Modified collate_fn for predicting multiple values per target property with M3GNet model and included a unit test

materialsvirtuallab / matgl

Graph deep learning library for materials

BSD 3-Clause "New" or "Revised" License

233 stars 57 forks source link

Summary

The current framework of collate_fn is only working for a single value per target with the M3GNet model. This pull request modifies the framework such that the M3GNet model can predict multiple values per target and the unit test is added.

Checklist

[x] Google format doc strings added. Check with ruff.
[x] Type annotations included. Check with mypy.
[x] Tests added for new features/fixes.
[x] If applicable, new classes/functions/modules have duecredit @due.dcite decorators to reference relevant papers by DOI (example)

Tip: Install pre-commit hooks to auto-check types and linting before every commit:

pip install -U pre-commit
pre-commit install

Codecov Report

All modified and coverable lines are covered by tests :white_check_mark:

Comparison is base (c3e5642) 98.59% compared to head (3451e0d) 98.59%.

Additional details and impacted files

```diff @@ Coverage Diff @@ ## main #192 +/- ## ======================================= Coverage 98.59% 98.59% ======================================= Files 28 28 Lines 1926 1926 ======================================= Hits 1899 1899 Misses 27 27 ```

materialsvirtuallab / matgl