Classification network and implementation method and device thereof

A technology of classification network and implementation method, which is applied in the field of neural network, can solve the problems of high complexity of classification network and large memory usage, and achieve the effects of improving training efficiency, simplifying network structure and saving manpower

Pending Publication Date: 2021-05-07
GOERTEK INC
View PDF4 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the classification network based on the IRv2 algorithm also has problems

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
  • Classification network and implementation method and device thereof
  • Classification network and implementation method and device thereof
  • Classification network and implementation method and device thereof

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0027] In order to make the purpose, technical solution and advantages of the present application clearer, the technical solution of the present application will be clearly and completely described below in conjunction with specific embodiments of the present application and corresponding drawings. Apparently, the described embodiments are only some of the embodiments of the present application, rather than all the embodiments. 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.

[0028] In order to expand the applicable scenarios of the classification neural network, reduce the training and reasoning time of the classification neural network, and compress the model size of the classification neural network, a large number of pruning, compression and quantization methods have been proposed in the academic community. Pruning, co...

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 classification network and an implementation method and device thereof, and the method comprises the steps: constructing a classification network which comprises a Stem module, a plurality of Inception modules and a plurality of IR modules based on an IRv2 algorithm, wherein a batch standardization BN layer of the classification network uses a gamma parameter; initializing the classification network, and performing sparse training on the initialized classification network to obtain a sparse gamma parameter; on the basis of the sparse gamma parameter, carrying out the network slip pruning on the Stem module, the pruning Inception module and the plurality of IR modules, wherein network slip pruning is not carried out on the non-pruning Inception module. According to the technical scheme, the classification effect of the classification network can be ensured, and meanwhile, simplification of a network structure is realized, so the training efficiency is improved, the reasoning time and memory occupation are reduced, manpower, working hours and funds are saved, and the classification network can be deployed on hardware equipment with different computing power.

Description

technical field [0001] The present application relates to the technical field of neural networks, in particular to a classification network and its implementation method and device. Background technique [0002] The full name of the IRv2 algorithm is Inception-ResNet-v2, which is the second generation algorithm that combines Inception and ResNet (residual network) for classification. Combining the advantages of Inception and ResNet, it can obtain a deeper classification network and better classification performance. very good. However, the classification network based on the IRv2 algorithm also has problems such as high complexity and large memory usage, which need to be solved urgently. Contents of the invention [0003] The embodiment of the present application provides a classification network and its implementation method and device, which can not only ensure the classification effect of the classification network, but also reduce the complexity of the classification ...

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): G06K9/62G06N3/04G06N3/08
CPCG06N3/08G06N3/047G06N3/045G06F18/2415
Inventor 冯蓬勃张一凡刘杰
Owner GOERTEK INC
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