Bowen Deng
Bowen Deng
Thanks a lot! We appreciate your efforts. This will be very valuable to users familiar with lammps.
@advancesoftcorp Thanks again! I see the CHGNet driver file has a input argument for loading different CHGNet weights. `def chgnet_initialize(model_name = None, dftd3 = False, gpu = True):` Say, now...
@advancesoftcorp Currently `CHGNet.load()` method only supports loading the MPtrj pretrained CHGNet. When users load their own fine-tuned model, it's loaded through `CHGNet.from_file('weight_path')` If there can be an interface to load...
This looks great, thanks!
If I understand correctly, `custom_model` should be a CHGNet obejct loaded from user's weights. This doesn't seem to be a issue with CHGNet code? Is there anything that is suggested...
Hi @naik-aakash The calculator class is more foundamental while relaxer should be a downstream function class. Will `calculator = CHGNetCalculator.from_file()`, and `relaxer = StructureOptimizer(calculator`) work?
Just made the [commit](https://github.com/CederGroupHub/chgnet/commit/df560ce7e4fd8b198f671fc8dedbfc7ea28b450c) If this is not urgent, we will release it in the next release
> maybe @BowenD-UCB can chime on this test failure which oddly only happens on Windows? perhaps this signals that one of the `dtype` changes in `make_graph` is still platform dependent...
@ajhoffman1229 Can you please give some tests on the DFTD and SumCalculator and share a notebook example or open a PR? Happy to help and merge if the combined calculator...
Can you try update your pymatgen version?