deepmd.infer.model_devi

deepmd.infer.model_devi#

Functions#

`calc_model_devi_f`(…)	Calculate model deviation of force.
`calc_model_devi_e`(→ numpy.ndarray)	Calculate model deviation of total energy per atom.
`calc_model_devi_v`(→ tuple[numpy.ndarray, ...)	Calculate model deviation of virial.
`write_model_devi_out`(devi, fname[, header, atomic])	Write output of model deviation.
`_check_tmaps`(tmaps[, ref_tmap])	Check whether type maps are identical.
`calc_model_devi`(coord, box, atype, models[, fname, ...])	Python interface to calculate model deviation.
`make_model_devi`(*, models, system, output, frequency)	Make model deviation calculation.

Module Contents#

deepmd.infer.model_devi.calc_model_devi_f(fs: numpy.ndarray, real_f: numpy.ndarray | None = None, relative: float | None = None, atomic: Literal[False] = ...) → tuple[numpy.ndarray, numpy.ndarray, numpy.ndarray][source]#

deepmd.infer.model_devi.calc_model_devi_f(fs: numpy.ndarray, real_f: numpy.ndarray | None = None, relative: float | None = None, atomic: Literal[True] = ...) → tuple[numpy.ndarray, numpy.ndarray, numpy.ndarray, numpy.ndarray]

deepmd.infer.model_devi.calc_model_devi_f(fs: numpy.ndarray, real_f: numpy.ndarray | None = None, relative: float | None = None, atomic: bool = False) → tuple[numpy.ndarray, Ellipsis]

Calculate model deviation of force.

Parameters:

fsnumpy.ndarray: size of n_models x n_frames x n_atoms x 3
real_fnumpy.ndarray or None: real force, size of n_frames x n_atoms x 3. If given, the RMS real error is calculated instead.
relativefloat, default: None: If given, calculate the relative model deviation of force. The value is the level parameter for computing the relative model deviation of the force.
atomicbool, default: False: Whether return deviation of force in all atoms

Returns:

max_devi_fnumpy.ndarray: maximum deviation of force in all atoms
min_devi_fnumpy.ndarray: minimum deviation of force in all atoms
avg_devi_fnumpy.ndarray: average deviation of force in all atoms
fs_devinumpy.ndarray: deviation of force in all atoms, returned if atomic=True

deepmd.infer.model_devi.calc_model_devi_e(es: numpy.ndarray, real_e: numpy.ndarray | None = None) → numpy.ndarray[source]#

Calculate model deviation of total energy per atom.

Here we don’t use the atomic energy, as the decomposition of energy is arbitrary and not unique. There is no fitting target for atomic energy.

Parameters:

esnumpy.ndarray: size of `n_models x n_frames x 1
real_enumpy.ndarray: real energy, size of n_frames x 1. If given, the RMS real error is calculated instead.

Returns:

max_devi_enumpy.ndarray: maximum deviation of energy

deepmd.infer.model_devi.calc_model_devi_v(vs: numpy.ndarray, real_v: numpy.ndarray | None = None, relative: float | None = None) → tuple[numpy.ndarray, numpy.ndarray, numpy.ndarray][source]#

Calculate model deviation of virial.

Parameters:

vsnumpy.ndarray: size of n_models x n_frames x 9
real_vnumpy.ndarray: real virial, size of n_frames x 9. If given, the RMS real error is calculated instead.
relativefloat, default: None: If given, calculate the relative model deviation of virial. The value is the level parameter for computing the relative model deviation of the virial.

Returns:

max_devi_vnumpy.ndarray: maximum deviation of virial in 9 elements
min_devi_vnumpy.ndarray: minimum deviation of virial in 9 elements
avg_devi_vnumpy.ndarray: average deviation of virial in 9 elements

deepmd.infer.model_devi.write_model_devi_out(devi: numpy.ndarray, fname: str, header: str = '', atomic: bool = False)[source]#

Write output of model deviation.

Parameters:

devinumpy.ndarray: the first column is the steps index
fnamestr: the file name to dump
headerstr, default=””: the header to dump
atomicbool, default: False: whether atomic model deviation is printed

deepmd.infer.model_devi._check_tmaps(tmaps, ref_tmap=None)[source]#: Check whether type maps are identical.

deepmd.infer.model_devi.calc_model_devi(coord, box, atype, models, fname=None, frequency=1, mixed_type=False, fparam: numpy.ndarray | None = None, aparam: numpy.ndarray | None = None, real_data: dict | None = None, atomic: bool = False, relative: float | None = None, relative_v: float | None = None)[source]#

Python interface to calculate model deviation.

Parameters:

coordnumpy.ndarray, n_frames x n_atoms x 3: Coordinates of system to calculate
boxnumpy.ndarray or None, n_frames x 3 x 3: Box to specify periodic boundary condition. If None, no pbc will be used
atypenumpy.ndarray, n_atoms x 1: Atom types
modelslist of DeepPot models: Models used to evaluate deviation
fnamestr or None: File to dump results, default None
frequencyint: Steps between frames (if the system is given by molecular dynamics engine), default 1
mixed_typebool: Whether the input atype is in mixed_type format or not
fparamnumpy.ndarray: frame specific parameters
aparamnumpy.ndarray: atomic specific parameters
real_datadict, optional: real data to calculate RMS real error
atomicbool, default: False: If True, calculate the force model deviation of each atom.
relativefloat, default: None: If given, calculate the relative model deviation of force. The value is the level parameter for computing the relative model deviation of the force.
relative_vfloat, default: None: If given, calculate the relative model deviation of virial. The value is the level parameter for computing the relative model deviation of the virial.

Returns:

model_devinumpy.ndarray, n_frames x 8: Model deviation results. The first column is index of steps, the other 7 columns are max_devi_v, min_devi_v, avg_devi_v, max_devi_f, min_devi_f, avg_devi_f, devi_e.

Examples

>>> from deepmd.tf.infer import calc_model_devi
>>> from deepmd.tf.infer import DeepPot as DP
>>> import numpy as np
>>> coord = np.array([[1, 0, 0], [0, 0, 1.5], [1, 0, 3]]).reshape([1, -1])
>>> cell = np.diag(10 * np.ones(3)).reshape([1, -1])
>>> atype = [1, 0, 1]
>>> graphs = [DP("graph.000.pb"), DP("graph.001.pb")]
>>> model_devi = calc_model_devi(coord, cell, atype, graphs)

deepmd.infer.model_devi.make_model_devi(*, models: list, system: str, output: str, frequency: int, real_error: bool = False, atomic: bool = False, relative: float | None = None, relative_v: float | None = None, **kwargs)[source]#

Make model deviation calculation.

Parameters:

modelslist: A list of paths of models to use for making model deviation
systemstr: The path of system to make model deviation calculation
outputstr: The output file for model deviation results
frequencyint: The number of steps that elapse between writing coordinates in a trajectory by a MD engine (such as Gromacs / LAMMPS). This parameter is used to determine the index in the output file.
real_errorbool, default: False: If True, calculate the RMS real error instead of model deviation.
atomicbool, default: False: If True, calculate the force model deviation of each atom.
relativefloat, default: None: If given, calculate the relative model deviation of force. The value is the level parameter for computing the relative model deviation of the force.
relative_vfloat, default: None: If given, calculate the relative model deviation of virial. The value is the level parameter for computing the relative model deviation of the virial.
**kwargs: Arbitrary keyword arguments.