stylegan2-pytorch
stylegan2-pytorch copied to clipboard
Parameters for generating faces
Hi, i want to train a GAN to generate images of faces but i am facing the following problems. I am using a dataset of 200000 images of 128x128 and generating images of the same size. I tried training with the dafault mode and the results have some abnormal characteristics in the faces and the background. I was wondering if there were some hyperparameters for the train that lead to clean results for generating faces?
Good question, what is @yoniker's params?