Parallel reasoning method and system for neural network encoding and decoding tools

A technology of neural network and reasoning method, which is applied in the field of parallel reasoning method and system for neural network encoding and decoding tools, which can solve the problems of increasing complexity and large amount of calculation of neural network models, and achieve the effect of reducing the complexity of encoding and decoding

Active Publication Date: 2021-07-20
PEKING UNIV
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, on the one hand, the neural network model usually has a large amount of calculation, and directly embedding it in the video codec will cause the complexity to double. network reasoning

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
  • Parallel reasoning method and system for neural network encoding and decoding tools
  • Parallel reasoning method and system for neural network encoding and decoding tools
  • Parallel reasoning method and system for neural network encoding and decoding tools

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0041] In order to understand the characteristics and technical content of the embodiments of the present disclosure in more detail, the implementation of the embodiments of the present disclosure will be described in detail below in conjunction with the accompanying drawings. The attached drawings are only for reference and description, and are not intended to limit the embodiments of the present disclosure. In the following technical description, for purposes of explanation, numerous details are set forth in order to provide a thorough understanding of the disclosed embodiments. However, one or more embodiments may be practiced without these details. In other instances, well-known structures and devices may be shown simplified in order to simplify the drawings.

[0042] figure 1 It is a schematic flowchart of a parallel reasoning method oriented to a neural network encoding and decoding tool according to an exemplary embodiment;

[0043] In some optional embodiments, a par...

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 parallel reasoning method oriented to a neural network encoding and decoding tool, comprising: extending the boundary of an image to be processed to obtain an image with a complete boundary; dividing the image with a complete boundary into images of the same size according to a raster scanning sequence block; the image blocks of the same size are organized into several tensors, and the several tensors are simultaneously sent to the neural network as a group of tensors for forward propagation processing, wherein, according to the neural network coding tool and HW memory size sets the batch size value for said tensors. Through the above method, the video memory of the neural network inference can be effectively reduced, and the encoding and decoding complexity of the neural network video encoding tool can be reduced.

Description

technical field [0001] The invention relates to the technical field of digital signal processing, in particular to a parallel reasoning method and system for neural network encoding and decoding tools. Background technique [0002] Deep learning has continuously made breakthroughs in traditional computer vision tasks. Loop filtering, as the underlying computer vision task, is very suitable for deep learning processing. The neural network has a strong nonlinear fitting ability, which is suitable for blocking effects and vibrations generated after video encoding. Bell effect, etc. have a good inhibitory effect. [0003] In the prior art, there are many neural network loop filtering works for mainstream video coding standards such as AVS3, VVC, and HEVC. However, on the one hand, the neural network model usually has a large amount of calculation, and directly embedding it in the video codec will cause the complexity to double. network reasoning. Contents of the invention ...

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 Patents(China)
IPC IPC(8): H04N19/436H04N19/176H04N19/147H04N19/14H04N19/70H04N19/82G06N3/04G06N3/08
CPCG06N3/04G06N3/08H04N19/14H04N19/147H04N19/176H04N19/436H04N19/70H04N19/82
Inventor 马思伟林凯贾川民王苫社赵政辉
Owner PEKING 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