Pooling operation method and device of convolutional neural network

A technology of convolutional neural network and operation method, which is applied in the field of pooling operation method and device of convolutional neural network, can solve the problem of high energy consumption, achieve the effect of reducing energy consumption and solving high energy consumption

Pending Publication Date: 2018-03-23
GREE ELECTRIC APPLIANCES INC
View PDF6 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] Embodiments of the present invention provide a pooling operation method and device for a convolutional neural network, so as to at least solve the technical problem of high energy consumption caused by the division operation required for the pooling operation 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
  • Pooling operation method and device of convolutional neural network
  • Pooling operation method and device of convolutional neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0022] According to an embodiment of the present invention, a method embodiment of a pooling operation method of a convolutional neural network is provided. It should be noted that the steps shown in the flow chart of the accompanying drawings can be performed on a computer such as a set of computer-executable instructions system, and, although a logical order is shown in the flowcharts, in some cases the steps shown or described may be performed in an order different from that shown or described herein.

[0023] figure 1 is a pooling operation method of a convolutional neural network according to an embodiment of the present invention, such as figure 1 As shown, the method includes the following steps:

[0024] Step S102, performing a summation operation on a plurality of image data to obtain a summation result.

[0025] In the above-mentioned step S102 of the present application, in the convolution layer, the plurality of image data are generated after performing convoluti...

Embodiment 2

[0039] The embodiment of the present invention also provides a pooling operation device for a convolutional neural network. It should be noted that the pooling operation device for the convolutional neural network in this embodiment can be used to implement the pooling operation method for the convolutional neural network in the embodiment of the present invention.

[0040] figure 2 is a schematic diagram of a convolutional neural network pooling operation device according to an embodiment of the present invention. Such as figure 2As shown, the pooling computing device of the convolutional neural network includes: a first computing unit 20 , a second computing unit 22 , a processing unit 24 and a third computing unit 26 .

[0041] Wherein, the first operation unit 20 is used to perform a summation operation on a plurality of image data to obtain a summation result;

[0042] The second operation unit 22 is configured to perform a shift operation on the summation result to ...

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 pooling operation method and device of the convolutional neural network. The method comprises that summation is carried out on different image data to obtain a summation result; shifting is carried out on the summation result to obtain a shifting result; according to the number of the image data and the shifted number in shifting, a weighting factor is determined; and according to the weighting factor, the shifting result is weighted to obtain a pooling result. The method and device of the invention can be used to solve the technical problem that pooling operation inthe prior art needs division operation and causes higher energy consumption.

Description

technical field [0001] The present invention relates to the field of image processing, in particular to a pooling operation method and device of a convolutional neural network. Background technique [0002] At present, with the rapid development of artificial intelligence, the demand for image processing is gradually increasing. For the average pooling operation, the current processing method is to perform summation first, and then divide the summation result. However, the division operation consumes more processor performance, which may easily cause an excessive burden on hardware resources. [0003] For the above problems, no effective solution has been proposed yet. Contents of the invention [0004] Embodiments of the present invention provide a convolutional neural network pooling operation method and device to at least solve the technical problem of high energy consumption caused by division operations required for pooling operations in the prior art. [0005] Acc...

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): G06N3/04
CPCG06T2207/20084G06T2207/20021G06N3/045
Inventor 高灵波
Owner GREE ELECTRIC APPLIANCES 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