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

Loading a subset of fields in NNPInput and Metadata #156

Open
ArnNag opened this issue Jun 11, 2024 · 0 comments
Open

Loading a subset of fields in NNPInput and Metadata #156

ArnNag opened this issue Jun 11, 2024 · 0 comments
Assignees
Labels
optimization Issues related to improving performance.

Comments

@ArnNag
Copy link
Collaborator

ArnNag commented Jun 11, 2024

There are some situations where we do not need to load all the fields currently included in the BatchData instance returned by collate_conformers. For example, we do not need to load forces when training only on energies, need neither forces nor energies if we just want to run inference, do not need total charge for some of the models, etc. Should we subclass NNPInput and Metadata for different combinations of datafields?

@ArnNag ArnNag added the optimization Issues related to improving performance. label Jun 12, 2024
@wiederm wiederm self-assigned this Jun 21, 2024
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
optimization Issues related to improving performance.
Projects
None yet
Development

No branches or pull requests

2 participants