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

❓ [QUESTION] CIF files & other target properties #268

Open
giotre opened this issue Nov 22, 2022 · 1 comment
Open

❓ [QUESTION] CIF files & other target properties #268

giotre opened this issue Nov 22, 2022 · 1 comment
Labels
question Further information is requested

Comments

@giotre
Copy link

giotre commented Nov 22, 2022

If this isn't an issue with the code or a request, please use our GitHub Discussions instead.

I have a database of CIF files (i.e., multiple structures), so I have created a *.xyz database in format *.extxyz, which, read in the Python notebook, appears like a list:
[Atoms(symbols='CH3FI', pbc=False, forces=...),
Atoms(symbols='CH3FI', pbc=False, forces=...),
Atoms(symbols='I2', pbc=False, forces=...),
...
]

I was wandering if it is possible to use other target properties beyond energies/forces, for instance properties related to the entire structure and not to the atoms. And what if one does not have energies and forces?

Environment

  • OS: Ubuntu
  • python version: 3.9
  • e3nn version: 0.5.0
  • pytorch version: 1.11.0+cu102
  • nequip version: 0.5.5
@giotre giotre added the question Further information is requested label Nov 22, 2022
@Linux-cpp-lisp
Copy link
Collaborator

Linux-cpp-lisp commented Nov 28, 2022

Hi @giotre ,

Thanks for your interest in our code!

Yes, that sounds correct— extxyz is our prefered input format and it supports arbitrary per-atom and per-graph fields. nequip supports arbitrary fields in datasets.

As to training on other targets, this is certainly possible and supported but not really documented anywhere yet. I think it would be best if I try to draft something more formal as soon as I get a chance and then send it along rather than doing it piecemeal here...

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

No branches or pull requests

2 participants