when training in 256x256, the output is 256x512 pixels

[notnot]

First, thanks for this great repository. It is very useful to study the sylegan2 architecture!

When training in 256x256 resolution, the output images have a size of 256x512 (h x w), These are in fact two images stacked on top of each other. I can easily 'unstack' this output by reshaping the tensor, but i wonder why it happens? If my batch size is 2, i get 4 outputs. This will become problematic when i will increase resolution and need to generate just a single 512x152. I don't want the system to actually generate a 512x1024.

The two 'stacked' images are also quite similar.

[notnot]

Ok, after diving deeper into the code i have discovered that Trainer.gen_samples() is stacking two variants of outputs. It is a feature, not a bug, I will adapt the code to suit my needs.