Jake Grigsby

@RaphaelMeudec I use tensorflow as my backend and it seems to be working. I use 1.10 so I'll update and see if that's the issue.

IIRC that's a convention inherited by Informer and the followup works to it that have come out since this repo's initial release and before it's more recent versions. The accuracy...

Yeah the traffic datasets / literature is the main example where reporting multiple horizons is the default. The longest horizons are 12 timesteps so this can be feasible. Once you...

Hi, and thanks! Sorry, I am not sure I fully understand the question. Do you have multiple variables (`{y_0, ... y_N}`), but each series is taken at different time intervals?...

Ok so the default embedding is designed to look at long sequences of N variables that have some relationship to each other and make a prediction of those same N...

There is a big difference between a batch size of 32 and a batch size of 3! This is probably the most memory-intensive dataset in the paper. It should be...

Hi, this looks like a generic PyTorch installation error that isn't related to the spacetimeformer code or PyTorch lightning (which is a third-party library that basically handles training loop boilerplate)....

Hey @ferdinandl007, in general our training script was meant more as a way to replicate the paper results than to help on new datasets. It's all pretty hardcoded as you...

@ferdinandl007 I added a demo of how to use this dataset and plot specific variables in #41 . Was only able to mess around with your dataset for a couple...

My conda env has the same torchmetrics, tqdm ,and lightning version as the pip freeze above but I wasn't able to replicate this... the command trains fine. It also works...