Open dominicrufa opened 3 years ago
This seems to be a common error. This issue has lots of discussion by people encountering it.
https://github.com/NVIDIA/apex/issues/580
Here's one where the problem was fixed by upgrading to PyTorch 1.9.
https://github.com/allenai/allennlp/issues/5064
In this one it was fixed by upgrading to CUDA 11.2.
There are many other pages discussing the same error. Often it seems related to inconsistencies in the shapes or dtypes of tensors.
I noticed these, too. Will give these solutions a try and get back. Thanks for the sleuthing.
@dominicrufa : Is this still an active issue?
In attempting to run MD on a
TorchForce
-equippedSystem
(theTorchForce
has theNNPOps
symmetry functions equipped as described here ), I am observing strange behavior. Namely, I am able to create aContext
with theSystem
and return theState
object with a potential energy, but when i run a step of dynamics, I observeOn the other hand, if i do not equip the
NNPops
ani symmetry functions, this error is not encountered. I didnt notice any examples/pytests in this repo re: equipping aTorchForce
withANISymmetryFunctions
. I'm not sure if this interoperability has been tested yet. If so, would it be possible to add a pytest/example? I'm not sure if this should go into theopenmm-torch
repo instead (since the functionality I was to practice usesNNPOPS
). I'd be happy to troubleshoot if needed.