Mobile Nets-based method for optimizing multi-scale learning network

Abstract

The invention relates to a Mobile Nets-based method for optimizing a multi-scale learning network. According to the invention, the multi-scale learning network comprises four parts. The front three parts of the four parts are composed of identical separable convolution layers, wherein the rear par of each separable convolution layer is connected with bachnorm and ReLU, then connected with a pooling layer, and finally connected with the full-connection layer and the output layer of the fourth part. The separable convolution layer comprises three groups of convolution operations. The specific network structures of the three groups of convolution operations are as follows: the first group is subjected to convolution operation according to the depth convolution of 3 * 3; the second group is subjected to convolution operation according to two continuous depth convolutions of 3 * 3; the outputs of the first and second groups are first subjected to adding operation and then subjected to convolution operation according to the point convolution of 1*1; the third group is subjected to convolution operation directly according to the point convolution of 1*1; the outputs of the first, second and third groups are subjected to combining operation. The experiment comparison shows that, the network structure constructed by the method and disclosed by the invention is few in experimental parameters and high in precision. The three groups of separable convolution layers are stable in structure and the experiment effect is most ideal.

Description

technical field [0001] The invention belongs to the field of image classification, which is mainly applied to mobile and embedded vision applications, and is a lightweight deep neural network proposed for embedded devices such as mobile phones. Image classification is an image processing method that distinguishes different types of objects through the different characteristics reflected in the image information. It uses computer to carry out quantitative analysis on images, and classifies each pixel or area in the image or image into one of several categories to replace human visual interpretation. Background technique [0002] In the context of the development of deep learning, convolutional neural networks have been recognized by more and more people, and their applications are becoming more and more common. The current general development trend of deep learning is to obtain higher accuracy through deeper and more complex networks. However, these deeper and more complex n...

AI Technical Summary

Problems solved by technology

However, compared with other networks with the same number of layers, the existing MobileNets network has optimized the time and number of parameters, but the accuracy is not optimistic.

Images