Prediction¶
- class mlip.typing.prediction.Prediction(energy: float | ndarray | None = None, forces: ndarray | None = None, stress: ndarray | None = None, stress_virial: ndarray | None = None, pressure: ndarray | None = None)¶
Holds data that is a prediction of an MLIP force field model.
As default, everything is
None, such that this class can be initialized with any property missing. Units will always be eV for energies and Angstrom for length.- energy¶
The energy or energies (if multiple graphs in a batch). Can be just a single float or array of shape
(n_graphs,).- Type:
float | numpy.ndarray | None
- forces¶
The forces. Will be of shape
(n_nodes, 3).- Type:
numpy.ndarray | None
- stress¶
The stress tensor. Will be of shape
(n_graphs, 3, 3).- Type:
numpy.ndarray | None
- stress_virial¶
The Virial stress. Will be of shape
(n_graphs, 3, 3).- Type:
numpy.ndarray | None
- pressure¶
The microsopic 0K pressure term. Will be of shape
(n_graphs,).- Type:
numpy.ndarray | None
Note
For more information on Virial stress and pressure computations, see de Miguel and Jackson, 2006. These features have not been thoroughly tested and should be viewed as experimental for now.