greatlog / DAN

This is an official implementation of Unfolding the Alternating Optimization for Blind Super Resolution
231 stars 41 forks source link

DANv2 group["initial_lr"] throwing error #49

Open kmbecker19 opened 10 months ago

kmbecker19 commented 10 months ago

Hi all, has anyone solved the following error message when trying to train DANv2?

group["initial_lr"] * weight for group in self.optimizer.param_groups TypeError: unsupported operand type(s) for *: 'NoneType' and 'int'

It does not appear with DANv1, and I've seen others report the same issue, but there are no solutions to be found.

syGe888 commented 3 months ago

you can add "lr_E: !!float 4e-4" in yml file to solve this problem