deepmd.pt.model.model.transform_output

Module Contents

Functions

atomic_virial_corr(extended_coord, atom_energy)
task_deriv_one(atom_energy, energy, extended_coord[, ...])
get_leading_dims(vv, vdef)	Get the dimensions of nf x nloc.
get_atom_axis(vdef)	Get the axis of atoms.
take_deriv(vv, svv, vdef, coord_ext[, do_virial, ...])
fit_output_to_model_output(→ Dict[str, torch.Tensor])	Transform the output of the fitting network to
communicate_extended_output(→ Dict[str, torch.Tensor])	Transform the output of the model network defined on

deepmd.pt.model.model.transform_output.atomic_virial_corr(extended_coord: torch.Tensor, atom_energy: torch.Tensor)

deepmd.pt.model.model.transform_output.task_deriv_one(atom_energy: torch.Tensor, energy: torch.Tensor, extended_coord: torch.Tensor, do_virial: bool = True, do_atomic_virial: bool = False)

deepmd.pt.model.model.transform_output.get_leading_dims(vv: torch.Tensor, vdef: deepmd.dpmodel.OutputVariableDef)

Get the dimensions of nf x nloc.

deepmd.pt.model.model.transform_output.get_atom_axis(vdef: torch.Tensor)

Get the axis of atoms.

deepmd.pt.model.model.transform_output.take_deriv(vv: torch.Tensor, svv: torch.Tensor, vdef: deepmd.dpmodel.OutputVariableDef, coord_ext: torch.Tensor, do_virial: bool = False, do_atomic_virial: bool = False)

deepmd.pt.model.model.transform_output.fit_output_to_model_output(fit_ret: Dict[str, torch.Tensor], fit_output_def: deepmd.dpmodel.FittingOutputDef, coord_ext: torch.Tensor, do_atomic_virial: bool = False) → Dict[str, torch.Tensor]

Transform the output of the fitting network to the model output.

deepmd.pt.model.model.transform_output.communicate_extended_output(model_ret: Dict[str, torch.Tensor], model_output_def: deepmd.dpmodel.ModelOutputDef, mapping: torch.Tensor, do_atomic_virial: bool = False) → Dict[str, torch.Tensor]

Transform the output of the model network defined on local and ghost (extended) atoms to local atoms.