Image Conversion in Multiple Domains Based on Gan

Generative Adversarial Networks can be used to generate clear images, but in different domains of the image conversion, for example, a picture from a man to a woman, or from hair to baldness, many methods use multiple models to transform input images rather than single model, which may cause the artifacts. There is no quantitative and qualitative way to evaluate the experimental results. Based on the idea of Generative Adversarial Networks, this paper can use a single model to convert multiple domains of images. After the conversion is completed, the pre-training is used to classify the images. The experimental results show that the method can realize image conversion between multiple domains and can better evaluate the experimental results.