deepmd.tf.infer

Submodule containing all the implemented potentials.

Submodules

• deepmd.tf.infer.deep_dipole
• deepmd.tf.infer.deep_dos
• deepmd.tf.infer.deep_eval
• deepmd.tf.infer.deep_polar
• deepmd.tf.infer.deep_pot
• deepmd.tf.infer.deep_tensor
• deepmd.tf.infer.deep_wfc
• deepmd.tf.infer.ewald_recp
• deepmd.tf.infer.model_devi

Classes

DeepEval	High-level Deep Evaluator interface.
DeepDipole	Deep dipole model.
DeepDOS	Deep density of states model.
DeepGlobalPolar	Old tensor models from v1, which has no gradient output.
DeepPolar	Deep polar model.
DeepPot	Potential energy model.
DeepWFC	Deep WFC model.
EwaldRecp	Evaluate the reciprocal part of the Ewald sum.

Functions

DeepPotential(→ deep_eval.DeepEval)	Factory function that forwards to DeepEval (for compatibility).
calc_model_devi(coord, box, atype, models[, fname, ...])	Python interface to calculate model deviation.

Package Contents

deepmd.tf.infer.DeepPotential(*args, **kwargs) → deep_eval.DeepEval

Factory function that forwards to DeepEval (for compatibility).

Parameters:

*args

positional arguments

**kwargs

keyword arguments

Returns:

DeepEval

potentials

class deepmd.tf.infer.DeepEval(model_file: str, *args: Any, auto_batch_size: bool | int | deepmd.utils.batch_size.AutoBatchSize = True, neighbor_list: ase.neighborlist.NewPrimitiveNeighborList | None = None, **kwargs: Any)

Bases: abc.ABC

High-level Deep Evaluator interface.

The specific DeepEval, such as DeepPot and DeepTensor, should inherit from this class. This class provides a high-level interface on the top of the low-level interface.

Parameters:

model_filePath

The name of the frozen model file.

*argslist

Positional arguments.

auto_batch_sizebool or int or AutoBatchSize, default: True

If True, automatic batch size will be used. If int, it will be used as the initial batch size.

neighbor_listase.neighborlist.NewPrimitiveNeighborList, optional

The ASE neighbor list class to produce the neighbor list. If None, the neighbor list will be built natively in the model.

**kwargsdict

Keyword arguments.

deep_eval

property output_def: deepmd.dpmodel.output_def.ModelOutputDef

Abstractmethod:

Returns the output variable definitions.

get_rcut() → float

Get the cutoff radius of this model.

get_ntypes() → int

Get the number of atom types of this model.

get_type_map() → list[str]

Get the type map (element name of the atom types) of this model.

get_dim_fparam() → int

Get the number (dimension) of frame parameters of this DP.

get_dim_aparam() → int

Get the number (dimension) of atomic parameters of this DP.

_get_natoms_and_nframes(coords: numpy.ndarray, atom_types: numpy.ndarray, mixed_type: bool = False) → tuple[int, int]

_expande_atype(atype: numpy.ndarray, nframes: int, mixed_type: bool)

eval_descriptor(coords: numpy.ndarray, cells: numpy.ndarray | None, atom_types: numpy.ndarray, fparam: numpy.ndarray | None = None, aparam: numpy.ndarray | None = None, mixed_type: bool = False, **kwargs: Any) → numpy.ndarray

Evaluate descriptors by using this DP.

Parameters:

coords

The coordinates of atoms. The array should be of size nframes x natoms x 3

cells

The cell of the region. If None then non-PBC is assumed, otherwise using PBC. The array should be of size nframes x 9

atom_types

The atom types The list should contain natoms ints

fparam

The frame parameter. The array can be of size : - nframes x dim_fparam. - dim_fparam. Then all frames are assumed to be provided with the same fparam.

aparam

The atomic parameter The array can be of size : - nframes x natoms x dim_aparam. - natoms x dim_aparam. Then all frames are assumed to be provided with the same aparam. - dim_aparam. Then all frames and atoms are provided with the same aparam.

efield

The external field on atoms. The array should be of size nframes x natoms x 3

mixed_type

Whether to perform the mixed_type mode. If True, the input data has the mixed_type format (see doc/model/train_se_atten.md), in which frames in a system may have different natoms_vec(s), with the same nloc.

