Programming-free development method of deep learning application

A deep learning and neural network technology, applied in the field of design software development, can solve problems such as complex and long cycles

Active Publication Date: 2018-07-24
徐磊 +1
View PDF4 Cites 14 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The purpose of the present invention is to provide a programming-free deep learning application development method, which aims to solve the technical problem of complex and long development process

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
  • Programming-free development method of deep learning application
  • Programming-free development method of deep learning application
  • Programming-free development method of deep learning application

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0042] Below in conjunction with specific embodiment and accompanying drawing, the present invention is further elaborated and illustrated:

[0043] Please refer to figure 1 , the development method of the programming-free deep learning application disclosed by the present invention comprises:

[0044] Step 1: Set the neural network type, set the data type of the raw data to be input according to the neural network type, and perform pre-training processing on the raw data to be input according to the set data type to form training data.

[0045] Among them, different neural network types can complete deep learning of different tasks, and need to input data of different data types. Before determining the neural network to be built, one should first set the type of neural network to be built, and Determine the data type of the original data to be input according to the type of neural network to be built. When the acquired raw data is inconsistent with the type of data to be in...

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 programming-free development method of a deep learning application. The method includes the following steps that a neutral network type is set, the data type of to-be-input original data is set according to the neutral network type, the original data is subjected to training preprocessing, and training data is formed; an established neutral network component library and/or an established neutral network template library are/is displayed on a graphical interface, a visual neutral network is erected on the graphical interface through visual operation, and the erecting operation process is displayed on the graphical interface; the neutral network is trained, and training indexes are displayed; neutral network input is given, and an inference result runs and is displayed. According to the software development method, the neutral network is established in the manner that the established neutral network component library and/or the established neutral network template library are/is displayed on the graphical interface, the visual neutral network is erected on the graphical interface through the visual operation, and the erecting operation process is displayed on the graphical interface, and the technical problems that traditionally, software programming is needed, interfaces are complex, and time consumed for debugging is long are avoided.

Description

technical field [0001] The invention relates to the field of design software development, and in particular relates to a development method for programming-free deep learning applications. Background technique [0002] Deep learning technology has developed rapidly, and great progress has been made in image, sound and semantic recognition, and application research in various other fields has also begun to be widely carried out. At present, there are deep learning frameworks such as Tensorflow, Caffe, Keras, and MXNet, and developers can use these tools for deep learning development. Currently, development based on these deep learning frameworks requires developers to be familiar with the frameworks used and related programming languages, and to write their own code to implement. The cycle is long, which is not conducive to rapid iterative development. Contents of the invention [0003] The purpose of the present invention is to provide a programming-free deep learning ap...

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): G06F8/30G06N3/04G06N3/08
CPCG06F8/30G06N3/08G06N3/045
Inventor 徐磊舒良轩
Owner 徐磊
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