to integer data of a predetermined bit, and enabling a convolution layer to perform convolution operation by using the integer data of thepredetermined bit. According to the method, the problems of large model body quantity and low operation speed are solved by optimizing the convolution operation.

Description

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine

Login to view more

AI Technical Summary

Benefits of technology

This technology improves how we process images through an algorithm called Convolution Neural Network (CNN). It integrates certain features from each image frame together for faster processing speeds or better accuracy than previous methods like Fast Fourier Transform techniques that took multiple frames over time. By doing this, CNN can handle larger models without taking up too much storage space compared to traditional approaches such as Random Forests algorithms.

Problems solved by technology

Technics: Current methods for detecting targets involve performing complex calculations on images captured through cameras attached to vehicles. These techniques require significant processing power due to their high computational complexity and slow speed compared to other systems like computer vision algorithms. Additionally, these current approaches use fixed point samples instead of moving ones which further complicates the process.

Images