Returns:

descriptor

Descriptors.

eval_typeebd() → numpy.ndarray

Evaluate output of type embedding network by using this model.

Returns:

np.ndarray

The output of type embedding network. The shape is [ntypes, o_size], where ntypes is the number of types, and o_size is the number of nodes in the output layer.

Raises:

KeyError

If the model does not enable type embedding.

See also

deepmd.tf.utils.type_embed.TypeEmbedNet

The type embedding network.

Examples

Get the output of type embedding network of graph.pb:

>>> from deepmd.infer import DeepPotential
>>> dp = DeepPotential("graph.pb")
>>> dp.eval_typeebd()

_standard_input(coords, cells, atom_types, fparam, aparam, mixed_type)

get_sel_type() → list[int]

Get the selected atom types of this model.

Only atoms with selected atom types have atomic contribution to the result of the model. If returning an empty list, all atom types are selected.

_get_sel_natoms(atype) → int

property has_efield: bool

Check if the model has efield.

property has_spin: bool

Check if the model has spin.

property has_hessian: bool

Check if the model has hessian.

get_ntypes_spin() → int

Get the number of spin atom types of this model. Only used in old implement.

get_model_def_script() → dict

Get model definition script.

get_model_size() → dict

Get model parameter count.

class deepmd.tf.infer.DeepDipole(model_file: str, *args: Any, auto_batch_size: bool | int | deepmd.utils.batch_size.AutoBatchSize = True, neighbor_list: ase.neighborlist.NewPrimitiveNeighborList | None = None, **kwargs: Any)

Bases: deepmd.infer.deep_tensor.DeepTensor

Deep dipole model.

Parameters:

model_filePath

The name of the frozen model file.

*argslist

Positional arguments.

auto_batch_sizebool or int or AutoBatchSize, default: True

If True, automatic batch size will be used. If int, it will be used as the initial batch size.

neighbor_listase.neighborlist.NewPrimitiveNeighborList, optional

The ASE neighbor list class to produce the neighbor list. If None, the neighbor list will be built natively in the model.

**kwargsdict

Keyword arguments.

property output_tensor_name: str

The name of the tensor.

class deepmd.tf.infer.DeepDOS(model_file: str, *args: Any, auto_batch_size: bool | int | deepmd.utils.batch_size.AutoBatchSize = True, neighbor_list: ase.neighborlist.NewPrimitiveNeighborList | None = None, **kwargs: Any)

Bases: deepmd.infer.deep_eval.DeepEval

Deep density of states model.

Parameters:

model_filePath

The name of the frozen model file.

*argslist

Positional arguments.

auto_batch_sizebool or int or AutoBatchSize, default: True

If True, automatic batch size will be used. If int, it will be used as the initial batch size.

neighbor_listase.neighborlist.NewPrimitiveNeighborList, optional

The ASE neighbor list class to produce the neighbor list. If None, the neighbor list will be built natively in the model.

**kwargsdict

Keyword arguments.

property output_def: deepmd.dpmodel.output_def.ModelOutputDef

Get the output definition of this model.

property numb_dos: int

Get the number of DOS.

eval(coords: numpy.ndarray, cells: numpy.ndarray | None, atom_types: list[int] | numpy.ndarray, atomic: bool = False, fparam: numpy.ndarray | None = None, aparam: numpy.ndarray | None = None, mixed_type: bool = False, **kwargs: Any) → tuple[numpy.ndarray, Ellipsis]

Evaluate energy, force, and virial. If atomic is True, also return atomic energy and atomic virial.

Parameters:

coordsnp.ndarray

The coordinates of the atoms, in shape (nframes, natoms, 3).

cellsnp.ndarray

The cell vectors of the system, in shape (nframes, 9). If the system is not periodic, set it to None.

atom_typeslist[int] or np.ndarray

The types of the atoms. If mixed_type is False, the shape is (natoms,); otherwise, the shape is (nframes, natoms).

atomicbool, optional

Whether to return atomic energy and atomic virial, by default False.

fparamnp.ndarray, optional

The frame parameters, by default None.

aparamnp.ndarray, optional

The atomic parameters, by default None.

mixed_typebool, optional

Whether the atom_types is mixed type, by default False.

