Releases: materialsvirtuallab/matgl
Releases · materialsvirtuallab/matgl
v1.1.3
What's Changed
- Matgl depends on torch==2.2.1 by @Badasper in #273
- FrechetCellFilter is added for variable cell relaxation in Relaxer class by @kenko911 in #275
- Improve the TensorNet model class coverage by @kenko911 in #276
- Improve SO3Net model class coverage and simplify TensorNet implementation by @kenko911 in #277
- Improve the coverage in MLP_norm class by @kenko911 in #278
- Better Documentation for M3GNet potential training with stresses by @kenko911 in #281
- Improve the implementation of three-body interactions in M3GNet by @kenko911 in #282
- Optimize the speed of _compute_3body implementation by @kenko911 in #283
- Type checking for scheduler is added by @kenko911 in #284
- Update M3GNet potential training notebook for the demonstrating of obtaining and using element offset by @kenko911 in #288
- Smooth l1 loss function is added and the united tests are improved. by @kenko911 in #289
- Merge the predict_structure and featurize_structure into a single method by @kenko911 in #290
- Remove unnecessary else statement for calculating magmom loss by @kenko911 in #294
- Bump rexml from 3.2.8 to 3.3.2 in /docs by @dependabot in #297
- Bump rexml from 3.3.2 to 3.3.3 in /docs by @dependabot in #298
New Contributors
Full Changelog: v1.1.2...v1.1.3
Contributors
Badasper, dependabot, and kenko911
Assets 2
v1.1.2
v1.1.1
v1.1.0
v1.0.0
- First 1.0.0 release to reflect the maturity of the matgl code! All changes below are the efforts of @kenko911.
- Equivariant TensorNet and SO3Net are now implemented in MatGL.
- Refactoring of M3GNetCalculator and M3GNetDataset into generic PESCalculator and MGLDataset for use with all models
instead of just M3GNet. - Training framework has been unified for all models.
- ZBL repulsive potentials has been implemented.
Contributors
kenko911
Assets 2
v0.9.2
- Added Tensor Placement Calls For Ease of Training with PyTorch Lightning (@melo-gonzo).
- Allow extraction of intermediate outputs in "embedding", "gc_1", "gc_2", "gc_3", and "readout" layers for use as
atom, bond, and structure features. (@JiQi535)
Contributors
melo-gonzo and JiQi535
Assets 2
v0.9.1
v0.9.0
- set pbc_offsift and pos as float64 by @lbluque in #153
- Bump pytorch-lightning from 2.0.7 to 2.0.8 by @dependabot in #155
- add cpu() to avoid crash when using ase with GPU by @kenko911 in #156
- Added the united test for hessian in test_ase.py to improve the coverage score by @kenko911 in #157
- AtomRef Updates by @lbluque in #158
- Bump pymatgen from 2023.8.10 to 2023.9.2 by @dependabot in #160
- Remove torch.unique for finding the maximum three body index and little cleanup in united tests by @kenko911 in #161
- Bump pymatgen from 2023.9.2 to 2023.9.10 by @dependabot in #162
- Add united test for trainer.test and description in the example by @kenko911 in #165
- Bump pytorch-lightning from 2.0.8 to 2.0.9 by @dependabot in #167
- Sequence instead of list for inputs by @lbluque in #169
- Avoiding crashes for PES training without stresses and update pretrained models by @kenko911 in #168
- Bump pymatgen from 2023.9.10 to 2023.9.25 by @dependabot in #173
- Allow to choose distribution in xavier_init by @lbluque in #174
- An example for the simple training of M3GNet formation energy model is added by @kenko911 in #176
- Directed line graph by @lbluque in #178
- Bump pymatgen from 2023.9.25 to 2023.10.4 by @dependabot in #180
- Bump torch from 2.0.1 to 2.1.0 by @dependabot in #181
- Bump pymatgen from 2023.10.4 to 2023.10.11 by @dependabot in #183
- add testing to m3gnet potential training example by @lbluque in #179
- Update Training a MEGNet Formation Energy Model with PyTorch Lightnin… by @1152041831 in #185
- Bump pymatgen from 2023.10.11 to 2023.11.12 by @dependabot in #187
- dEdLat contribution for stress calculations is added and Universal Potentials are updated by @kenko911 in #189
- Bump torch from 2.1.0 to 2.1.1 by @dependabot in #190
Contributors
lbluque, dependabot, and 2 other contributors