Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Model missing aggregator #25

Open
mrjoness opened this issue Jun 14, 2024 · 2 comments
Open

Model missing aggregator #25

mrjoness opened this issue Jun 14, 2024 · 2 comments
Assignees

Comments

@mrjoness
Copy link

Hello, I am trying to run CLN tutorial model using the following command:

python /torchmd_mamba_env/lib/python3.10/site-packages/torchmd/run.py --conf simulate.yaml

But I see the following error, which shows there is no aggregator argument associated with the model (I'm using ../Models/cln/model.ckpt)

model.py 228 load_model
model = create_model(args)

model.py 76 create_model
aggr=args["aggr"],

KeyError:
aggr

I tried manually setting the aggr to "add", "mean", and "max", which fixes this issue and starts a simulation, but in each case I see the following issue:

run.py 265 dynamics
Ekin, Epot, T = integrator.step(niter=args.output_period)

integrator.py 68 step
pot = self.forces.compute(s.pos, s.box, s.forces)

forces.py 84 compute
raise RuntimeError("Found NaN coordinates.")

RuntimeError:
Found NaN coordinates.

Is there some version issue with TorchMD? or is there something else I am doing wrong here?

Thank you

@AdriaPerezCulubret
Copy link
Collaborator

Could you tell me which version of torchmd and torchmdnet you have?

@mrjoness
Copy link
Author

Hello, yes here are the versions. I followed the mamba installation in the torchmd repo as I was having trouble with the installation instructions here.

torchmd 1.0.2 pypi_0 pypi
torchmd-net 2.2.0 cpu_py310h6472234_2 conda-forge

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants