Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

Deep learning model training method, device and equipment and storage medium

A deep learning and training method technology, applied in the field of deep learning, can solve the problems of large number of deep learning model samples, inability to provide deep learning models, poor training effect, etc., to improve anti-noise and anti-displacement capabilities, and improve training speed , Improve the effect of training effect

Active Publication Date: 2019-08-30
SHENZHEN UNIV
View PDF9 Cites 9 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The object of the present invention is to provide a training method, device, equipment and storage medium of a deep learning model, aiming at solving the problem that the prior art cannot provide an effective The training method of the deep learning model leads to the problems of large number of samples for training the deep learning model, slow model training, and poor training effect

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 model training method, device and equipment and storage medium
  • Deep learning model training method, device and equipment and storage medium
  • Deep learning model training method, device and equipment and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0025] figure 1 The implementation process of the deep learning model training method provided by Embodiment 1 of the present invention is shown. For the convenience of description, only the parts related to the embodiment of the present invention are shown, and the details are as follows:

[0026] In step S101, a deep learning model is constructed according to the received training image set, wherein the deep learning model includes a hidden layer and a fully connected layer, and the hidden layer consists of several feature extraction layers and a lower layer corresponding to the feature extraction layer The feature extraction layer is composed of several feature extraction surfaces, and the downsampling layer is composed of several downsampling surfaces.

[0027] Embodiments of the present invention are applicable to computing devices, such as personal computers, servers, and the like. In the embodiment of the present invention, according to the complexity of the training i...

Embodiment 2

[0047] image 3 The structure of the training device for the deep learning model provided by Embodiment 2 of the present invention is shown. For the convenience of description, only the parts related to the embodiment of the present invention are shown, including:

[0048] The model construction unit 31 is used to construct a deep learning model according to the training image set received, wherein the deep learning model includes a hidden layer and a fully connected layer, and the hidden layer is composed of several feature extraction layers and corresponding to the feature extraction layer. The downsampling layer is composed of the feature extraction layer consisting of several feature extraction surfaces, and the downsampling layer is composed of several downsampling surfaces.

[0049] Embodiments of the present invention are applicable to computing devices, such as personal computers, servers, and the like. In the embodiment of the present invention, according to the comp...

Embodiment 3

[0077] Figure 5 The structure of the computing device provided by the third embodiment of the present invention is shown, and for the convenience of description, only the parts related to the embodiment of the present invention are shown.

[0078] The computing device 5 of the embodiment of the present invention includes a processor 50 , a memory 51 and a computer program 52 stored in the memory 51 and operable on the processor 50 . When the processor 50 executes the computer program 52, the steps in the embodiment of the training method of the above-mentioned deep learning model are realized, for example figure 1 Steps S101 to S104 are shown. Alternatively, when the processor 50 executes the computer program 52, the functions of the units in the above-mentioned device embodiments are realized, for example image 3 Function of units 31 to 34 shown.

[0079] In the embodiment of the present invention, according to the received training image set, the preset feature extracti...

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 method is applicable to the technical field of deep learning, and provides a deep learning model training method, device and equipment and a storage medium. The method comprises the following steps: according to the received training image set, using a preset feature extraction algorithm and a pre-constructed untrained deep learning model to extractcorresponding target features, performing local training on a hidden layer of the deep learning model through a target feature set formed by the extracted target features; after local training is completed, selecting a target image set from thetraining image set; performing classification training on the full connection layer of the deep learning model. The deep learning model is trained through the deep learning model, so that the number of samples for training the deep learning model is reduced, the trained deep learning model better conforms to the human brain visual cortex characteristics, the noise resistance and the displacement resistance of the deep learning model are improved, and the training speed and the training effect of the deep learning model are improved.

Description

technical field [0001] The invention belongs to the technical field of deep learning, and in particular relates to a training method, device, equipment and storage medium of a deep learning model. Background technique [0002] Existing deep learning models map a large amount of data into a high-dimensional space through continuous nonlinear transformation by building a deep network to obtain abstract feature vectors, and then complete the task of classifying or regressing data. For deep networks, depth and data volume are the basis for correct expression learning. Generally, the deeper the network, the stronger its nonlinear expression ability, and the larger the data volume, it can fit the data more effectively, which is beneficial to Networks perform classification or regression tasks in high-dimensional spaces. Recently, the accuracy of image recognition on the dataset ImageNet using a deep network structure of more than 150 layers can exceed the accuracy of human eye re...

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): G06K9/62G06N3/06
CPCG06N3/061G06F18/2321G06F18/214
Inventor 石大明刘露
Owner SHENZHEN UNIV
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
Eureka Blog
Learn More
PatSnap group products