Open
Conversation
Removes code repetitions that are in the alchemical and nonalchemical part of the code
Refactor alchemical code and adding doc plus doctest
Remove redundant r_cut hyper for VectorExpansion
We will change the dtypes of torch tensors to the default type which is usually 32 bit. To ignore the accuracy loss of the tests, we change equal to allclose
* change forward signature to a Dict[str, torch.Tensor] because torch does not support non torch Tensor types for compiling * the conversion from ase.Atoms to Dict[str, torch.Tensor] is done within a function outside of SphericalExpansion because TorchScript does not support foreign types * atomic_species is now flattened tensor to consider structures of different size * add typing for various inputs
* this corresponds to the bugfix lab-cosmo/sphericart#64
* the equistore version was pinned with the wrong character which resulted in usage of most recent version when installing
* add asserts to the allclose statements that got lost * set combination matrix in computation of alchemical spherical expansion because seed cannot recreate the reference combination matrix
* ase.neighborlist can have different order on different systems for unknown reasons so we need to sort the output according to the metadata before comparing
Fix various issues with the tests
* the artificial dataset covers cases - perodic images - noncubic lattice parameters - heterogeneous distribution of species - heterogeneous distribution of structure size - heterogeneous distribution of lattice parameters * test have been added for multiple frames using artiifical dataset
* to reduce the number of neighbors we increased the cell size * to also include higher l channels than 0 and 1 we increased the E_max parameter
agoscinski
force-pushed
the
forward-api
branch
2 times, most recently
from
95289c1 to
514db1d
Compare
* Spherical and VectorExpansion now accepts direction vectors and corresponding metainformation * created temporary dateset and dataloader for creation of neighborlist * test_finite_differences is now using artificial dataset
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
No description provided.