Open ryanwebster90 opened 2 years ago
We didn't benchmark that, but it is expected that InfinityGAN training will be slower than StyleGAN2, since (i) we have an additional structure synthesizer, and (ii) the padding-free generator requires a larger input features than usual models (which zeros-padding pads those regions with zeros).
Hey, thanks for the open source code. Do you have benchmarks for various training setups, for instance, what is the iter/s for InfinityGAN.yaml (using patchsize of 101).