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

Deployment method and device for operators in deep learning framework and electronic equipment

A deep learning and device deployment technology, applied in machine learning, software deployment, computing, etc., can solve problems such as high cost, low efficiency, and lack of flexibility

Active Publication Date: 2021-06-22
BEIJING BAIDU NETCOM SCI & TECH CO LTD
View PDF17 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In this way, it will inevitably lead to extremely high cost for users, strong impact on other three-party libraries (such as library pybind11), lack of flexibility, and low 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
  • Deployment method and device for operators in deep learning framework and electronic equipment
  • Deployment method and device for operators in deep learning framework and electronic equipment
  • Deployment method and device for operators in deep learning framework and electronic equipment

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0031] The exemplary embodiments of the present application will be described below in connection with the accompanying drawings, including various details of the present application embodiments to help understand, and they should be considered simply exemplary. Accordingly, it will be appreciated by those skilled in the art that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of the present application. Similarly, a description of the well-known functions and structures is omitted in order to clear and concise, the following description is omitted.

[0032] The technical fields involved in the present application are briefly described below:

[0033] Data Processing, including processing, storage, retrieval, processing, variation, and transmission of data, aimed to extract and derive and derive from certain specific users in data. Speak valuable, meaningful data.

[0034] AI (Artificial Intelligence, ar...

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 deployment method and device for operators in a deep learning framework and electronic equipment, and relates to the technical field of artificial intelligence such as deep learning. The scheme comprises the following steps of acquiring source files of operators; compiling source files of the operators to form a dynamic link library of the operators; generating an interface file converted by the dynamic link library of the operators; generating an installable library file according to the dynamic link library and the interface file; installing the installable library file to the target programming language library so that all the operator installation processes can be completely hidden, the learning cost of a user is greatly reduced, and meanwhile, the efficiency, flexibility and reliability in the operator deployment process in a deep learning framework are improved.

Description

Technical field [0001] The embodiments of the present application generally relate to the field of data processing, and more particularly to the artificial intelligence technology of deep learning. Background technique [0002] At present, the mainstream depth learning framework contains rich tensor calculation processing units, collectively referred to as operators, rich operators libraries provide a powerful infrastructure for fast-building depth learning models, but the operator library in the depth learning framework is generally Unable to be complete, especially in the frontier academic research field, often present the current operator library unable to meet the specific logic calculation operations. Therefore, the major depth learning frameworks provide users with a mechanism for custom operators. [0003] The custom operator is mainly implemented by the C ++ language (The C ++ Programming Language / C Plus Plus), and the source code is required separately, link into a dyn...

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): G06F8/41
CPCG06F8/447G06F9/44521G06F8/61G06F8/36G06N20/00G06N3/105G06N3/04G06F8/31G06F8/54G06F8/41G06N3/10
Inventor 张留杰蓝翔郑辉煌刘红雨周威马艳军于佃海王海峰
Owner BEIJING BAIDU NETCOM SCI & TECH CO LTD
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