At present, the generative adversarial networks research that generates a high\nconfidence image for a large number of training samples has achieved some\nresults, but the existing research only performs image generation for known\ntraining samples, but does not use the training parameters for image generation\nother than training samples. This paper uses the Tensor Flow deep learning\nframework to build deep convolutional generative adversarial networks to\ncomplete the generation of virtual face images. From the experimental results,\nit can better generate virtual face images similar to real faces, which provides\nnew ideas and methods for the research of generating virtual images.
Loading....