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

Reasoning method and system for dynamic branch selection of deep learning model

A technology of deep learning and reasoning method, applied in the field of artificial intelligence deep learning and reasoning, it can solve the problems of feature redundancy and insufficient reasoning speed of edge computing equipment, and achieve the effect of improving reasoning speed and reducing computational redundancy.

Active Publication Date: 2021-04-23
魔视智能科技(上海)有限公司
View PDF8 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] Aiming at the problem that the feature redundancy of the current deep learning model leads to insufficient reasoning speed in edge computing devices, the present invention provides a reasoning method and system for dynamic branch selection of deep learning models with low redundancy and high speed, which are suitable for edge computing devices

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
  • Reasoning method and system for dynamic branch selection of deep learning model
  • Reasoning method and system for dynamic branch selection of deep learning model
  • Reasoning method and system for dynamic branch selection of deep learning model

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0019] Such as figure 1 as well as figure 2 As shown, the embodiment of this specification provides a reasoning method for dynamic branch selection of a deep learning model, including:

[0020] S101. Construct and train a deep learning model for semantic classification, semantic detection or semantic segmentation of pictures. The deep learning model includes an encoder 11, a branch selector 12, and a plurality of decoding branches 13 corresponding to different branch categories one by one, The deep learning model is trained as:

[0021] A plurality of primary features (intermediate features) are extracted from the input picture by the encoder 11 .

[0022] The branch classes of the primary features are identified and output by the branch selector 12 .

[0023] The decoding branch 13 processes all the primary features through the feature weight group corresponding to the branch category to obtain deep features, recognizes the deep features and outputs the inference result. ...

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 provides a reasoning method and system for dynamic branch selection of a deep learning model. The invention aims at the problem that the deep features of the convolutional neural network in the decoding part are redundant in the reasoning process of the traditional deep learning model. , automatically select the corresponding decoding branch, and each decoding branch is trained through the primary feature input and corresponding output of the corresponding branch category to obtain different feature weight groups, which can focus on the processing of the primary features of the corresponding branch category and the identification of deep features In order to complete more complex classification or representation generation, thereby reducing computing redundancy, improving reasoning speed, and meeting the actual application requirements of edge computing devices.

Description

technical field [0001] The invention belongs to the technical field of artificial intelligence deep learning reasoning, and in particular relates to a reasoning method and system for dynamic branch selection of a deep learning model applied on an edge computing device. Background technique [0002] The current edge computing terminal applications have more and more demands for deep learning vision algorithms, but due to the cost of current edge terminals, the running inference delay of high-precision and complex models cannot meet the practical application, and the accuracy of simple models cannot meet the requirements. This is because For data-intensive and complex tasks, complex convolutional neural network models are usually required to fit the tasks well, and models that are too lightweight will underfit. [0003] In addition, during the inference process of deep learning visual models, there will be redundancy in the deep features generated by the convolutional neural n...

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): G06K9/62G06N3/04G06N3/08G06N5/04
CPCG06N3/08G06N5/04G06N3/045G06F18/24G06F18/214
Inventor 李发成袁施薇张如高虞正华
Owner 魔视智能科技(上海)有限公司
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