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.
This PR fixes the inability to import BatchQuantileLoss from the losses submodule, even if importing it directly with from matsciml.models.losses import BatchQuantileLoss, as it was accidentally omitted from the module's __all__ definition.
This PR fixes the inability to import
BatchQuantileLossfrom thelossessubmodule, even if importing it directly withfrom matsciml.models.losses import BatchQuantileLoss, as it was accidentally omitted from the module's__all__definition.