Alex Colpitts

This still seems to be an issue. I had been training in a Docker container and thus not seeing the plots. After training completed when not using a container, my...

Google Research implementation: https://github.com/google-research/google-research/blob/master/tsmixer/tsmixer_basic/models/tsmixer.py Details in the paper aren't great; however, the source code clears things up.

I have ran into a few things with the implementation and had some other PRs that I needed to cleanup. I managed to implement reversible instance normalization, but there is...

I started working on it roughly two months ago. I have been busy wrapping up school and starting a new job. I should have some time to clean it up...

Hey! There are a few issues I can see at a high level with the replication. `Scaler` in darts defaults to min-max scaling when they used standardization in the paper....

I see that they used gradient clipping. You can use it with darts by passing it to `pl_trainer_kwargs`. Ex: `gradient_clip_val=0.5`. https://lightning.ai/docs/pytorch/stable/advanced/training_tricks.html I am also not sure you configured the learning...