Unlock instant, AI-driven research and patent intelligence for your innovation.

Deep learning method and device for image recognition, client and server

A technology of deep learning and image recognition, which is applied in the field of image recognition, can solve the problems of slow training speed of large networks, and achieve the effect of solving slow training speed, reducing training time, and saving parameters

Pending Publication Date: 2018-11-06
BEIJING MOSHANGHUA TECH CO LTD
View PDF6 Cites 15 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] The main purpose of this application is to provide a deep learning method for image recognition to solve the problem of slow training in large networks

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 method and device for image recognition, client and server
  • Deep learning method and device for image recognition, client and server
  • Deep learning method and device for image recognition, client and server

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0028] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiment of the application will be clearly and completely described below in conjunction with the accompanying drawings in the embodiment of the application. Obviously, the described embodiment is only It is an embodiment of a part of the application, but not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by persons of ordinary skill in the art without creative efforts shall fall within the scope of protection of this application.

[0029] It should be noted that the terms "first" and "second" in the description and claims of the present application and the above drawings are used to distinguish similar objects, but not necessarily used to describe a specific sequence or sequence. It should be understood that the data so used may be interchanged under appropriate circumstances for...

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 deep learning method and device for image recognition, a client and a server. The method comprises the following steps of: inputting a to-be-recognized picture in an input layer; establishing a plurality of group convolution modules; outputting a feature map of the to-be-recognized picture through the plurality of group convolution modules; and outputting a picture recognition result on an output layer according to the feature map. The group convolution modules at least comprise a depth-separable convolution unit and a convolution unit preset with a convolution kernelsize. According to the method, the technical problem that the big networks are relatively low in training speed is solved. Moreover, the invention discloses a brand-new network structure, so that existing deep learning method can be directly replaced, thereby realizing end-to-end training, shortening the training time and saving the labor cost.

Description

technical field [0001] This application relates to the field of image recognition, specifically, a deep learning method and device, client, and server for image recognition. The new network structure proposed by this application can directly replace the existing deep learning method. Background technique [0002] With the rapid development of computer vision, great progress has been made in the fields of face recognition and object detection, especially in the accuracy rate. The emergence of many deep networks has accelerated face recognition. Progress in fields such as object detection has made great leaps in many public datasets for computer vision. [0003] For example, the face recognition LFW data set has an accuracy rate of 99.83%, far exceeding the accuracy of human eyes. For example, the PascalVOC data set has an accuracy rate of nearly 90% for object detection, and the COCO data set has an object detection rate of more than 50%. Accuracy, it can be seen that many m...

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): G06K9/62
CPCG06F18/217G06F18/241
Inventor 张默
Owner BEIJING MOSHANGHUA TECH CO LTD