Supercharge Your Innovation With Domain-Expert AI Agents!

Conversion method, device, electronic device and storage medium of deep learning model

A technology of deep learning and conversion methods, which is applied in the fields of devices, electronic equipment and storage media, and deep learning model conversion methods. It can solve problems such as unsatisfactory conversion effects of model conversion tools and poor model conversion experience, and improve readability. , reduce the number, reduce the effect of the amount of code

Active Publication Date: 2022-05-03
BEIJING BAIDU NETCOM SCI & TECH CO LTD
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the conversion effect of the model conversion tool in the related art is not ideal, and the user's model conversion experience is poor

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
  • Conversion method, device, electronic device and storage medium of deep learning model
  • Conversion method, device, electronic device and storage medium of deep learning model
  • Conversion method, device, electronic device and storage medium of deep learning model

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0021] Exemplary embodiments of the present application are described below in conjunction with the accompanying drawings, which include various details of the embodiments of the present application to facilitate understanding, and they should be regarded as exemplary only. Accordingly, those of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope and spirit of the application. Also, descriptions of well-known functions and constructions are omitted in the following description for clarity and conciseness.

[0022] In the related art, when the deep learning framework of the model needs to be converted, the user can use the model conversion tool to perform the conversion. However, in related technologies, the converted model provided by the conversion tool has a large amount of code and poor readability of the code, requiring the user to manually modify the code of the co...

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 application discloses a deep learning model conversion method, device, electronic equipment, and storage medium, and relates to artificial intelligence technology fields such as deep learning. The specific implementation plan is: convert the original deep learning framework of the deep learning model to obtain the target deep learning framework of the deep learning model, and based on the target deep learning framework, determine the model graph structure of the deep learning model, and obtain the model graph structure from the model graph structure Among the operation nodes, determine the corresponding frequent itemset set, and combine some nodes among the N operation nodes to merge them into modules, and generate an optimized model graph structure according to the modules and unmerged operation nodes. Transcode the optimized model graph structure to get code results. In this way, the operation nodes in the model graph structure are modularized, and the number of nodes in the optimized model graph structure is reduced, so as to optimize the code and improve the readability of the converted code.

Description

technical field [0001] The present application relates to the field of computer technology, specifically to the field of artificial intelligence technology such as deep learning, and in particular to the conversion method, device, electronic equipment and storage medium of the deep learning model. Background technique [0002] With the rapid development of the field of artificial intelligence, many excellent deep learning frameworks have emerged. In some scenarios, when a user needs to transfer a model built by a deep learning framework to another familiar deep learning framework, the user can use the model conversion tool to convert the model framework. However, the conversion effect of the model conversion tool in the related art is not ideal, and the user's model conversion experience is poor. Contents of the invention [0003] The present application provides a conversion method, device, electronic equipment and storage medium for deep learning models. [0004] Accor...

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): G06N20/00
CPCG06N3/082Y02D10/00
Inventor 孙妍芳蒋佳军
Owner BEIJING BAIDU NETCOM SCI & TECH CO LTD
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

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

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com