**kwargsdict[str, Any]

Keyword arguments.

Returns:

energy

The energy of the system, in shape (nframes,).

force

The force of the system, in shape (nframes, natoms, 3).

virial

The virial of the system, in shape (nframes, 9).

atomic_energy

The atomic energy of the system, in shape (nframes, natoms). Only returned when atomic is True.

atomic_virial

The atomic virial of the system, in shape (nframes, natoms, 9). Only returned when atomic is True.

get_numb_dos() → int

class deepmd.tf.infer.DeepGlobalPolar(model_file: str, *args: Any, auto_batch_size: bool | int | deepmd.utils.batch_size.AutoBatchSize = True, neighbor_list: ase.neighborlist.NewPrimitiveNeighborList | None = None, **kwargs: Any)

Bases: deepmd.infer.deep_tensor.OldDeepTensor

Old tensor models from v1, which has no gradient output.

property output_tensor_name: str

The name of the tensor.

eval(coords: numpy.ndarray, cells: numpy.ndarray | None, atom_types: list[int] | numpy.ndarray, atomic: bool = False, fparam: numpy.ndarray | None = None, aparam: numpy.ndarray | None = None, mixed_type: bool = False, **kwargs) → numpy.ndarray

Evaluate the model.

Parameters:

coords

The coordinates of atoms. The array should be of size nframes x natoms x 3

cells

The cell of the region. If None then non-PBC is assumed, otherwise using PBC. The array should be of size nframes x 9

atom_typeslist[int] or np.ndarray

The atom types The list should contain natoms ints

atomic

If True (default), return the atomic tensor Otherwise return the global tensor

fparam

Not used in this model

aparam

Not used in this model

mixed_type

Whether to perform the mixed_type mode. If True, the input data has the mixed_type format (see doc/model/train_se_atten.md), in which frames in a system may have different natoms_vec(s), with the same nloc.

Returns:

tensor

The returned tensor If atomic == False then of size nframes x output_dim else of size nframes x natoms x output_dim

property output_def: deepmd.dpmodel.output_def.ModelOutputDef

Get the output definition of this model.

class deepmd.tf.infer.DeepPolar(model_file: str, *args: Any, auto_batch_size: bool | int | deepmd.utils.batch_size.AutoBatchSize = True, neighbor_list: ase.neighborlist.NewPrimitiveNeighborList | None = None, **kwargs: Any)

Bases: deepmd.infer.deep_tensor.DeepTensor

Deep polar model.

Parameters:

model_filePath

The name of the frozen model file.

*argslist

Positional arguments.

auto_batch_sizebool or int or AutoBatchSize, default: True

If True, automatic batch size will be used. If int, it will be used as the initial batch size.

neighbor_listase.neighborlist.NewPrimitiveNeighborList, optional

The ASE neighbor list class to produce the neighbor list. If None, the neighbor list will be built natively in the model.

**kwargsdict

Keyword arguments.

property output_tensor_name: str

The name of the tensor.

class deepmd.tf.infer.DeepPot(model_file: str, *args: Any, auto_batch_size: bool | int | deepmd.utils.batch_size.AutoBatchSize = True, neighbor_list: ase.neighborlist.NewPrimitiveNeighborList | None = None, **kwargs: Any)

Bases: deepmd.infer.deep_eval.DeepEval

Potential energy model.

Parameters:

model_filePath

The name of the frozen model file.

*argslist

Positional arguments.

auto_batch_sizebool or int or AutoBatchSize, default: True

If True, automatic batch size will be used. If int, it will be used as the initial batch size.

neighbor_listase.neighborlist.NewPrimitiveNeighborList, optional

The ASE neighbor list class to produce the neighbor list. If None, the neighbor list will be built natively in the model.

**kwargsdict

Keyword arguments.

