v0.8.3

• Extend the functionality of ASE-interface for molecular systems and include more different ensembles. (@kenko911)
• Improve the dgl graph construction and fix the if statements for stress and atomwise training. (@kenko911)
• Refactored MEGNetDataset and M3GNetDataset classes with optimizations.

v0.8.2

• Add site-wise predictions for Potential. (@lbluque)
• Enable CLI tool to be used for multi-fidelity models. (@kenko911)
• Minor fix for model version for DIRECT model.

v0.8.1

• Fixed bug with loading of models trained with GPUs.
• Updated default model for relaxations to be the M3GNet-MP-2021.2.8-DIRECT-PES model.

v0.8.0

• Fix a bug with use of set2set in M3Gnet implementation that affected intensive models such as the formation energy
  model. M3GNet model version is updated to 2 to invalidate previous models. Note that PES models are unaffected.
  (@kenko911)

v0.7.1

• Minor optimizations for memory and isolated atom training (@kenko911)

v0.7.0

• MatGL now supports structures with isolated atoms. (@JiQi535)
• Fourier expansion layer and generalize cutoff polynomial. (@lbluque)
• Radial bessel (zeroth order bessel). (@lbluque)

v0.6.2

• Simple CLI tool mgl added.

v0.6.1

• Bug fix for training loss_fn.

v0.6.0

• Refactoring of training utilities. Added example for training an M3GNet potential.

v0.5.6

• Minor internal refactoring of basis expansions into _basis.py. (@lbluque)