I've built the stylegan and its training loop using Tensorflow from its research paper, I'm using celebA-HQ dataset of 30k images. But even after running more than 5000+ steps it is not showing any improvements. Can anyone help me in my script where I'm doing mistake? PFA colab notebook https://colab.research.google.com/drive/12Y4J3SnmQ1iK2TuoUfykF8zz_9Ykji7Z?usp=sharing
Generated image after running more than 5000 steps:
I've tried altering hyperparameters Added missing steps like normalizing image before feeding into mapping network, corrected the w-loss, added gradient penalty
