Image classification network training method, image classification method and device, and server

Abstract

The invention discloses a training method of an image classification network, an image classification method and device and a server. The training method comprises the following steps: preparing a data set of pictures with labels as input in advance; Constructing corresponding hierarchical neural network structures according to different classification levels; And carrying out hierarchical training on each hierarchical neural network structure to obtain a parent class corresponding to the maximum probability value and probability values of the input pictures under the parent class belonging todifferent subclasses. According to the method and the device, the technical problem of overfitting caused by redundancy of a full connection layer due to very large data set classification data is solved. Through the training method provided by the invention, the phenomena of low network training speed and over-fitting of the network caused by too many full connection layer parameters are solved.According to the image classification method provided by the invention, hierarchical training is adopted, so that a subclass classification result can be more accurately obtained on a classificationresult of a parent class, and accurate classification is realized.

Description

technical field [0001] The present application relates to the field of computer vision, in particular, to a training method for an image classification network, an image classification method and device, and a server. Background technique [0002] For computer vision tasks, image classification is one of the main tasks, such as image recognition, target detection, etc., all of which involve image classification. Usually, the convolutional layer in the convolutional neural network is responsible for extracting features, the pooling layer is responsible for feature selection, and the fully connected layer acts as a classifier. [0003] The inventors found that the parameters of the fully connected layer in the convolutional neural network increase with the increase of the number of types of data sets, resulting in redundant parameters of the fully connected layer, which reduces the training speed and easily causes overfitting . [0004] Aiming at the problem of redundancy in...

AI Technical Summary

Problems solved by technology

[0005] The main purpose of this application is to provide an image classification network training method, image classification method and device, and a server to solve the problem of redundancy in the fully connected layer and overfitting due to the large data set classification data

Images