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

Network training method, device, computing device and computer storage medium

A network training and network technology, applied in the field of image processing, can solve the problems of large amount of calculation, long training time, low efficiency of image stylization processing, etc., and achieve the effect of improving efficiency

Active Publication Date: 2021-05-18
BEIJING QIHOO TECH CO LTD
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In the training process of the image conversion network, tens of thousands of iterative operations cause a huge amount of calculation, which will take a long time for training, resulting in low efficiency of image stylization processing

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
  • Network training method, device, computing device and computer storage medium
  • Network training method, device, computing device and computer storage medium
  • Network training method, device, computing device and computer storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0062] Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be embodied in various forms and should not be limited by the embodiments set forth herein. Rather, these embodiments are provided for more thorough understanding of the present disclosure and to fully convey the scope of the present disclosure to those skilled in the art.

[0063] figure 1 It shows a schematic flowchart of an image stylization processing method according to an embodiment of the present invention, the method can be executed by a terminal or a server, and the method is executed based on a trained first network, such as figure 1 As shown, the method includes the following steps:

[0064] Step S100, acquire a first image.

[0065] Wherein, the first image may be a style image with any s...

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 network training method, device, computing equipment and computer storage medium, wherein the network training method is completed through multiple iterations; wherein the training step of one iteration process includes: extracting a first sample image and a second sample image ; According to the first network and the first sample image, a second network corresponding to the style of the first sample image is obtained; using the second network, a third sample image corresponding to the second sample image is generated; according to the third sample image The weight parameters of the first network are updated by the loss between the first sample image and the second sample image; and the above training steps are iteratively executed until a predetermined convergence condition is met. According to the technical solution provided by the present invention, the first network suitable for arbitrary style images and arbitrary content images can be trained, and the use of the first network is helpful to quickly obtain the corresponding image conversion network, and improve the efficiency of image stylization processing.

Description

technical field [0001] The present invention relates to the technical field of image processing, in particular to a network training method, device, computing equipment and computer storage medium. Background technique [0002] Using image stylization processing technology, the style on the style image can be transferred to the daily captured image, so that the image can obtain better visual effects. In the prior art, a given style image is directly input into a neural network (neural network), and then a large number of content images are used as sample images, and the corresponding image corresponding to the given style image is obtained after multiple iterations of training. An image conversion network, using the image conversion network to realize the style conversion of the input content image. [0003] In the prior art, for any given style image, tens of thousands of iterative operations are required to train the neural network to obtain the image conversion network c...

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 Patents(China)
IPC IPC(8): G06N3/08G06T3/00
CPCG06N3/08G06T3/00
Inventor 申发龙颜水成曾钢
Owner BEIJING QIHOO TECH CO LTD