deepmd.dpmodel.model.transform_output

deepmd.dpmodel.model.transform_output#

`fit_output_to_model_output`(→ dict[str, numpy.ndarray])	Transform the output of the fitting network to
`get_leading_dims`(vv, vdef)	Get the dimensions of nf x nloc.
`communicate_extended_output`(→ dict[str, numpy.ndarray])	Transform the output of the model network defined on

deepmd.dpmodel.model.transform_output.fit_output_to_model_output(fit_ret: dict[str, numpy.ndarray], fit_output_def: deepmd.dpmodel.output_def.FittingOutputDef, coord_ext: numpy.ndarray, do_atomic_virial: bool = False) → dict[str, numpy.ndarray][source]#: Transform the output of the fitting network to the model output.

deepmd.dpmodel.model.transform_output.get_leading_dims(vv: numpy.ndarray, vdef: deepmd.dpmodel.output_def.OutputVariableDef)[source]#

Get the dimensions of nf x nloc.

Parameters:

vvnp.ndarray: The input array from which to compute the leading dimensions.
vdefOutputVariableDef: The output variable definition containing the shape to exclude from vv.

Returns:

list: A list of leading dimensions of vv, excluding the last len(vdef.shape) dimensions.

deepmd.dpmodel.model.transform_output.communicate_extended_output(model_ret: dict[str, numpy.ndarray], model_output_def: deepmd.dpmodel.output_def.ModelOutputDef, mapping: numpy.ndarray, do_atomic_virial: bool = False) → dict[str, numpy.ndarray][source]#: Transform the output of the model network defined on local and ghost (extended) atoms to local atoms.