luthaf / alchemical-learning Goto Github PK
View Code? Open in Web Editor NEWLicense: BSD 3-Clause "New" or "Revised" License
License: BSD 3-Clause "New" or "Revised" License
This should be pretty similar to the AlchemicalCombine
module, operating on radial basis instead of species. Cross-optimization of both species and radial basis would come after that.
Currently the code takes a list of spherical expansion, where each element is the representation of a single structure. Since we want to use it for fixed-size structures anyway, it might not be too hard to move the structure index closer to the proposed TLMIQ storage. (currently, the code is using ILMTQ storage order).
Larger arrays should improve the overall performance.
When i try to open any of the tutorial notebooks, I receive the following errors:
train_dataset = AtomisticDataset(train_frames, all_species, HYPERS_SMALL, train_energies)
test_dataset = AtomisticDataset(test_frames, all_species, HYPERS_SMALL, test_energies)
argument of type 'NoneType' is not iterable
This happens in the "HEAs-with-forces.ipynb" and "alchemical-learning-elpasolites.ipynb" notebooks.
In the "HEA-singles" notebook i get a
train_dataset = AtomisticDataset(train_frames, all_species, HYPERS_SMALL, train_energies)
test_dataset = AtomisticDataset(test_frames, all_species, HYPERS_SMALL, test_energies)
Descriptor' object has no attribute 'keys_to_properties
And in the "HEAs-multi-body-order.ipynb" notebook it is:
rain_dataset = AtomisticDataset(train_frames, all_species,
{"radial_spectrum": HYPERS_RADIAL, "spherical_expansion":HYPERS_SMALL}, train_energies,
normalization = "automatic", do_gradients=False
)
train_normalization = { "radial_spectrum": train_dataset.radial_norm,
"spherical_expansion": train_dataset.spherical_expansion_norm}
train_forces_dataset = AtomisticDataset(train_forces_frames, all_species,
{"radial_spectrum": HYPERS_RADIAL, "spherical_expansion":HYPERS_SMALL}, train_forces_e,
normalization = train_normalization, do_gradients=False
)
test_dataset = AtomisticDataset(test_frames, all_species,
{"radial_spectrum": HYPERS_RADIAL, "spherical_expansion":HYPERS_SMALL}, test_energies,
normalization = train_normalization, do_gradients=False
)
SphericalExpansion.__init__() got an unexpected keyword argument 'center_atom_weight'
I have tried using both the newest equistore and rascaline versions and using the commits from the requirements file, no luck.
I am using a python 3.10.4 environment on an M1 mac.
A declarative, efficient, and flexible JavaScript library for building user interfaces.
๐ Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. ๐๐๐
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google โค๏ธ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.