Why the training always stop at scale 8 ?

tamarott / SinGAN

Official pytorch implementation of the paper: "SinGAN: Learning a Generative Model from a Single Natural Image"

https://tamarott.github.io/SinGAN.htm

Other

3.31k stars 611 forks source link

Why the training always stop at scale 8 ? #164

Open Philip-PKU opened 2 years ago

Philip-PKU commented 2 years ago

I've tried several times to train different pictures, but every time the training will stop at scale 8 [1999/2000], but the preference at that scale is not good enough.

How can I fix that to continue the training? Thanks.