YojoNick

I realize I'm like 5 months late to the party with this response, but in case anyone else runs across this, the way I fixed this (without having to edit...

In my experience with this problem, I've found that the memory consumption stops increasing and goes down (a little bit) after an epoch is complete. Therefore, in my circumstance, if...

Changing the target_normalizer parameter to GroupNormalizer(groups=['GroupID'], transformation="softplus") still results in the target value being equal to its original, unnormalized value.

FYI - The values in tsd.data['target'] are all also not normalized

I have this same issue with the following: ------ installed packages -------- jupyterlab-tensorboard-pro 0.7.0 tensorboard 2.10.0 tensorflow 2.10.0 jupyterlab 3.0.16 python3.8