Luthaf / rascaline

Computing representations for atomistic machine learning
https://luthaf.fr/rascaline/
BSD 3-Clause "New" or "Revised" License
44 stars 13 forks source link

Allow computing splines exactly at the largest point #174

Closed Luthaf closed 1 year ago

Luthaf commented 1 year ago

Fixes #173


:books: Documentation preview :books:: https://rascaline--174.org.readthedocs.build/en/174/

Luthaf commented 1 year ago

Such points should not be generated by the neighbor list, but we are checking the squared distance versus the squared cutoff, so I could see a difference. Since we do not always control the NL, it is better to accept point exactly on the cutoff in the spline evaluator.

github-actions[bot] commented 1 year ago

Here is a pre-built version of the code in this pull request: wheels.zip, you can install it locally by unzipping wheels.zip and using pip to install the file matching your system