Unlock instant, AI-driven research and patent intelligence for your innovation.

Neural network training method and device and computer readable medium

A neural network training, neural network technology, applied in the fields of equipment and computer-readable media, neural network training methods, can solve problems such as poor image performance, and achieve the effect of improving recognition performance

Pending Publication Date: 2021-10-22
上海眼控科技股份有限公司
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] One purpose of this application is to provide a neural network training scheme to solve the problem of poor performance in identifying images with a certain rotation angle in the prior art

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
  • Neural network training method and device and computer readable medium
  • Neural network training method and device and computer readable medium
  • Neural network training method and device and computer readable medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0046]In order to make the purposes, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments It is a part of the embodiments of this 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 creative efforts fall within the protection scope of this application.

[0047] In a typical configuration of the present application, the terminal and the equipment serving the network include one or more processors (CPUs), input / output interfaces, network interfaces and memory.

[0048] Memory may include non-permanent storage in computer readable media, in the form of random access memory (RAM) and / or nonvolatile memory such as ...

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 neural network training scheme, and the scheme carries out fractal processing of a training picture, obtains an input picture of the training picture comprising multiple rotation angles, enables the extracted image features to comprise the content information of the picture, also comprises the directivity information, a neural network obtained by training can identify more stereoscopic image features, including content information and directivity information, so that the identification performance of the neural network can be improved, and the neural network can better identify a picture with a certain rotation angle.

Description

technical field [0001] The present application relates to the field of information technology, and in particular to a neural network training method, device and computer-readable medium. Background technique [0002] Convolutional Neural Networks (CNN, Convolutional Neural Networks) have achieved great achievements and widespread applications in image classification and image detection since 2012. [0003] The power of the convolutional neural network is that its multi-layer structure can automatically learn features, and can learn features at multiple levels: Among them, the shallower convolutional layer has a smaller perceptual domain, and learns the features of some parts of the area. The deeper convolutional layer has a larger perceptual field and can learn more abstract features. These general features are less sensitive to object size, position and orientation, thus contributing to the improvement of recognition performance. Due to the mechanism of convolution, for t...

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
IPC IPC(8): G06N3/04G06N3/08
CPCG06N3/08G06N3/084G06N3/045
Inventor 姚广苏仲岳闫正
Owner 上海眼控科技股份有限公司