v0.2.2

Important Notes

v0.2.2 has a breaking change in model initialization from scratch i.e. chgnet = CHGNet(), to address #79.
The developer team is running another round of pretraining and the updated weights will be released in the next release.

For now, chgnet = CHGNet.load() loads same pretrained model as previous releases.
If user wants to load their own fine-tuned weights trained from previous releases, please do
chgnet = CHGNet.from_file("your_weights_path", mlp_out_bias=True)

What's Changed

• Run cibuildwheel on Apple silicon to publish pre-compiled macOS ARM binaries by @janosh in #78
• always report cov by @lbluque in #77
• 1.Dropped torch.det for MPS compatibility 2.better testing for rotation/supercell invariance by @BowenD-UCB in 4cee9e6
• Added function to output site energies by @BowenD-UCB in 77845dc
• Added examples for parsing DFT by @BowenD-UCB in 2ebc57f
• Fixed bug in #79, while not breaking loading pretrained weights by @BowenD-UCB in 1a558ea
• CHGNet now supports Apple MPS:tada:, pytorch-MPS has been tested with torch-2.0.1 by @BowenD-UCB in 516c422
• added num_isolated_atoms property by @BowenD-UCB in 20ebc58
• allow specifying decay fraction in CosineAnnealing LR scheduler by @BowenD-UCB in dbb0305
• Moved all torch.int64 to torch.int32 for MPS support by @BowenD-UCB in 828478a
• added notes to avoid Colab bug by @BowenD-UCB in a760ec8
• added installation from source by @BowenD-UCB in 030d897
• removed print message by @BowenD-UCB in 38a5cc4
• minor fix by @BowenD-UCB in 465f833
• fixed test by @BowenD-UCB in d5ba24b
• loosen numerical tolerance by @BowenD-UCB in b59d301
• added gMLP_norm option if gMLP is used at read_out by @BowenD-UCB in 195d48c

Full Changelog: v0.2.1...v0.2.2

v0.2.1

More Supports for MD: LAMMPS and ASE-MD ⚡

Main updates in this release:

1. Implemented support for Nose-Hoover thermostat with ASE MD, choice of thermostat is now an option. @BowenD-UCB @tsihyoung
2. MD and structure optimization now defaults to CUDA with most available memory. Device selection is mostly automatic now. @BowenD-UCB
3. MD now has option to generate hidden space features, allowing opportunity for post analysis. @AegisIK @BowenD-UCB
4. LAMMPS interface has been implemented, more tests to go. #57 @advancesoftcorp
5. NVE MD is implemented with ASE-MD. @BowenD-UCB
6. Isolated atom now defaults to warning in MD and relaxer (previously raised an error). Makes MD more stable @BowenD-UCB
7. VASP parser now checks electronic convergence at every ionic step. @BowenD-UCB
8. Updated paper reference and citation. @janosh
9. tests and minor bug-fix. @janosh @BowenD-UCB
10. Publish pre-compiled wheels for all platforms to PyPI. @janosh

New Contributors

• @tsihyoung
• @advancesoftcorp

Full Changelog: v0.2.0...v0.2.1

v0.2.0

CHGNet is much faster now 🚀 🚀 🚀

Main updates in this release:

1. Implement fast Cython graph converter in #40 by @AegisIK, yielding a 2 - 3x speed up in graph conversion depending on system size. Molecular dynamics now runs 1.5 - 2 x faster as well!

2. CHGNet API docs went live at https://chgnet.lbl.gov 🎉 in #39 by @janosh

3. Better tests and docstrings by @BowenD-UCB

All PRs since previous release

• API Docs by @janosh in #39
• Fix ValueError: ndarray is not C-contiguous CI errors by @janosh in #41
• 2.4x avg speedup on PMG struct to CHGNET graph conversion by @AegisIK in #40
• More descriptive names for single-letter variables by @janosh in #42
• Fix ruff PERF203 + PERF401 violations by @janosh in #43
• FIXED MEMORY LEAK in fast graph converter. Also cleaned up unneeded code. by @AegisIK in #44
• Add CHGNet.todict method needed for ASE JSON serialization by @janosh in #49
• Added garbage collection cyclic references turnoff for fast graph converter by @AegisIK in #50
• Solved final memory leak in fast converter by @AegisIK in #51
• Use MaterialsProject2020Compatibility to correct final energy in fine_tuning.ipynb by @janosh in #46

New Contributors

• @AegisIK made their first contribution in #40

Full Changelog: v0.1.04...v0.2.0

v0.1.4

This release mainly cleans up the code (e.g. Graph creation) and adds docstrings. It also introduces a function to parse VASP outputs for training CHGNet.

Minor bug fixes:

1. CHGNet detault initialization now matches pretrained model
2. energy_loss_ratio now functions correctly
3. GraphData now functions correctly

What's Changed

• More ruff by @janosh in #31
• Fix arg-type annotations missing None by @janosh in #33
• Use PyPI trusted publishing in CI release job by @janosh in #36
• Drop jupyter-dash and update CTK relax viewer by @janosh in #37

Full Changelog: v0.1.03...v0.1.04

v0.1.2

The first published PyPI version. 🚀 📦

What's Changed

• Fix markdown in examples/fine_tuning.ipynb by @janosh in #26
• Notebook tweaks by @janosh in #27
• coverage reporting by @lbluque in #28
• Publish to PyPI by @janosh in #29

Full Changelog: v0.1.01...v0.1.02

v0.1.1

What's Changed

• Add kwarg on_isolated_atoms: ignore | warn | error = error to CrystalGraphConverter.forward() by @janosh in #1
• ruff + pre-commit by @janosh in #2
• Report CHGNet device by @janosh in #3
• Tests by @janosh in #4
• Style, docstring and minor edits by @lbluque in #5
• Refactor package setup by @janosh in #6
• Use future type annotations by @janosh in #7
• Packaging with pyproject.toml only by @lbluque in #8
• Test CHGNet keyword combinations by @janosh in #9
• Add test for predict_structure() by @janosh in #11
• cleanup graph classes by @lbluque in #12
• Add test_graph.py by @janosh in #13
• Crystaltoolkit Relaxation Viewer by @janosh in #14
• Relax viewer show dft energy by @janosh in #15
• Plot force in Crystal Toolkit relaxation viewer by @janosh in #16
• StructureData types and docs by @janosh in #17
• Fix use_device not set correctly by @janosh in #18
• Add readme table with "Open in Colab" badges for example notebooks by @janosh in #19
• Add cell that installs CHGNet on Colab to example notebooks by @janosh in #20
• Fix typo in filename tests/test_(crytalgraph -> crystal_graph).py by @janosh in #21
• Use urllib to read example structure from GitHub raw URL if local file not found by @janosh in #22
• Add tests/test_encoders.py by @janosh in #23
• Add tests/test_converter.py by @janosh in #24

Full Changelog: v0.0.01...v0.1.01

initial release

Initial release of CHGNet with the pre-trained weights.

Full Changelog: https://github.com/CederGroupHub/chgnet/commits/v0.0.01-beta