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

A method and apparatus for generating a model

A technology for generating models and initial models, applied in the computer field, can solve the problems of large differences in sample acquisition difficulty and unbalanced number of samples, and achieve the effect of balancing the number and improving the accuracy.

Active Publication Date: 2019-03-08
BEIJING BYTEDANCE NETWORK TECH CO LTD
View PDF9 Cites 11 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, in the sample set used for model training, due to the large difference in the difficulty of obtaining samples of different categories, the number of samples of different categories in the sample set is unbalanced

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
  • A method and apparatus for generating a model
  • A method and apparatus for generating a model
  • A method and apparatus for generating a model

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0031] The present application will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the related invention, but not to limit the invention. In addition, it should be noted that, for the convenience of description, only the parts related to the related invention are shown in the drawings.

[0032] It should be noted that the embodiments in the present application and the features of the embodiments may be combined with each other in the case of no conflict. The present application will be described in detail below with reference to the accompanying drawings and in conjunction with the embodiments.

[0033] figure 1 An exemplary system architecture 100 is shown to which the method for generating a model or the apparatus for generating a model of the present application may be applied.

[0034] like figure 1 As shown, the system arch...

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

A method and apparatus for generating a model is disclosed in embodiment of that present application. One embodiment of the method includes obtaining a sample set; extracting a subset of partial samples in the sample set, and performing the following training steps of inputting the samples in the subset to an initial model, determining a loss value of each sample inputted based on the informationoutputted from the initial model and the class annotation carried by the samples in the subset; selecting the loss value of the positive sample and the loss value of the part of the negative sample inthe subset, and determine the average value of the selected loss value as the target loss value; determining whether the initial model training is completed based on the target loss value; if so, determining the initial model after training as the category detection model. This embodiment improves the accuracy of the generated model.

Description

technical field [0001] The embodiments of the present application relate to the field of computer technology, and in particular, to a method and an apparatus for generating a model. Background technique [0002] In the field of machine learning, it is usually necessary to use sample sets for model training. However, in the sample set used for model training, since the difficulty of obtaining samples of different categories is quite different, the number of samples of different categories in the sample set is not balanced. As an example, when training is used to detect video categories (for example, it is divided into abnormal category videos and normal category videos), the sample set used, usually the number of positive samples (non-normal category videos) is very small. And negative samples (normal category videos) are more. [0003] The related method is usually to directly use the sample set and use the supervised learning method for model training. SUMMARY OF THE IN...

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): G06K9/62G06K9/00
CPCG06V20/41G06F18/214
Inventor 袁泽寰王长虎
Owner BEIJING BYTEDANCE NETWORK 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