Examples

>>> from deepmd.infer import DeepPot
>>> import numpy as np
>>> dp = DeepPot("graph.pb")
>>> 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]
>>> e, f, v = dp.eval(coord, cell, atype)

where e, f and v are predicted energy, force and virial of the system, respectively.

property output_def: deepmd.dpmodel.output_def.ModelOutputDef

Get the output definition of this model.

property output_def_mag: deepmd.dpmodel.output_def.ModelOutputDef

Get the output definition of this model with magnetic parts.

eval(coords: numpy.ndarray, cells: numpy.ndarray | None, atom_types: list[int] | numpy.ndarray, atomic: Literal[True], fparam: numpy.ndarray | None, aparam: numpy.ndarray | None, mixed_type: bool, **kwargs: Any) → tuple[numpy.ndarray, numpy.ndarray, numpy.ndarray, numpy.ndarray, numpy.ndarray] | tuple[numpy.ndarray, numpy.ndarray, numpy.ndarray, numpy.ndarray, numpy.ndarray, numpy.ndarray]

eval(coords: numpy.ndarray, cells: numpy.ndarray | None, atom_types: list[int] | numpy.ndarray, atomic: Literal[False], fparam: numpy.ndarray | None, aparam: numpy.ndarray | None, mixed_type: bool, **kwargs: Any) → tuple[numpy.ndarray, numpy.ndarray, numpy.ndarray] | tuple[numpy.ndarray, numpy.ndarray, numpy.ndarray, numpy.ndarray]

eval(coords: numpy.ndarray, cells: numpy.ndarray | None, atom_types: list[int] | numpy.ndarray, atomic: bool, fparam: numpy.ndarray | None, aparam: numpy.ndarray | None, mixed_type: bool, **kwargs: Any) → tuple[numpy.ndarray, Ellipsis]

Evaluate energy, force, and virial. If atomic is True, also return atomic energy and atomic virial.

Parameters:

coordsnp.ndarray

The coordinates of the atoms, in shape (nframes, natoms, 3).

cellsnp.ndarray

The cell vectors of the system, in shape (nframes, 9). If the system is not periodic, set it to None.

atom_typeslist[int] or np.ndarray

The types of the atoms. If mixed_type is False, the shape is (natoms,); otherwise, the shape is (nframes, natoms).

atomicbool, optional

Whether to return atomic energy and atomic virial, by default False.

fparamnp.ndarray, optional

The frame parameters, by default None.

aparamnp.ndarray, optional

The atomic parameters, by default None.

mixed_typebool, optional

Whether the atom_types is mixed type, by default False.

**kwargsdict[str, Any]

Keyword arguments.

Returns:

energy

The energy of the system, in shape (nframes,).

force

The force of the system, in shape (nframes, natoms, 3).

virial

The virial of the system, in shape (nframes, 9).

atomic_energy

The atomic energy of the system, in shape (nframes, natoms). Only returned when atomic is True.

atomic_virial

The atomic virial of the system, in shape (nframes, natoms, 9). Only returned when atomic is True.

hessian

The Hessian matrix of the system, in shape (nframes, 3 * natoms, 3 * natoms). Returned when available.

class deepmd.tf.infer.DeepWFC(model_file: str, *args: Any, auto_batch_size: bool | int | deepmd.utils.batch_size.AutoBatchSize = True, neighbor_list: ase.neighborlist.NewPrimitiveNeighborList | None = None, **kwargs: Any)

Bases: deepmd.infer.deep_tensor.OldDeepTensor

Deep WFC model.

Parameters:

model_filePath

The name of the frozen model file.

*argslist

Positional arguments.

auto_batch_sizebool or int or AutoBatchSize, default: True

If True, automatic batch size will be used. If int, it will be used as the initial batch size.

neighbor_listase.neighborlist.NewPrimitiveNeighborList, optional

The ASE neighbor list class to produce the neighbor list. If None, the neighbor list will be built natively in the model.

**kwargsdict

Keyword arguments.

property output_tensor_name: str

The name of the tensor.

property output_def: deepmd.dpmodel.output_def.ModelOutputDef

Get the output definition of this model.

class deepmd.tf.infer.EwaldRecp(hh, beta)

Evaluate the reciprocal part of the Ewald sum.

hh

beta

sess

eval(coord: numpy.ndarray, charge: numpy.ndarray, box: numpy.ndarray) → tuple[numpy.ndarray, numpy.ndarray, numpy.ndarray]

Evaluate.

Parameters:

coord

The coordinates of atoms

charge

The atomic charge

box

The simulation region. PBC is assumed

Returns:

e

The energy

f

The force

v

The virial

deepmd.tf.infer.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)

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)