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

Added a few classes util for structure relaxations (in particular MOMONANO) #415

Merged
merged 46 commits into from
Jun 17, 2022

Conversation

jnsLs
Copy link
Collaborator

@jnsLs jnsLs commented Jun 1, 2022

  • added batch-wise atoms converter
  • modified ase_interface (for optimization)
  • added neighborlist wrapper (for postprocessing of the nbh list, e.g., neglecting neighbors)
  • adapted Skin NBL documentation

jnsLs and others added 30 commits November 1, 2021 15:33
@@ -29,6 +31,37 @@ class CacheException(Exception):
pass


class NeighborlistWrapper(Transform):
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

why is this needed? why not add a separate preprocessing layer?

Copy link
Collaborator Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

for the training procedure you are right: one could just use a separate preprocessing layer. However, in the scope of MD and structure relaxation, this wrapper makes it more convenient to use NBL postprocessing. For example, the AtomsConverter in its current state does not allow the usage of additional pre/postprocessing. One would either have to implement a postprocessing parameter there or keep it as is and use the nbl wrapper instead.

@jnsLs jnsLs requested a review from ktschuett June 10, 2022 13:09
@ktschuett ktschuett merged commit e3ae8ce into atomistic-machine-learning:dev Jun 17, 2022
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

Successfully merging this pull request may close these issues.

2 participants