Implement exaggeration
Closed this issue · 2 comments
Implement (early) exaggeration, which means that relation values are rescaled by a given factor for the first few epochs. The relation loss has to be rescaled accordingly. This could be specified in the relation loss.
Much easier, and a nice proof of the generalization of training phases: implement Exaggerate
transform that simply multiplies the relations by a given factor. Still, to get correct scaling of the relation loss it will be necessary to detect the existence of an exaggeration transform inside ParametricDR
and pass the info on to the loss.
I decided to not implement this at all for now. Users can specify exaggeration easily via a Functional
transform. The just have to rescale the loss themselves, if at all necessary.