Victor Rodriguez-Fernandez

I believe it's the other way around

I've just realized that this function does not work when using `Normalize` as a `batch_tfms`. It produces this error: ``` --------------------------------------------------------------------------- RuntimeError Traceback (most recent call last) in ----> 1...

I am not sure that @ai-fast-track is still maintaining this repo...

It must be something specific of that Callback. I use `WandbCallback` and it does not raise that error

I don't think so. I forked it just to update it for the new fastai release, in case you want to use it

What about InceptionTimePlus?

Isn't this a fastai issue?

Does that happen only with augmentation Transforms (those that inherit from fastai's `RandTranform`) or it happens with normal preprocessing transforms too?

You can apply padding to make all the sequences have the same length, and add timestamp information as additional variables.

awesome, thanks! Where can I stay tuned for updates?