Model conversion method and device

A model and network model technology, applied in the field of artificial intelligence, can solve the problem of low model transformation efficiency

Active Publication Date: 2021-05-18
HANGZHOU HIKVISION DIGITAL TECH
View PDF8 Cites 12 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

There may be operators defined by users in the original network model, that is, private operators, which usually require users to manually convert the above-mentioned private operators, resulting in low model conversion efficiency

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
  • Model conversion method and device
  • Model conversion method and device
  • Model conversion method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0104] The following will clearly and completely describe the technical solutions in the embodiments of the application with reference to the drawings in the embodiments of the application. Apparently, the described embodiments are only some of the embodiments of the application, not all of them. Based on the embodiments in this application, all other embodiments obtained by persons of ordinary skill in the art without making creative efforts belong to the scope of protection of this application.

[0105] In order to improve the model conversion efficiency, the embodiments of the present application provide a model conversion method and device, which will be described in detail below.

[0106] see figure 1 , figure 1 It is a schematic flowchart of a model conversion method provided in the embodiment of this application. The method can be applied to electronic devices such as electronic computers, mobile phones, and tablet computers. Such as figure 1 As shown, the model con...

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 embodiment of the invention provides a model conversion method and device, and relates to the technical field of artificial intelligence, and the method comprises the steps: obtaining an original network model generated based on an original deep learning framework; identifying a first type of operators in the original network model; extracting an algorithm logic of the first type of operators, generating a target logic code supported by a target platform according to the algorithm logic, and obtaining a parameter list of the first type of operators, wherein the target platform is a reasoning platform used for deploying a converted original network model; according to the data processing flow direction of the original network model, converting all operators of the original network model in sequence, conversion of the original network model is achieved, and under the condition that an operator to be converted is a first type of operator, converting parameters in a parameter list of the operator according to a parameter format supported by a target framework. By applying the scheme, the model conversion efficiency can be improved.

Description

technical field [0001] The present application relates to the technical field of artificial intelligence, in particular to a model conversion method and device. Background technique [0002] The network model is usually generated based on the deep learning framework. For the convenience of expression, the above network model is called the original network model, and then the original network model is deployed on the inference platform to run. Since the deep learning framework connected to the inference platform may be different from the deep learning framework used to generate the original network model, the original network model needs to be transformed so that the transformed network model can run on the above inference platform. [0003] A network model generally includes multiple operators. When converting the original network model, each operator in the original network model needs to be converted. There may be operators defined by users in the original network model, ...

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 Applications(China)
IPC IPC(8): G06N3/08G06N3/02G06N3/063
CPCG06N3/08G06N3/063G06N3/02
Inventor 孟泽民冷明鑫袁浩然高其涛陈辉
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