librascal
librascal copied to clipboard
lab-cosmo
A scalable and versatile library to generate representations for atomic-scale learning
Another discovery by @bananenpampe. The following code segfaults: ```py from rascal.representations import SphericalInvariants hypers = { "soap_type": "PowerSpectrum", "interaction_cutoff": 3, "radial_basis": "GTO", "max_radial": 0, "max_angular": 9, "gaussian_sigma_constant": 0.3, "gaussian_sigma_type": "Constant",...
Hello everyone, calling the SphericalCovariants function with covariant_lambda=0 results in a segmentation fault. ```Python #load some wrapped training structures hypers = {"soap_type": "LambdaSpectrum", "interaction_cutoff": 3, "radial_basis": "GTO", "max_radial": 9, "max_angular":...
Judging from the name and documentation of this function -- e.g. here: https://github.com/cosmo-epfl/librascal/blob/43a410c6d7cea3d17852e9c8c6fe332ec46f13df/bindings/rascal/representations/spherical_expansion.py#L236-L240 -- I would expect this function to also update the parameters of the underlying C++ object, so...
Hello everyone, I am computing the polynomial kernel between atomic environments using the rascal.models.kernel class ```python for structure in structures_train: mask_center_atoms_by_species(structure,species_select=[1]) calculator = SphericalInvariants(**hypers) atoms_list_train = calculator.transform(structures_train) kernel = Kernel(calculator,target_type="Atom",zeta=2)...
Hi, I installed the requirements using: sudo python3 -m pip install -r requirements.txt but when I try to install librascal using: sudo python3 -m pip install librascal I get the...
Improve the handling of input structures before passing them to the neighbor list. The neighbor list requires atoms to be in the unit cell so the atoms of periodic structures...
Implement an RKHS solver for the sparse GPR problem. Rationale and detailed description of the changes: Solving the GPR problem using the "normal" equation is very ill-conditioned. This implements an...
Plotting zundel.out: ``` axs[0].plot(time, (KE - KE[0]), linewidth = 1.5, label = r'$\Delta PE$') axs[0].plot(time, (PE - PE[0]), linewidth = 1.5, label = r'$\Delta KE$') ```
Running the code below prints `False`, but I would expect it to print `True`. ```py import ase from ase import build import numpy as np from rascal.representations import...
Building the latest master (db2e2445d34c196c94731249061740123f9fbc28) on macOS (with a small change to fix #378), I get a errors for this test: https://github.com/cosmo-epfl/librascal/blob/db2e2445d34c196c94731249061740123f9fbc28/tests/test_calculator.cc#L290-L357 ``` Running 37 test cases... /Users/guillaume/code/librascal/tests/test_calculator.cc:331: error: in...