Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Image classification model training method and device, electronic equipment and computer readable storage medium

A classification model and training method technology, applied in computer components, calculation, biological neural network models, etc., can solve problems such as classification errors, and achieve the effect of improving image classification accuracy

Pending Publication Date: 2020-08-18
BEIJING DAJIA INTERNET INFORMATION TECH CO LTD
View PDF7 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] However, in related technologies, although the current image classification model has a certain ability to classify images, there will still be a large number of classification errors.

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 model training method and device, electronic equipment and computer readable storage medium
  • Image classification model training method and device, electronic equipment and computer readable storage medium
  • Image classification model training method and device, electronic equipment and computer readable storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0050] Please refer to figure 1 , figure 1 It is a flowchart of an image classification model training method for image classification provided according to an exemplary embodiment. The image classification model training method can be executed by, but not limited to, an image classification model training device in an electronic device. The electronic device can be A server or a terminal device, etc. In practical applications, the terminal device may be a computer, a smart phone, an IPAD, a wearable device, or the like. refer to figure 1 , the image classification model training method may include the following steps.

[0051] S10, selecting a preset number of image samples to form a training data set, wherein each image sample corresponds to a classification label and an image semantic feature.

[0052] Wherein, the number of image samples in the training data set, that is, the value of the aforementioned preset number can be flexibly set according to requirements. It sh...

Embodiment 2

[0082] image 3 It is a block diagram of an image classification model training device 100 for image classification according to an exemplary embodiment, and the image classification model training device 100 can be applied to electronic equipment. refer to image 3 , the image classification model training device includes a sample selection module 110 , a model training module 120 and a parameter adjustment module 130 .

[0083] The sample selection module 110 is configured to select a preset number of image samples to form a training data set, wherein each image sample corresponds to a classification label and an image semantic feature;

[0084] The model training module 120 is configured to input the image samples in the training data set into a preset image classification model, and obtain the classification result of each image sample in the training data set output by the image classification model;

[0085] The parameter adjustment module 130 is configured to adjust t...

Embodiment 3

[0091] see Figure 4 , is a block diagram of an electronic device 10 provided according to an exemplary embodiment, the electronic device 10 may include at least a processor 11, and a memory 12 for storing instructions executable by the processor 11. Wherein, the processor 11 is configured to execute instructions to implement all or part of the steps of the image classification model training method in the above-mentioned embodiments.

[0092] The processor 11 and the memory 12 are directly or indirectly electrically connected to realize data transmission or interaction. For example, these components can be electrically connected to each other through one or more communication buses or signal lines.

[0093] Wherein, the processor 11 is used for reading / writing data or programs stored in the memory, and executing corresponding functions.

[0094] The memory 12 is used for storing programs or data, such as storing instructions executable by the processor 11 . This memory 12 ...

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 invention relates to an image classification model training method and device for image classification, electronic equipment and a computer readable storage medium, and relates to the technical field of artificial intelligence. Wherein when the image classification model is trained, model parameters of the image classification model are adjusted and optimized through a constructed joint loss function containing an image semantic feature loss function, so that the image classification precision of the image classification model is improved.

Description

technical field [0001] The present disclosure relates to the technical field of artificial intelligence, and in particular to an image classification model training method, device, electronic equipment, and computer-readable storage medium. Background technique [0002] Recently, deep learning has been widely used in image recognition, speech recognition, natural language processing and other related fields. As an important branch of deep learning, convolutional neural network (CNN) has greatly improved the prediction accuracy of image classification tasks due to its strong fitting ability and end-to-end global optimization ability. [0003] However, in related technologies, although the current image classification model has a certain ability to classify images, a large number of classification errors still occur. Contents of the invention [0004] The present disclosure provides an image classification model training method, device, electronic equipment, and computer-re...

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): G06K9/62G06N3/04
CPCG06N3/045G06F18/214Y02T10/40
Inventor 张志伟李铅
Owner BEIJING DAJIA INTERNET INFORMATION TECH CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com