Image conversion model generation method and device, electronic equipment and storage medium

Abstract

The invention discloses an image conversion model generation method and device, electronic equipment and a storage medium, and belongs to the field of image processing. The method comprises the stepsof training a first initial model based on an obtained first sample image set until a first training stopping condition is met to obtain a second initial model, wherein the first sample image set comprises a plurality of real person images and a plurality of cartoon images, and the classification category of each cartoon image belongs to a first classification category or a second classification category; wherein the cartoon styles of the cartoon images belonging to the second classification category are consistent; inputting the real person image set belonging to the first classification category into a second initial model to obtain a first generated cartoon image set belonging to the first classification category, so that a set of the first generated cartoon image set and the first sample image set is used as a second sample image set; and training the first initial model based on the second sample image set until a second training stopping condition is met to obtain an image conversion model. According to the invention, the similarity between the converted cartoon image and the real person image can be improved.

Description

Technical field[0001]This application relates to the field of image processing technology, and in particular to a method, device, electronic device, and storage medium for generating an image conversion model.Background technique[0002]With the development of the Internet, neural network models can have image conversion functions. For example, neural network models can perform image conversion processing on real-person avatars to obtain cartoon-like avatars; or, neural network models can image captured landscape images The conversion process can obtain an image with oil painting effect. The commonly used neural network model is Cycle-GAN (Cycle-Generative Adversarial Networks).[0003]However, when using Cycle-GAN to cartoonize real-life images, there is a problem of low similarity between the converted cartoon images and real-life images.Summary of the invention[0004]In order to solve the above technical problems, this application provides a method, device, electronic equipment and st...

AI Technical Summary

Problems solved by technology

[0003] However, when using Cycle-GAN to perform image cartoonization on real-life images, there is a problem that the similarity between the converted cartoon images and real-life images is low

Images