Alby M.

Added some basic tests, the model does run and produce numbers for the stress when PBC are used. (See `minimal-stress.yaml`.) Whether they're reasonable I can't really say. One thing I'm...

Great! That's partially trained on forces, predicting stresses? Looking at `stress_dir.zip` I'm not sure I see the finite difference test you're talking about... EDIT: I've added stress to the rescaling

Hi @keano130 , Wanted to let you know that stress is now being implemented in the `stress-develop` branch off of the latest `develop` — see PR https://github.com/mir-group/nequip/pull/119. We hope to...

Hi @keano130, Just a heads up that I've gone ahead and merged the (now much more complete) `stress-develop` branch into develop to end the merge hell that's starting to accumulate...

@davidleocadio does your model include a `StressForceOutput`? The model must be built to calculate stresses for the calculator to be able to get those outputs. See `minimal_stress.yaml` for an example...

@davidleocadio it'll be something like this: 1. pull the latest `develop`--- I renamed something in `StressOutput` to make this more consistant going forward. (Warning: this will break loading models trained...

Hi @peastman , Thanks very much for posting this! I am away from code development right now and unfortunately will not be able to take a closer look for a...

This looks like a historical `e3nn` / `opt_einsum_fx` bug, see: https://github.com/e3nn/e3nn/issues/311 that intersects with the PyTorch version you have. In general I think `nequip` 0.5.5 is still compatible with `e3nn`...

Hi @peastman , Please try the latest un-stable `develop` branch (**at least to pre-process your dataset, once it's cached you should be able to go back and run trainings using...

...huh. Is your `r_max` very big or your atomic systems very dense? I'm struggling to see how 1.5GB of `.xyz` could get there... You could try adding some `print` statements...