jsvetter
jsvetter
TODO for Hackathon: Circular import Fix by either - Restructuring codebase - Directly importing the relevant objects and removing the circular import from `__init__.py`
This is heavily related to #962! So it would probably be good to coordinate some aspects :)
I would also be interested in doing this!
[torchdiffeq](https://github.com/rtqichen/torchdiffeq) seems like a reasonable choice for ODEs in pytorch. It's also used in [dingo](https://github.com/dingo-gw/dingo)! Alternatives are [torchDyn](https://github.com/DiffEqML/torchdyn) and [torchode](https://github.com/martenlienen/torchode).
TODO for the hackathon: As described by @janfb above, this issue is not concerned with the core codebase, but only with the tutorial notebooks. - [ ] Go through all...
Yes, absolutely!
Hi! Re 1: I'm personally not very familiar with the full AJILE Dataset myself! The experiments in the paper used the preprocessed data from the [this paper](https://iopscience.iop.org/article/10.1088/1741-2552/abda0b) (which is provided...
Hi! In this case, as in the paper, it would be possible to cut the recording into shorter segments to create a training data set of shape $(N,C,L)$. Longer dependencies...