Image processing method and device, electronic equipment and storage medium

An image and scale technology, applied in the field of neural networks, can solve problems such as poor speed improvement effect, and achieve the effect of good improvement effect and inference speed improvement.

Pending Publication Date: 2022-07-29
BEIJING DAJIA INTERNET INFORMATION TECH CO LTD
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The present disclosure provides an image processing method, device, electronic equipment, and storage medium, so as to at least solve the problem in the related art that the speed of obtaining corresponding recognition results is poorly improved

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
  • Image processing method and device, electronic equipment and storage medium
  • Image processing method and device, electronic equipment and storage medium
  • Image processing method and device, electronic equipment and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0026] In order to make those skilled in the art better understand the technical solutions of the present disclosure, the technical solutions in the embodiments of the present disclosure will be clearly and completely described below with reference to the accompanying drawings.

[0027] It should be noted that the terms "first", "second" and the like in the description and claims of the present disclosure and the above drawings are used to distinguish similar objects, and are not necessarily used to describe a specific sequence or sequence. It is to be understood that the data so used may be interchanged under appropriate circumstances such that the embodiments of the disclosure described herein can be practiced in sequences other than those illustrated or described herein. The implementations described in the illustrative examples below are not intended to represent all implementations consistent with this disclosure. Rather, they are merely examples of apparatus and methods ...

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 relates to an image processing method and device, electronic equipment and a storage medium. The method comprises the steps that a to-be-recognized image is acquired; a target convolutional neural network is utilized to process the to-be-recognized image, a recognition result corresponding to the to-be-recognized image is obtained, the target convolutional neural network is obtained by cutting a weight channel of each original convolutional layer of the original convolutional neural network according to the optimal cutting proportion, and the recognition result corresponding to the to-be-recognized image is obtained. The optimal cutting proportion is determined from a plurality of candidate cutting proportions, and the optimal cutting proportion is the maximum candidate cutting proportion in all candidate cutting proportions meeting a preset condition in the plurality of candidate cutting proportions; the preset condition is that the difference quantity between the recognition precision of the clipped convolutional neural network corresponding to the candidate clipping proportion and the recognition precision of the original convolutional neural network is smaller than a difference quantity threshold value.

Description

technical field [0001] The present disclosure relates to the field of neural networks, and in particular, to an image processing method, an apparatus, an electronic device, and a storage medium. Background technique [0002] At present, convolutional neural networks are widely used to process corresponding images to be recognized, such as gesture recognition, to obtain corresponding recognition results. The convolutional neural network includes a large number of weights, which causes the convolutional neural network to process the input to the convolutional neural network to be recognized, that is, the inference speed is slow. The channel of the convolutional layer in the neural network is pruned, that is, the number of channels of the convolutional layer is pruned to obtain a target convolutional neural network with faster inference speed than the original convolutional neural network. The network processes the corresponding images to be recognized. [0003] In the relate...

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): G06V40/20G06V40/10G06V10/26G06N3/04G06N3/08
CPCG06N3/082G06N3/045
Inventor 涂小兵马振昌吴浩博
Owner BEIJING DAJIA INTERNET INFORMATION TECH 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