-
Notifications
You must be signed in to change notification settings - Fork 275
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Misc ASE db bugfixes #965
Misc ASE db bugfixes #965
Conversation
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
lgtm thanks a lot @wolearyc! Just a minor question on the stress comment in the unit test
# There is a possible bug in ASE which makes this test annoying to write. | ||
# AtomsRow.toatoms() has a calculator attached that computes a stress tensor # with the wrong shape: (9,). This makes convert_all fail due to an assertion in | ||
# atoms.get_stress(). |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Where does this issue come up?
Is that here?
fairchem/src/fairchem/core/preprocessing/atoms_to_graphs.py
Lines 235 to 239 in bd93b2d
if self.r_stress: | |
stress = torch.tensor( | |
atoms.get_stress(apply_constraint=False, voigt=False), | |
dtype=torch.float32, | |
) |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Yup, precisely.
Codecov ReportAttention: Patch coverage is
|
* fixed bug in which row data was not fully copied during dataset split * fixed bug in which row data was not fully copied during dataset split Former-commit-id: 6289401e3e128c8018a7dc76cd12010d9d466310
* fixed bug in which row data was not fully copied during dataset split * fixed bug in which row data was not fully copied during dataset split Former-commit-id: 99f064a3d1b2e45842e136913e76e3427ed1f0ab
This PR addresses #962 as well as a related bug in which AtomsRow data was not fully copied during dataset splitting.