Closed hiroyamaeda closed 6 years ago
I do not have a lot of practical experience in dealing with large images, but I believe you might need to increase the number of filters in the Conv layers (both generator and discriminator). Maybe add 1-2 additional conv-batch norm-relu layers, but I doubt if they are really needed.
Thank you for sharing the important information! I will try.
When changing the output image size to 128x128, what should be changed in the code ...?