Hong Yue

I'm having the same problem as well

Not sure if this is a typo or actually intended, but it looks like there are some inconsistencies in the TimeGAN notebook with regards to indexing for the supervisor inputs...

Hi, thinking of taking this on. It looks like all that's needed is to replace `history['sresid'].append(tmp_results.resid / tmp_results.scale)` with `history['sresid'].append(tmp_results.resid / self.scale)`. Anything else I should consider?