Deep learning framework conversion method and system, storage medium and equipment

A deep learning and framework technology, applied in the field of artificial intelligence, can solve problems such as inconvenient conversion

Inactive Publication Date: 2021-09-10
INSPUR SUZHOU INTELLIGENT TECH CO LTD
View PDF4 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] In view of this, the object of the present invention is to propose a deep learning framework conversion method, system, storage medium and equipment to solve the inconvenience of converting the deep learning framework used by the deep learning model in the inference engine in the prior art The problem

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
  • Deep learning framework conversion method and system, storage medium and equipment
  • Deep learning framework conversion method and system, storage medium and equipment
  • Deep learning framework conversion method and system, storage medium and equipment

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0023] In order to make the object, technical solution and advantages of the present invention clearer, the embodiments of the present invention will be further described in detail below in conjunction with specific embodiments and with reference to the accompanying drawings.

[0024]It should be noted that all expressions using "first" and "second" in the embodiments of the present invention are used to distinguish two entities with the same name or different parameters. It can be seen that "first" and "second" " is only for the convenience of expression, and should not be understood as limiting the embodiment of the present invention. Furthermore, the terms "comprising" and "having", as well as any variations thereof, are intended to cover a non-exclusive inclusion, for example, of a process, method, system, product or other steps or elements inherent in a process, method, system, product, or device comprising a series of steps or elements.

[0025] Based on the above purpos...

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 deep learning framework conversion method and system, a storage medium and equipment. The method comprises the following steps: acquiring an operator which does not support conversion of a deep learning model in a native framework; operating a deep learning model in the native framework to obtain an input size of input data and an output size of output data of the operator which does not support conversion, and comparing and determining an algorithm logic of the operator which does not support conversion through a preset rule; filling the plug-in with a preset rule and a core function used for executing the algorithm logic; and replacing the operator which does not support conversion with the filled plug-in to convert the inference engine from the native framework to the target framework. According to the invention, rapid conversion of the deep learning framework in the inference engine can be realized.

Description

technical field [0001] The present invention relates to the technical field of artificial intelligence, in particular to a deep learning framework conversion method, system, storage medium and equipment. Background technique [0002] Deep learning technology is currently the main algorithm for the application of AI (artificial intelligence) in various industries. This technology includes a series of model algorithms, such as CNN architecture models (ResNet, DenseNet), transformer architecture models (Bert, gpt), etc. When solving problems in practical application scenarios, such as judging the category of objects in the image, speech-to-text, and emotional tendencies of the text, it needs to go through two steps: training, reasoning and deployment. A current natural process is to train the model on a deep learning framework to achieve the available accuracy, and then use the engine framework for inference; for example, use a deep learning framework such as TensorFlow, Pytor...

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): G06N20/00G06N5/04
CPCG06N20/00G06N5/04
Inventor 王鹏飞赵冰刘鑫
Owner INSPUR SUZHOU INTELLIGENT TECH CO LTD
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