Closed dominicrufa closed 1 year ago
@peastman , @raimis: turns out ^this is actually the crux of this issue
This may also be related to https://github.com/openmm/openmm/issues/3588.
in the interest of getting openmm-ml
working with nnpops
, i think the easiest thing would be to just extract the TorchForce
from the customCV (as in my fork) and run with it until a more stable solution is found. is that agreeable?
@peastman, have you found a stable workaround for this issue, or should we proceed with removing the TorchForce
from the CVForce
?
tagging @jchodera
Let me make one more effort at trying to figure it out. I suspect this is related to https://github.com/openmm/openmm/issues/3588, and most especially to https://github.com/openmm/openmm/issues/3588#issuecomment-1151731824. If I can't figure out a proper solution, we can use your suggested workaround.
@dominicrufa : Can you test the PR here? https://github.com/openmm/openmm-torch/pull/78
@peastman , I am unable to source install the PR and make it compatible with the rest of the conda
-installed bits needed for the nnpops
test. if you can source install it locally, can you run the test i mentioned at the top of this issue?
It runs without problem now. It looks like that fixes it!
@peastman , awesome! can you merge the PR and make it conda-installable? i can add a PR with the nnpops
implementation for anipotential.py
here and modify the test to test for the torchani
and nnpops
implementation if you'd like.
@peastman could reopen this. I don't permissions.
I just added you as a maintainer. You should have full permissions now.
@dominicrufa I can reproduce the issue and created a minimal test https://github.com/openmm/openmm-torch/pull/80/commits/63a49c170232531c12edf5db2d2f5255af1dfa6f.
@raimis , great! let me know if/when i can conda-install the fix to write the openmm-ml
tests.
@dominicrufa : Can you confirm the latest release fixes this? If so, can you close this?
yes, this is fixed. closing
I have been trying to create a minimally-modified implementation to get
nnpops
working on a conda-installableopenmm-ml
environment, and i am encountering an error inTestMLPotential.py
with the implementation.If you drop in/replace the
anipotential.py
with this and run the test, (making sure to set theplatform
toCUDA
), you should see that the test fails on line 26,meaning that the
createMixedSystem(..., interpolate=False)
is compatible withnnpops
, butinterpolate=True
is not. I have found a way around this (by taking theTorchForce
out of the customCVForce and adding ascale
parameter to theANIForce
manually), but I don't want to open a PR attempting to merge my modifications unless the compatibility issue withnnpops
can't be fixed an easier way.