Model training method and device, image processing method and device, electronic equipment and medium

A model training and image technology, applied in the fields of model training methods, electronic equipment and media, devices, and image processing methods, can solve problems such as time-consuming training process and slow model training speed

Pending Publication Date: 2021-12-28
BEIJING ZITIAO NETWORK TECH CO LTD
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The shortcomings of the existing technology include at least that in order to ensure the effect of face conversion, the model needs to undergo a long training process, resulting in slow model training.

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
  • Model training method and device, image processing method and device, electronic equipment and medium
  • Model training method and device, image processing method and device, electronic equipment and medium
  • Model training method and device, image processing method and device, electronic equipment and medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0045] figure 1 It is a schematic flowchart of a model training method provided in Embodiment 1 of the present disclosure. The embodiments of the present disclosure are applicable to the situation of training a model for image conversion, for example, it is suitable for the situation of training a model for face image conversion. The method can be executed by a model training device, which can be implemented in the form of software and / or hardware, and the device can be configured in electronic equipment, such as a computer.

[0046] like figure 1 As shown, the model training method provided in this embodiment includes:

[0047] S110. Train a conversion model according to the first image of the source type and the second image of the target type, so as to convert the first image into a third image of the target type based on the trained conversion model.

[0048] The model trained based on the model training method of the embodiment of the present disclosure can be used to ...

Embodiment 2

[0076] The embodiments of the present disclosure may be combined with various optional solutions in the model training methods provided in the foregoing embodiments. The model training method provided in this embodiment describes the training steps of the conversion model in detail. First, by training the generative model based on the first image, the generative model can generate images of the source type; secondly, by using the generative model as a priori, and training the encoder based on the first image, the encoder can extract image features; again , by connecting the encoder to the conversion model, using the parameters of the trained generation model to configure the initial parameters of the conversion model, and training the conversion model based on the first image and the second image, the conversion model can be realized from the source type to the target type image conversion.

[0077]By training the encoder based on the generative model, the encoder can extract...

Embodiment 3

[0111] Figure 7 It is a schematic flowchart of an image processing method provided in Embodiment 3 of the present disclosure. The embodiments of the present disclosure are applicable to the situation of performing face conversion on a human face image, for example, applicable to situations such as age conversion and gender conversion. The method can be executed by an image processing device, which can be implemented in the form of software and / or hardware, which can be integrated into application software, and can be installed in electronic equipment along with the application software, such as installed in servers, mobile phones, computers and other electronic equipment.

[0112] like Figure 7 As shown, the image processing method provided in this embodiment includes:

[0113] S710. Input the to-be-converted image of the source type into the special effect model.

[0114] S720. Output the target image of the target type through the special effect model.

[0115] Wherei...

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 embodiment of the invention discloses a model training method and device, an image processing method and device, electronic equipment and a medium, and the method comprises the steps: training a conversion model according to a first image of a source type and a second image of a target type, and based on the trained conversion model, converting the first image into a third image of the target type; adjusting the corresponding object in the third image according to the object contained in the first image to obtain an adjusted image; and training a special effect model according to the first image and the adjusted image. The third image generated by the conversion model is adjusted, and the special effect model training is performed based on the adjusted image, so that the model training speed can be improved on the basis of ensuring the conversion effect.

Description

technical field [0001] Embodiments of the present disclosure relate to the technical field of machine learning, and in particular, to a model training method, an image processing method, an apparatus, electronic equipment, and a medium. Background technique [0002] Nowadays, special effects of face images have been widely used in various application software, such as image / video editing software, shooting software, etc. Wherein, the special effect playing method of the face image may include face conversion, such as age conversion, gender conversion, and the like. [0003] In the prior art, face conversion in a face image can be realized based on a trained model. The deficiencies of the prior art at least include that in order to ensure the face conversion effect, the model needs to undergo a long training process, resulting in a slow model training speed. Contents of the invention [0004] Embodiments of the present disclosure provide a model training method, an image ...

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): G06T3/00G06N20/00
CPCG06N20/00G06T2207/30201G06T3/04
Inventor 张朋周思宇
Owner BEIJING ZITIAO NETWORK 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

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