CatLearn
CatLearn copied to clipboard
A machine learning environment for atomic-scale modeling in surface science and catalysis.
It seems that right now, when you create a mlneb object, it doesnt assign the calculator of the images to be the calculator passed in the ase_calc variable. On my...
Makes it compatible with ase 3.22 Parprint in the MLMin tutorial
In Ase 3.22, get_number_of_atoms() is deprecated. It is suggested, "if your atoms are distributed, use (and see) get_global_number_of_atoms()."
There seem to be again issues with ML-NEB convergence and the newer ASE 3.20 version.
Hi all, I have noticed that CatLearn includes both energy and forces in the training of a Gaussian process model, but only predicts energy from the GP model. The predicted...
The ASE 3.19.1 MDMin Object needs self.nsteps reset so that the ml_opt object can do the optimization
I removed the indentation on line 300 or else the mlmin wont train a new point if the mlmin is stuck
There is a major bug in MLMIN when used with ASE 3.19. It behaves like previous NEB bug (if im not mistaken) The bug is: the iteration of geo_opt using...
I started building a conda-forge package: https://github.com/conda-forge/catlearn-feedstock And I was wondering if catlearn/api/magpie can be compiled from code as well, or maybe distributed as a separate package.
Predicting mean and covariance on a test set, X_test, scale N**2, because we are constructing K(X_test, X_test). In case X_test is large, we would prefer to not calculate the covariance...