Training method of convolutional neural network, and image processing method and apparatus

A convolutional neural network, training image technology, applied in the field of deep learning, can solve problems such as increasing the network running time, and achieve the effect of reducing the running time

Active Publication Date: 2018-07-20
BEIJING SENSETIME TECH DEV CO LTD
View PDF2 Cites 19 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, deepening or widening the network will inevitably increase the running time of the network during training and testing

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
  • Training method of convolutional neural network, and image processing method and apparatus
  • Training method of convolutional neural network, and image processing method and apparatus
  • Training method of convolutional neural network, and image processing method and apparatus

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0076] In order to understand the characteristics and technical contents of the embodiments of the present invention in more detail, the implementation of the embodiments of the present invention will be described in detail below in conjunction with the accompanying drawings. The attached drawings are only for reference and description, and are not intended to limit the embodiments of the present invention.

[0077] At the same time, it should be understood that, for the convenience of description, the sizes of the various parts shown in the drawings are not drawn according to the actual proportional relationship.

[0078] The following description of at least one exemplary embodiment is merely illustrative in nature and in no way serves as any limitation of the application, its application or uses.

[0079] Techniques, methods and devices known to those of ordinary skill in the relevant art may not be discussed in detail, but where appropriate, such techniques, methods and dev...

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 training method of a convolutional neural network, an image processing method and apparatus, a computer storage medium, a computer readable storage medium and a computer program. The training method of the convolutional neural network includes: deleting at least a non-linear correction layer arranged behind a linear structural layer in a first convolutional neural networkto obtain a second convolutional neural network; and performing supervision training on the second convolutional neural network based on a training image and annotated information of the training image. The image processing method comprises: merging at least a serial branch and / or at least a parallel branch in the second convolutional neural network after training completion to obtain a third convolutional neural network, wherein the at least one non-linear correction layer arranged behind a linear structural layer in the second convolutional neural network is deleted; inputting the image tothe third convolutional neural network; and processing the image through the third convolutional neural network to obtain a processing result of the image.

Description

technical field [0001] The present invention relates to the technical field of deep learning, in particular to a convolutional neural network training method, image processing method, device, computer equipment, computer-readable storage medium, and computer program. Background technique [0002] With the development of deep convolutional neural networks, deeper or wider network structures are constantly refreshing the accuracy of various computer vision datasets. However, deepening or widening the network will inevitably increase the running time of the network during training and testing. In recent years, in order to be able to run deep convolutional neural networks on platforms with low power consumption and low computing resources, more and more researchers have begun to pay attention to networks that are lightweight and require less time for training and testing. [0003] How to design some lightweight convolutional neural networks to achieve shorter training time or s...

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): G06N3/04G06K9/62
CPCG06N3/045G06F18/29
Inventor 程光亮石建萍
Owner BEIJING SENSETIME TECH DEV CO 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