Deep learning model training method

A deep learning and model training technology, applied in the field of deep learning, can solve problems such as poor interactivity

Active Publication Date: 2022-02-01
粤港澳大湾区数字经济研究院(福田)
View PDF14 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The technical problem to be solved by the present invention is to provide a deep learning model training method aimed at solving the problem of poor interaction with users during the model training process in the prior art.

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
  • Deep learning model training method
  • Deep learning model training method
  • Deep learning model training method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0046] In order to make the object, technical solution and advantages of the present invention more clear and definite, the present invention will be further described in detail below with reference to the accompanying drawings and examples. It should be understood that the specific embodiments described here are only used to explain the present invention, not to limit the present invention.

[0047] Please also see Figure 1-Figure 5 , the present invention provides some embodiments of a deep learning model training method.

[0048] Such as figure 1 As shown, the deep learning model training method of the embodiment of the present invention includes the following steps:

[0049] Step S100, acquiring a first data set.

[0050] Specifically, the first data set includes samples and labels corresponding to the samples. According to different training purposes and testing purposes, the first data set is divided into a training set and a testing set, and samples are divided int...

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 discloses a deep learning model training method. The method comprises the steps of obtaining a first data set; setting an initial model parameter and a training suspension condition of the deep learning model, performing multiple times of iterative training on the deep learning model based on the first data set, and calculating a model parameter value generated by each time of iteration according to the initial model parameter; when the training suspension condition is met, generating a model node; and storing the model parameter value generated by the last iteration training as the node information of the model node. According to the deep learning model training method provided by the invention, at least two model nodes can be formed in the training process, and node information is stored. Furthermore, a display interface of the node information can be formed, and interactive operation of deep learning model training is provided on the display interface, so that a user can perform timely adjustment according to the node information of each model node in the training process to obtain an optimal deep learning model more quickly.

Description

technical field [0001] The present invention relates to the technical field of deep learning, in particular to a deep learning model training method. Background technique [0002] With the increasing maturity of AI (Artificial Intelligence) technology and theory, the application fields of AI algorithms are becoming wider and wider, and the business volume is showing a trend of rapid development. In order to free algorithm engineers from tedious engineering development tasks and concentrate on algorithm research and development, various machine learning algorithm platforms have emerged. In the existing technology, most AI algorithm platforms only provide a list of training records sorted by time, the training process cannot be managed, and the interaction with users during the model training process is poor. [0003] Therefore, the prior art still needs to be improved and developed. Contents of the invention [0004] The technical problem to be solved by the present inven...

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): G06N3/08G06N3/10G06N3/04
CPCG06N3/08G06N3/105G06N3/045
Inventor 张家兴李鹏飞郑海波王昊王瑞吴晓均
Owner 粤港澳大湾区数字经济研究院(福田)
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