Face recognition neural network adjustment method and device

A neural network and face recognition technology, applied in the field of deep learning, can solve problems such as computing power and power consumption restricting the promotion and deployment of face recognition technology, and achieve the effect of avoiding convergence and oscillation problems and ensuring accuracy

Active Publication Date: 2022-06-28
XILINX TECH BEIJING LTD
View PDF8 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] However, the limitations of computing power and power consumption in actual application scenarios seriously restrict the promotion and deployment of face recognition technology.

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
  • Face recognition neural network adjustment method and device
  • Face recognition neural network adjustment method and device
  • Face recognition neural network adjustment method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0034] Preferred embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While preferred embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be embodied in various forms and should not be limited by the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.

[0035] The solution of this application is applicable to various artificial neural networks, including deep neural network (DNN), recurrent neural network (RNN) and convolutional neural network (CNN). The following takes CNN as an example for some background explanation.

[0036] Basic concepts of CNN

[0037]CNNs achieve state-of-the-art performance on a wide range of vision-related tasks. To help understand the CNN-based classification a...

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

A method and device for tuning and deploying neural networks for face recognition is proposed. The face recognition neural network includes at least a plurality of convolutional layers and at least one fully connected layer, and the last fully connected layer is a classifier for classification, and the method includes: obtaining a neural network model to be trained; using fixed-point quantization to training the neural network model to obtain a trained fixed-point quantized neural network model, wherein the last fully connected layer maintains a floating point during training; and outputting the A trained fixed-point quantized neural network model. Therefore, taking advantage of the particularity of the face recognition network, by keeping the fixed point of the classifier layer that has a greater impact on the overall accuracy of the network during the training phase and not including the classifier layer in the network, it is possible to ensure that the trained fixed point The neural network has high precision while avoiding additional computing power requirements during network deployment.

Description

technical field [0001] The present invention relates to deep learning, and in particular, to fixed-point quantization of a face recognition neural network. Background technique [0002] At the beginning of the birth of machine learning, face recognition was one of the most basic application areas. In recent years, with the continuous development and progress of deep learning, the accuracy of face recognition has also increased rapidly, and even surpassed the human level on multiple evaluation sets. Therefore, face recognition has also begun to be applied in life scenarios such as smartphones and smart surveillance cameras. [0003] However, the limitation of computing power and power consumption in practical application scenarios seriously restricts the promotion and deployment of face recognition technology. Given the fact that existing neural network parameters have a lot of redundancy, it is possible to significantly reduce resource usage by localizing neural networks. ...

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 Patents(China)
IPC IPC(8): G06V40/16G06V10/764G06V10/774G06V10/82G06K9/62
CPCG06V40/172G06F18/24G06F18/214
Inventor 高梓桁
Owner XILINX TECH BEIJING 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