Model expansion method and device, electronic device and storage medium

An extension method and model technology, applied in the computer field, can solve the problems of consuming a lot of computing resources, more training time, poor fitting effect of neural network, etc., and achieve good fitting effect

Active Publication Date: 2019-01-08
BEIJING SENSETIME TECH DEV CO LTD
View PDF6 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0002] With the rapid growth of training data, it is necessary to design a deeper or wider neural network to fit the training data, but directly using these data to retrain a deeper or wider model will consume a lot

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
  • Model expansion method and device, electronic device and storage medium
  • Model expansion method and device, electronic device and storage medium
  • Model expansion method and device, electronic device and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0077] Various exemplary embodiments, features, and aspects of the present disclosure will be described in detail below with reference to the accompanying drawings. The same reference numbers in the figures indicate functionally identical or similar elements. While various aspects of the embodiments are shown in drawings, the drawings are not necessarily drawn to scale unless specifically indicated.

[0078] The word "exemplary" is used exclusively herein to mean "serving as an example, embodiment, or illustration." Any embodiment described herein as "exemplary" is not necessarily to be construed as superior or better than other embodiments.

[0079] In addition, in order to better illustrate the present disclosure, numerous specific details are given in the following specific implementation manners. It will be understood by those skilled in the art that the present disclosure may be practiced without some of the specific details. In some instances, methods, means, componen...

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 present disclosure relates to a model expansion method and device, an electronic device and a storage medium. The method includes: determining importance parameters of a plurality of nodes according to activation values and gradients of activation values of a plurality of nodes in a plurality of network layers of a first model; determining a node to be expanded among the plurality of nodes according to an importance parameter of the plurality of nodes and a preset growth ratio of the plurality of network layers; expanding the first model according to the nodes to be expanded of the plurality of network layers, and obtaining a second model. The disclosed embodiment can determine the nodes to be expanded among a plurality of nodes through the importance parameter, and expand the first model to obtain a second model, and the nodes in the first model can be used to obtain the second model, so that excessive computational resources and training time need not be consumed, and the fittingeffect is good.

Description

technical field [0001] The present disclosure relates to the field of computer technology, and in particular to a model extension method and device, electronic equipment and a storage medium. Background technique [0002] With the rapid growth of training data, it is necessary to design a deeper or wider neural network to fit the training data, but directly using these data to retrain a deeper or wider model will consume a lot of computing resources and take more training time. And when using existing data to train a deeper or wider neural network, the amount of data may not be enough, so the fitting effect of the neural network may be poor. Contents of the invention [0003] The disclosure proposes a model extension method and device, electronic equipment, and a storage medium. [0004] According to an aspect of the present disclosure, a model extension method is provided, including: [0005] determining the importance parameters of the plurality of nodes according to t...

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
IPC IPC(8): G06N3/04G06N3/08
CPCG06N3/082G06N3/045
Inventor 张学森伊帅闫俊杰王晓刚
Owner BEIJING SENSETIME TECH DEV 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

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap