Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Convolution operation method and device of convolutional neural network

A convolutional neural network and operation method technology, applied in the field of artificial intelligence algorithms, can solve problems such as increasing the power consumption of digital-to-analog converters, and achieve the effect of reducing digital-to-analog conversion consumption and energy consumption

Pending Publication Date: 2022-07-15
INST OF MICROELECTRONICS CHINESE ACAD OF SCI
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] Among them, when performing convolution calculation on the data in the macro window, it is necessary to extract the same data multiple times for convolution calculation, and each time the data is extracted, the memory needs to be read, and, after each reading of the data, The process of convolution calculation through the digital-to-analog converter also increases the power consumption of the digital-to-analog converter

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
  • Convolution operation method and device of convolutional neural network
  • Convolution operation method and device of convolutional neural network
  • Convolution operation method and device of convolutional neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0054] Embodiment 1 of the present invention provides a convolution operation method of a convolutional neural network, such as figure 2 shown, including:

[0055] S201, acquiring an input voltage used to characterize a pixel value.

[0056] S202, when the input voltage is scanned through the convolution sliding window, the multiplexing times of the input voltage in the convolution sliding window is obtained.

[0057] S203 , grouping the input voltages based on the difference in the multiplexing times of the input voltages.

[0058] S204 , extract the input voltages in the same group once, and perform convolution calculation with the convolution kernel respectively to obtain a result corresponding to each group.

[0059] S205, based on the result corresponding to each grouping, obtain the result of the convolution operation, so as to realize the convolution operation in the convolutional neural network.

[0060] In an optional implementation manner, the input voltage used ...

Embodiment 2

[0097] Based on the same inventive concept, an embodiment of the present invention also provides a convolution operation device of a convolutional neural network, such as Figure 8 shown, including:

[0098] an acquisition module 801, configured to acquire an input voltage used to characterize a pixel value;

[0099] a first obtaining module 802, configured to obtain the multiplexing times of the input voltage in the convolution sliding window when the input voltage is scanned through the convolution sliding window;

[0100] a grouping module 803, configured to group the input voltages based on the difference in the multiplexing times of the input voltages;

[0101] The second obtaining module 804 is used to extract the input voltage in the same group once, and perform convolution calculation with the convolution kernel respectively to obtain the result corresponding to each group;

[0102] The third obtaining module 805 is configured to obtain the result of the convolution ...

Embodiment 3

[0113] Based on the same inventive concept, the fourth embodiment of the present invention provides an electronic device, such as Figure 9 As shown, it includes a memory 904, a processor 902, and a computer program stored in the memory 904 and running on the processor 902. When the processor 902 executes the program, the above-mentioned convolution operation method of the convolutional neural network is realized. step.

[0114] Among them, in Figure 9 In the bus architecture (represented by bus 900 ), bus 900 may include any number of interconnected buses and bridges, bus 900 will include one or more processors represented by processor 902 and various types of memory represented by memory 904 circuits are linked together. The bus 900 may also link together various other circuits, such as peripherals, voltage regulators and power management circuits, etc., which are well known in the art and therefore will not be described further herein. Bus interface 906 provides an inte...

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 relates to the technical field of artificial intelligence algorithms, in particular to a convolution operation method and device of a convolutional neural network, and the method comprises the steps: obtaining an input voltage used for representing a pixel value; when the input voltage is scanned through a convolution sliding window, the number of multiplexing times of the input voltage in the convolution sliding window is obtained; grouping the input voltages based on different multiplexing times of the input voltages; extracting the input voltage in the same group once, and performing convolution calculation with a convolution kernel to obtain a result corresponding to each group; and on the basis of the result corresponding to each group, a convolution operation result is obtained, so that the convolution operation in the convolutional neural network is realized, and the energy consumption in the convolution operation process is effectively reduced.

Description

technical field [0001] The present invention relates to the technical field of artificial intelligence algorithms, and in particular, to a convolution operation method and device for convolutional neural networks. Background technique [0002] In the process of image processing using Convolutional Neural Network (CNN), a large number of convolution calculation steps are required. [0003] Among them, when convolution calculation is performed on the data in the macro window, the same data needs to be extracted multiple times for convolution calculation, and the memory needs to be read every time the data is extracted. The process of performing the convolution calculation through the digital-to-analog converter also increases the power consumption of the digital-to-analog converter. [0004] Therefore, how to reduce the energy consumption during the convolution operation is an urgent technical problem to be solved. SUMMARY OF THE INVENTION [0005] In view of the above pro...

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): G06N3/04G06F17/15G06N3/063
CPCG06N3/04G06F17/15G06N3/063G06N3/0464G06N3/065
Inventor 张锋霍强
Owner INST OF MICROELECTRONICS CHINESE ACAD OF SCI
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com