Convolutional neural network generation method and device

A convolutional neural network and convolution kernel technology, which is applied in neural learning methods, biological neural network models, neural architectures, etc., can solve problems such as low computing efficiency

Active Publication Date: 2019-07-26
HANGZHOU HIKVISION DIGITAL TECH
View PDF8 Cites 20 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0007] Embodiments of the present invention provide a method and device for generating a convolutional neural network, which ca

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 generation method and device
  • Convolutional neural network generation method and device
  • Convolutional neural network generation method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0256] In order to make the object, technical solution and advantages of the present invention clearer, the present invention will be further described in detail below in conjunction with the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, rather than all embodiments . Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without making creative efforts belong to the protection scope of the present invention.

[0257] An embodiment of the present invention provides a method for generating a convolutional neural network, which can be executed by a device for generating a convolutional neural network. The method for generating a convolutional neural network is mainly used for further adjustment after training the initial convolutional neural network. The target convolutional neural network is obtained. The generation method of the convolutional neur...

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 a convolutional neural network generation method and device, and belongs to the technical field of video coding and decoding. The method comprises the following steps: training an initial convolutional neural network to obtain a trained convolutional neural network; determining a to-be-processed convolutional neural network based on the trained convolutional neural network; and performing tensor decomposition operation on at least one target convolutional layer in the to-be-processed convolutional neural network to obtain a target convolutional neural network. According to the invention, the problem that the operation efficiency is low when the current convolutional neural network performs convolution operation can be solved.

Description

technical field [0001] The present invention relates to the technical field of video encoding and decoding, in particular to a method and device for generating a convolutional neural network. Background technique [0002] During processing in digital image systems, filtering, data rounding, quantization, or other manipulations can shift the intensity of pixel values, causing visual disturbances or artifacts. In order to avoid or mitigate the potential problems mentioned above, image de-distortion filters can be designed to post-process the image to restore the pixel intensity shift and alleviate the visual loss. [0003] Traditional image de-distortion filters usually generalize the characteristics of distorted images artificially, artificially design filter structures, and configure filter coefficients based on experiments and experience, such as deblocking filters used in image / video coding standards ( English: Deblocking Filter; Abbreviation: DBK), etc.; there is also a ...

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
CPCG06N3/08H04N19/61G06N3/045G06F18/23211
Inventor 姚佳宝
Owner HANGZHOU HIKVISION DIGITAL TECH
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