Ahmed Abdou comments

Repositories
Issues
Comments

Results 2 comments of


                                            Ahmed Abdou

triplet loss can't convergence,how can I do?

I came across this issue, I don't know if you still need an answer but for future readers: The loss=margin, mainly means that all the embeddings collapsed to one point....

TorchNormalizer.transform() missing 1 required positional argument: 'X'

The error is due to using older version of pytorch-forecasting. The issue is solved in the recent version in this [line ](https://github.com/jdb78/pytorch-forecasting/blob/cd0ecbd925e4519a33950c27c8bc2a2376117520/pytorch_forecasting/data/encoders.py#L961C9-L961C9) ` return super().transform(y, return_norm=return_norm, target_scale=target_scale) ` the commit...