Michaël Defferrard

There's indeed no such file. Sorry the project is still in development and things are fluid. I guess we'll provide all the data in a zenodo archive or something at...

You can find spherical layers (both convolutions and poolings) in [`modules/layers.py`](https://github.com/deepsphere/deepsphere-weather/blob/main/modules/layers.py). They are to be used like standard PyTorch layers (see [`modules/my_models_graph.py`](https://github.com/deepsphere/deepsphere-weather/blob/main/modules/my_models_graph.py)).

Thank you for your interest. @ghiggi could you advise?

**User Story No. 13** Tania is a packager (linux distro, conda-forge, homebrew, containers). What are best practices to build, test, and package numpy? ~Should they bundle OpenBLAS or delegate to...

Thanks for your interest and kind words. The [3-body problem](https://en.wikipedia.org/wiki/Three-body_problem) seems like a good fit indeed. I however don't know what "opening angles" are. Our method allows to easily model...

Quick drawing of the situation as I understood it:  In which case you could represent `d_{12}` and `α_{12}` as features of node `v_3` and/or edge `(v_1,v_2)`.

> wouldn't appending these features lead to node descriptors that are of different length depending on the ammount of connections coming off them Oh so it's not always 3 bodies?...

I see. Distances are indeed better modeled as edge features than as a set of node features. A simplicial complex would be a good model of the geometry of your...

From an information point-of-view, there are many ways to model the problem. For example, both the set of all 3D positions (as node features) and the set of all pairwise...

Sure keep us posted. :)