Convolutional neural network compression method based on global feature relationship

A technology of convolutional neural network and compression method, which is applied in the field of convolutional neural network compression based on global feature relationship, which can solve the problems of slow inference speed, large memory occupation of network model, and complex model.

Inactive Publication Date: 2021-02-02
HUNAN UNIV
View PDF2 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] However, due to the complex model of the traditional convolutional neural network, the network model takes up a large amount of memory and the inference speed is slow; this seriously hinders the app

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
  • Convolutional neural network compression method based on global feature relationship
  • Convolutional neural network compression method based on global feature relationship
  • Convolutional neural network compression method based on global feature relationship

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0031] The present invention will be further described below in conjunction with the accompanying drawings.

[0032] figure 1 The flow chart of the convolutional neural network compression method based on the global feature relationship proposed by the embodiment of the present invention is given.

[0033] refer to figure 1 , a convolutional neural network compression method based on global feature relations, comprising the following steps:

[0034] Step 1: Add the GFR sub-module after the BN layer of the convolutional neural network model, and perform sparse processing on the network model;

[0035] Step 2: Retrain the model, extract the relationship factor sr of each channel and the scale factor γ of the BN layer;

[0036] Step 3: Evaluate the importance of each channel, and then sort all channels according to the importance of the channel;

[0037] Step 4: According to the ranking results of all channels, the model is compressed using the fast compression method.

[00...

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 belongs to the field of computer science, and discloses a convolutional neural network compression method based on a global feature relationship. According to the method, a global feature relationship (GFR) submodule is added behind a Batch Normalization (BN) layer of the convolutional neural network, so that the aims of extracting a channel relationship and suppressing an unimportant channel are fulfilled. The GFR sub-module mainly relates to pooling, full connection layer and moving average operation. Then, the importance degree of each channel is evaluated by combining the channel relationship and the channel scale factor of the BN layer, and the index can help the model compression method to screen out important channels in the model more accurately. And finally, by utilizing a channel pruning algorithm and a grid search technology, the compression of the network model is completed by consuming less time and computing resources without finely adjusting the model, so the running memory and the storage memory of the model are remarkably reduced, and the deduction speed of the model is increased, so the possibility of deploying the convolutional neural network on thesmall mobile device is greatly improved.

Description

technical field [0001] The invention belongs to the field of computer science and relates to the application of artificial intelligence technology, in particular to a convolutional neural network compression method based on global feature relationships. Background technique [0002] Thanks to the in-depth development of GPU and other computing platforms, deep learning was born and developed rapidly, which greatly narrowed the gap between science and practical application. The deep learning model represented by Convolutional Neural Network (CNN) has made amazing achievements in the fields of computer vision and natural language processing. Various vision tasks such as pattern recognition, image classification, object detection, etc. are well done. [0003] However, due to the complex model of the traditional convolutional neural network, the network model takes up a large amount of memory and the inference speed is slow; this seriously hinders the application of the convolut...

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): G06N3/04G06N3/08G06K9/62
CPCG06N3/082G06N3/045G06F18/214
Inventor 彭绍亮程英杰王小奇何芒芒赵雄君白亮李肯立
Owner HUNAN UNIV
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