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

batch active learning #175

Merged
merged 20 commits into from
Oct 6, 2023
Merged

batch active learning #175

merged 20 commits into from
Oct 6, 2023

Conversation

M-R-Schaefer
Copy link
Contributor

@M-R-Schaefer M-R-Schaefer commented Sep 27, 2023

rudimentary batch active learning implementation.
currently only supports last layer gradient features (also of ensembles) and greedy max dist selection.

Further changes:

  • cleanup of the ASE calculators handling of implemented_properties
  • switched all pbars from using context managers to explicit closing
    • Fixed NL pbar diappearing after completion
  • moved all loading of parameters from the ASE calc to checkpoints

TODO:

  • citations
  • doc strings
  • progress bar for feature computing
  • improve feature map config

@M-R-Schaefer M-R-Schaefer changed the title [WIP] batch active learning batch active learning Sep 29, 2023
@M-R-Schaefer M-R-Schaefer merged commit 6f26fc3 into dev Oct 6, 2023
5 checks passed
@M-R-Schaefer M-R-Schaefer deleted the bal branch October 6, 2023 09:42
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