You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
@Honlan The first phase is for latent-guided synthesis and the second phase is for reference-guided synthesis. The only difference is whether to use the mapping network or the style encoder to extract target style codes.
So, why mapping_network and style_encoder are optimized during the first phase (optims.mapping_network.step(), optims.style_encoder.step()), but these two modules are not optimized during the second phase?
Hi~ thanks a lot for your awesome work!
I find that during each iteration, D is optimized for twice:
G is also optimized for twice:
However, mapping_network and style_encoder are only optimized for once.
Could you explain it for me? many thanks again.
The text was updated successfully, but these errors were encountered: