Giacomo Guiduzzi

I'm having the same issue. I'm using docker stats through a Python script to collect CPU and memory usage of a container while a client sends requests so to analyze...

Hi @dennisbader, I thought of opening the issue in the meantime just in case you had any idea of similar issues; I'm working on the example to provide you, I'll...

Hello @dennisbader, I thought of creating a git repo as the script is pretty long, although I tried to minimise the code for the example: [https://github.com/giacomoguiduzzi/tcnmodel_bug_example](url) The script terminates correctly,...

Hi @dennisbader, after reading the posts you suggested, it makes sense. It looks like the model runs fine now with your correction! Thanks a lot for the help. Best Regards,...

Hi @eschibli, Thank you for your answer. So the `output_chunk_shift` parameter doesn't simply shift the predictions ahead; the model is actually able to learn in a different way through it....

Thanks for the info @eschibli, I've been looking into this parameter using DLinear as a reference model. I don't quite get if `output_chunk_shift` only changes the dataloader's behavior or the...

Thank you for confirming my thoughts. This means that the parameter is not used at all because I am overloading the dataloader class using `fit_from_dataset` to supply my sliding windows....

No worries @eschibli, I'll give you some more context. In issue #2365, I asked for info about controlling the window-creating process, as I wanted to be sure regarding how data...