mirko-m

I am also running into this issue when I use the `NegativeBinomialDistributionLoss` , but things work fine when I use the `NormalDistributionLoss` instead.

In my case I was able to fix the problem by changing the following line ```python target_normalizer=TorchNormalizer(method="identity",center=False,transformation=None ) ``` to ```python target_normalizer=EncoderNormalizer(method="identity", center=False, transformation=None) ```` when defining the `TimeSeriesDataSet`. The...

@baumanab did you end up creating a PR for this? I am also running into the same issue.

I found a workaround, so this is no longer a pressing issue for me. However, I am interested in collaborating on a fix since that seems like a good opportunity...

Sorry for the late reply. My workaround is to have multiple columns with flat arrays instead of a single column with a nested array. Then, in the loop over the...

Sounds good. Just ping me when you have something and I can try to help.

I have not heard anything since my last post.

I was also having issues using a `TransformSpec` together with `make_batch_reader` . In my case the issue was that I thought that the `func` parameter which is passed to the...

Thanks, Do you happen to know what actually fixed the error? Is it something that is different in the way in which you instantiate the `TimeSeriesDataSet`?