aydao

You are suffering divergence with the losses you report, making it unlikely to recover. Hopefully you have an earlier checkpoint around and can resume training from a point that was...

Yes, typically you would want to decrease the learning rate gradually to converge to a local minimum. However, the original StyleGAN code specifies multiple learning rates that increase during progressive...

Both, or with the generator set to 0.0003 and the discriminator even lower. Note that I've found it important to keep the learning rates at 0.003 initially for transfer learning,...

The load_data() function [is defined in utils.py](https://github.com/taki0112/StyleGAN-Tensorflow/blob/1cca9da1f55f91a42a4b05b61c9340930eda0d94/utils.py#L56), which [StyleGAN.py imports](https://github.com/taki0112/StyleGAN-Tensorflow/blob/1cca9da1f55f91a42a4b05b61c9340930eda0d94/StyleGAN.py#L3).