Open MatSci ML Toolkit is a framework for prototyping and scaling out deep learning models for materials discovery supporting widely used materials science datasets, and built on top of PyTorch Lightning, the Deep Graph Library, and PyTorch Geometric.
The checkpoint check from #215 was not working as expected. Somthing about how __ functions get tied up with the class in which they are associated with (mangling). This PR fixes this issue by making it a single underscore.
File "./matsciml/examples/interfaces/ase_from_pretrained.py", line 24, in <module>
calc = MatSciMLCalculator.from_pretrained_force_regression(
File "./matsciml/matsciml/interfaces/ase/base.py", line 264, in from_pretrained_force_regression
ckpt_path = __checkpoint_conversion_exist_check(ckpt_path)
NameError: name '_MatSciMLCalculator__checkpoint_conversion_exist_check' is not defined
The checkpoint check from #215 was not working as expected. Somthing about how
__functions get tied up with the class in which they are associated with (mangling). This PR fixes this issue by making it a single underscore.