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

Convolutional neural network model training method and device and computer readable storage medium

A convolutional neural network and model training technology, which is applied in the field of convolutional neural network model training and can solve problems such as the inability to read and write data at high speed.

Active Publication Date: 2019-09-27
BEIJING BYTEDANCE NETWORK TECH CO LTD
View PDF24 Cites 16 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The technical problem solved by this disclosure is to provide a convolutional neural network model training method to at least partially solve the technical problem in the prior art that cannot achieve high-speed reading and writing of data and can achieve persistence

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
  • Convolutional neural network model training method and device and computer readable storage medium
  • Convolutional neural network model training method and device and computer readable storage medium
  • Convolutional neural network model training method and device and computer readable storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0114] In order to solve the technical problem of low target area recognition accuracy in the prior art, an embodiment of the present disclosure provides a convolutional neural network model training method. Such as Figure 1a As shown, the convolutional neural network model training method mainly includes the following steps S11 to S15. in:

[0115] Step S11: Divide multiple convolutional layers of the convolutional neural network to obtain multiple convolutional stages; wherein the multiple convolutional layers are connected in series.

[0116]Among them, Convolutional Neural Networks (CNN) is a type of feedforward neural network that includes convolution calculations and has a deep structure, mainly including an input layer, multiple convolutional layers, a pooling layer, a fully connected layer, and an output layer. layer. Such as Figure 1b Shown is a structural example of a convolutional neural network, including three convolutional layers, namely convolutional layer ...

Embodiment 2

[0152] In order to solve the technical problem of low recognition accuracy of the target area in the prior art, an embodiment of the present disclosure further provides a method for training a convolutional neural network model. The convolutional neural network model training method mainly includes: obtaining a negative training sample set; wherein the negative training sample set is composed of a plurality of background areas marked with non-target areas and a plurality of foreground areas marked with target areas; according to the negative training The sample set is trained using the convolutional neural network model training method described in the first embodiment above to obtain a negative sample convolutional neural network model. Such as figure 2 shown, including:

[0153] Step S21: Divide multiple convolutional layers of the convolutional neural network to obtain multiple convolutional stages; wherein the multiple convolutional layers are connected in series.

[01...

Embodiment 3

[0182] Embodiments of the present disclosure also provide a target area identification method, such as image 3 shown, including:

[0183] S31: Obtain an image to be recognized.

[0184] Among them, the image to be recognized can be obtained in real time through the camera. Or obtain a pre-stored image to be recognized locally.

[0185] S32: Input the image to be recognized into the positive sample convolutional neural network model for recognition to obtain the target area.

[0186] Wherein, the positive sample convolutional neural network model is trained by using the convolutional neural network model training method described in the first embodiment above, and the specific training process is referred to the first embodiment above.

[0187] In an optional embodiment, the method also includes:

[0188] Step S33: Input the target region into the negative sample convolutional neural network model for classification.

[0189] Wherein, the negative sample convolutional neu...

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 convolutional neural network model training method and device, an electronic device and a computer readable storage medium. The method comprises the following steps of dividing the convolutional neural network into a plurality of convolutional stages, wherein the convolution stage is composed of at least one convolution layer; determining the parameters of the convolutional neural network; inputting a positive training sample set into the convolutional neural network for training to obtain the feature images of a plurality of convolutional stages corresponding to each sample image; for each sample image, fusing the feature images of a plurality of corresponding convolution stages; obtaining a positive sample convolutional neural network model according to the fused feature image of each sample image, wherein the positive sample convolutional neural network model is used for identifying a target area. According to the embodiment of the invention, the feature images of the plurality of convolution stages of the convolutional neural network are fused during the training process of the positive sample convolutional neural network model, so that the correct recognition rate of the positive sample convolutional neural network model to the target area can be improved.

Description

technical field [0001] The present disclosure relates to the technical field of convolutional neural network model training, in particular to a convolutional neural network model training method, device and computer-readable storage medium. Background technique [0002] Many of the captured video images contain cars, and the images containing cars generally include license plates. Since the license plate involves privacy, it is necessary to process the license plate in the video image or use other images to cover the license plate. When processing the image containing the license plate, it is the key to recognize the license plate area in the image. [0003] In the prior art, a straight network is usually used to train the model, and the trained model is used to recognize the license plate area in the image. In this way, the edge of the finally recognized license plate area is very blurred, and the outline of the license plate cannot be accurately located. In addition, for ...

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
CPCG06N3/08G06N3/045
Inventor 朱延东王长虎
Owner BEIJING BYTEDANCE NETWORK 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