Confusion about dense model？ about gan-slimming HOT 3 OPEN

if i use gs.py for other network,whether i need change model?

from gan-slimming.

Thanks for your interest in our work. GAN training is unstable due to the minimax optimization process, and combining it with model compression makes it even more unstable due to the use of non-differentiable sparse constraints. Using the dense model for distillation stabilizes the training process and empirically achieves better results. You can definitely directly compress GAN without the dense model, but it won't achieve as good a performance, as shown in our ablation study.

from gan-slimming.

if i use gs.py for other network,whether i need change model?

Yes, you will need to replace CycleGAN (the model currently used) with your own network.

from gan-slimming.