Image classification method and device, equipment and storage medium

A classification method and image technology, applied in the field of machine learning, can solve problems such as poor classification effect and unbalanced distribution of data samples, and achieve the effect of balanced sample size and enhanced image classification effect

Pending Publication Date: 2021-08-10
BEIJING YOUZHUJU NETWORK TECH CO LTD
View PDF8 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] In order to solve the problem of poor classification effect due to the unbalanced distribution of data samples of different image categories in the prior art, this application proposes an image classification method and a model training method

Method used

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
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Image classification method and device, equipment and storage medium
  • Image classification method and device, equipment and storage medium
  • Image classification method and device, equipment and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0061] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiment of the application will be clearly and completely described below in conjunction with the accompanying drawings in the embodiment of the application. Obviously, the described embodiment is only It is a part of the embodiments of this application, not all of them. Based on the embodiments in this application, all other embodiments obtained by persons of ordinary skill in the art without making creative efforts belong to the scope of protection of this application.

[0062] Currently, the field of machine learning includes image or video classification problems, for example, a certain type of image or video can be classified as people, animals, scenery, etc. Image classification can be divided into many categories, and the sample size of each category is not the same, and the sample size distribution is also uneven. In the cas...

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

PUM

No PUM Login to view more

Abstract

The embodiment of the invention discloses an image classification method and device, equipment and a storage medium, and each image classification model in a plurality of image classification models is obtained by training a training image of a corresponding class cluster; the class clusters are obtained by dividing the classes corresponding to the class labels according to the sample sizes corresponding to the class labels of the training images, each class cluster comprises one or more classes of training images, and the sample sizes included in each class cluster are relatively balanced; therefore, when the image classification model is trained, due to the fact that the sample sizes of each class cluster are relatively balanced, the image classification effect is enhanced.

Description

technical field [0001] The present application relates to the field of machine learning, and in particular to an image classification method, device, equipment and storage medium. Background technique [0002] With the rapid development of computer technology, many technological advances have been made in the field of machine learning. In the field of machine learning, it is mainly to train neural network models to predict or process certain data to replace repeated manual operations, such as training neural network models to achieve computer vision, speech recognition, natural language processing or image classification. [0003] When training neural networks for image classification, there is a very important problem: the data samples of different image categories are not evenly distributed. The unbalanced distribution of data samples of different image categories will lead to the classification results of the machine learning process will be more biased towards the categ...

Claims

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

Application Information

Patent Timeline
no application Login to view more
Patent Type & Authority Applications(China)
IPC IPC(8): G06K9/62G06N3/08
CPCG06N3/08G06F18/2321G06F18/214G06F18/2415
Inventor 陈伟聪赵妍黄凯王长虎
Owner BEIJING YOUZHUJU NETWORK TECH CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products