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

Neural network training method and device, electronic equipment and storage medium

A neural network and training method technology, applied in the fields of electronic equipment and storage media, neural network training methods and devices, can solve problems such as failure to achieve deployment environment accuracy, non-existence, etc.

Inactive Publication Date: 2019-09-06
SHANGHAI SENSETIME INTELLIGENT TECH CO LTD
View PDF1 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, when a low-precision model is deployed on an electronic device, there is a problem that the accuracy of the deployment environment cannot be achieved. For this, there is no effective solution in the related 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, electronic equipment and storage medium
  • Neural network training method and device, electronic equipment and storage medium
  • Neural network training method and device, electronic equipment and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0122] Various exemplary embodiments, features, and aspects of the present disclosure will be described in detail below with reference to the accompanying drawings. The same reference numbers in the figures indicate functionally identical or similar elements. While various aspects of the embodiments are shown in drawings, the drawings are not necessarily drawn to scale unless specifically indicated.

[0123] The word "exemplary" is used exclusively herein to mean "serving as an example, embodiment, or illustration." Any embodiment described herein as "exemplary" is not necessarily to be construed as superior or better than other embodiments.

[0124] The term "and / or" in this article is just an association relationship describing associated objects, which means that there can be three relationships, for example, A and / or B can mean: A exists alone, A and B exist simultaneously, and there exists alone B these three situations. In addition, the term "at least one" herein mean...

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 relates to a neural network training method and device, electronic equipment and a storage medium. The method comprises the following steps: according to a bit width determined by a deployment environment of a neural network based on a fixed-point number, mapping each parameter of the trained neural network based on a floating-point number into the fixed-point number to obtain a first neural network, each parameter of the first neural network being the fixed-point number; and training the first neural network by adopting a sample image set to obtain the neural network based on the fixed-point number. By adopting the neural network based on the fixed-point number, which is obtained through mapping from the floating-point number to the fixed-point number and training, the precision of the deployment environment of the deployed electronic equipment can be met.

Description

technical field [0001] The present disclosure relates to the technical field of computer vision, and in particular to a neural network training method and device, electronic equipment and a storage medium. Background technique [0002] In related technologies, in the application scenario of image processing, a deep learning model can be used for detection. The deep learning model generally uses floating-point numbers for storage and calculation. The deep learning model based on floating-point numbers has high storage and calculation overhead. In order to reduce storage and computing overhead, low-precision models can be used. However, when a low-precision model is deployed on an electronic device, there is a problem that the accuracy of the deployment environment cannot be achieved. For this, there is no effective solution in the related art. Contents of the invention [0003] The disclosure proposes a technical solution for neural network training. [0004] According to...

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): G06N3/08
CPCG06N3/08
Inventor 李润东王岩秦红伟
Owner SHANGHAI SENSETIME INTELLIGENT 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