openff.bespokefit.schema.fitting.OptimizationStageSchema
- model openff.bespokefit.schema.fitting.OptimizationStageSchema[source]
Bases:
SchemaBase,ABCA schema that encodes a single stage in a multi-stage optimization.
A common example may be one in which in the first stage a charge model is trained, followed by the valence parameters being trained, and finally the torsion parameters are trained.
- field optimizer: ForceBalanceSchema [Required]
The optimizer to use and its associated settings.
- field parameters: List[Union[VdWSMIRKS, BondSMIRKS, AngleSMIRKS, ProperTorsionSMIRKS, ImproperTorsionSMIRKS]] [Required]
A list of the specific force field parameters that should be optimized.
- field parameter_hyperparameters: List[Union[ProperTorsionHyperparameters, BondHyperparameters, AngleHyperparameters, VdWHyperparameters, ImproperTorsionHyperparameters]] [Required]
The hyperparameters that describe how classes of parameters, e.g. the force constant and length of a bond parameter, should be restrained during the optimisation such as through the inclusion of harmonic priors.
- field targets: List[Union[TorsionProfileTargetSchema, AbInitioTargetSchema, VibrationTargetSchema, OptGeoTargetSchema]] = []
The fittings targets to simultaneously optimize against.
- property n_targets: int
Returns the number of targets to be fit.