A Construction Method of Weighted Residual Neural Network for Image Classification

Abstract

The invention discloses a method for constructing a weighted residual neural network for image classification, which includes sequentially connecting a convolutional layer, a batch normalization layer, and an activation layer from front to back and packaging them into a root module; using parallel main branches and The bypass branch is encapsulated to obtain the weighted incomplete module; the main branch is encapsulated by repeating the convolution layer, batch normalization layer, and activation layer from front to back several times; if the weighted residual neural network is down-sampled, the side The road branch is composed of a convolutional layer and a bypass branch network in parallel; the bypass branch network is encapsulated by repeating the convolution layer, batch normalization layer, and activation layer from front to back several times; otherwise, the bypass branch It is packaged by repeating the convolutional layer, batch normalization layer, and activation layer from front to back several times; from front to back, the global average pooling layer, fully connected layer, and activation layer are connected in sequence and encapsulated into a head module ; Connect the root module, several weighted incomplete modules and the head module in sequence to obtain a weighted residual neural network.

Description

technical field [0001] The invention relates to the field of image classification in computer machine vision, in particular to a method for constructing a weighted residual neural network for image classification. Background technique [0002] At present, neural network technology in computer vision is widely used in many fields such as image classification, target detection, image segmentation, face recognition, and behavior recognition. In these fields, image classification is the most basic technology. Most of the neural networks used in other fields use the neural network for image classification as their backbone network, which is implemented after adding other functional modules. Therefore, a high-performance image classification network is very important for machine vision based on neural network technology. [0003] Residual network, as a popular type of network in image classification network, mainly utilizes the residual module that can be stacked repeatedly. In...

AI Technical Summary

Problems solved by technology

However, the information output by the main branch has passed through more network layers, and theoretically has richer feature expression information. It is directly added to the output of the bypass branch with fewer network layers, which may weaken the features extracted by the main branch. , thus affecting the improvement of model accuracy

Images