deepmd.pt.loss

Submodules

Classes

`DenoiseLoss`	Helper class that provides a standard way to create an ABC using
`DOSLoss`	Helper class that provides a standard way to create an ABC using
`EnergyStdLoss`	Helper class that provides a standard way to create an ABC using
`EnergySpinLoss`	Helper class that provides a standard way to create an ABC using
`TaskLoss`	Helper class that provides a standard way to create an ABC using
`PropertyLoss`	Helper class that provides a standard way to create an ABC using
`TensorLoss`	Helper class that provides a standard way to create an ABC using

Package Contents

class deepmd.pt.loss.DenoiseLoss(ntypes, masked_token_loss=1.0, masked_coord_loss=1.0, norm_loss=0.01, use_l1=True, beta=1.0, mask_loss_coord=True, mask_loss_token=True, **kwargs)[source]

Bases: deepmd.pt.loss.loss.TaskLoss

Helper class that provides a standard way to create an ABC using inheritance.

ntypes

masked_token_loss

masked_coord_loss

norm_loss

has_coord

has_token

has_norm

use_l1

beta

frac_beta

mask_loss_coord

mask_loss_token

forward(model_pred, label, natoms, learning_rate, mae=False)[source]

Return loss on coord and type denoise.

Returns:

loss: Loss to minimize.

class deepmd.pt.loss.DOSLoss(starter_learning_rate: float, numb_dos: int, start_pref_dos: float = 1.0, limit_pref_dos: float = 1.0, start_pref_cdf: float = 1000, limit_pref_cdf: float = 1.0, start_pref_ados: float = 0.0, limit_pref_ados: float = 0.0, start_pref_acdf: float = 0.0, limit_pref_acdf: float = 0.0, inference=False, **kwargs)[source]

Bases: deepmd.pt.loss.loss.TaskLoss

Helper class that provides a standard way to create an ABC using inheritance.

starter_learning_rate

numb_dos

inference

start_pref_dos

limit_pref_dos

start_pref_cdf

limit_pref_cdf

start_pref_ados

limit_pref_ados

start_pref_acdf

limit_pref_acdf

has_dos

has_cdf

has_ados

has_acdf

forward(input_dict, model, label, natoms, learning_rate=0.0, mae=False)[source]

Return loss on local and global tensors.

Parameters:

input_dictdict[str, torch.Tensor]: Model inputs.
modeltorch.nn.Module: Model to be used to output the predictions.
labeldict[str, torch.Tensor]: Labels.
natomsint: The local atom number.

Returns:

model_pred: dict[str, torch.Tensor]: Model predictions.
loss: torch.Tensor: Loss for model to minimize.
more_loss: dict[str, torch.Tensor]: Other losses for display.

property label_requirement: List[deepmd.utils.data.DataRequirementItem]: Return data label requirements needed for this loss calculation.

class deepmd.pt.loss.EnergyStdLoss(starter_learning_rate=1.0, start_pref_e=0.0, limit_pref_e=0.0, start_pref_f=0.0, limit_pref_f=0.0, start_pref_v=0.0, limit_pref_v=0.0, start_pref_ae: float = 0.0, limit_pref_ae: float = 0.0, start_pref_pf: float = 0.0, limit_pref_pf: float = 0.0, relative_f: float | None = None, enable_atom_ener_coeff: bool = False, start_pref_gf: float = 0.0, limit_pref_gf: float = 0.0, numb_generalized_coord: int = 0, use_l1_all: bool = False, inference=False, **kwargs)[source]

Bases: deepmd.pt.loss.loss.TaskLoss

Helper class that provides a standard way to create an ABC using inheritance.

starter_learning_rate

has_e

has_f

has_v

has_ae

has_pf

has_gf

start_pref_e

limit_pref_e

start_pref_f

limit_pref_f

start_pref_v

limit_pref_v

start_pref_ae

limit_pref_ae

start_pref_pf

limit_pref_pf

start_pref_gf

limit_pref_gf

relative_f

enable_atom_ener_coeff

numb_generalized_coord

use_l1_all

inference

forward(input_dict, model, label, natoms, learning_rate, mae=False)[source]

Return loss on energy and force.

Parameters:

input_dictdict[str, torch.Tensor]: Model inputs.
modeltorch.nn.Module: Model to be used to output the predictions.
labeldict[str, torch.Tensor]: Labels.
natomsint: The local atom number.

Returns:

model_pred: dict[str, torch.Tensor]: Model predictions.
loss: torch.Tensor: Loss for model to minimize.
more_loss: dict[str, torch.Tensor]: Other losses for display.

property label_requirement: List[deepmd.utils.data.DataRequirementItem]: Return data label requirements needed for this loss calculation.

class deepmd.pt.loss.EnergySpinLoss(starter_learning_rate=1.0, start_pref_e=0.0, limit_pref_e=0.0, start_pref_fr=0.0, limit_pref_fr=0.0, start_pref_fm=0.0, limit_pref_fm=0.0, start_pref_v=0.0, limit_pref_v=0.0, start_pref_ae: float = 0.0, limit_pref_ae: float = 0.0, enable_atom_ener_coeff: bool = False, use_l1_all: bool = False, inference=False, **kwargs)[source]

Bases: deepmd.pt.loss.loss.TaskLoss

Helper class that provides a standard way to create an ABC using inheritance.

starter_learning_rate

has_e

has_fr

has_fm

has_v

has_ae

start_pref_e

limit_pref_e

start_pref_fr

limit_pref_fr

start_pref_fm

limit_pref_fm

start_pref_v

limit_pref_v

start_pref_ae

limit_pref_ae

enable_atom_ener_coeff

use_l1_all

inference

forward(input_dict, model, label, natoms, learning_rate, mae=False)[source]

Return energy loss with magnetic labels.

Parameters:

input_dictdict[str, torch.Tensor]: Model inputs.
modeltorch.nn.Module: Model to be used to output the predictions.
labeldict[str, torch.Tensor]: Labels.
natomsint: The local atom number.

Returns:

model_pred: dict[str, torch.Tensor]: Model predictions.
loss: torch.Tensor: Loss for model to minimize.
more_loss: dict[str, torch.Tensor]: Other losses for display.

property label_requirement: List[deepmd.utils.data.DataRequirementItem]: Return data label requirements needed for this loss calculation.

class deepmd.pt.loss.TaskLoss(**kwargs)[source]

Bases: torch.nn.Module, abc.ABC

Helper class that provides a standard way to create an ABC using inheritance.

abstract forward(input_dict, model, label, natoms, learning_rate)[source]: Return loss .

property label_requirement: List[deepmd.utils.data.DataRequirementItem]

Abstractmethod:

Return data label requirements needed for this loss calculation.

static display_if_exist(loss: torch.Tensor, find_property: float) → torch.Tensor[source]

Display NaN if labeled property is not found.

Parameters:

losstorch.Tensor: the loss tensor
find_propertyfloat: whether the property is found

class deepmd.pt.loss.PropertyLoss(task_dim, loss_func: str = 'smooth_mae', metric: list = ['mae'], beta: float = 1.0, **kwargs)[source]

Bases: deepmd.pt.loss.loss.TaskLoss

Helper class that provides a standard way to create an ABC using inheritance.

task_dim

loss_func

metric

beta

forward(input_dict, model, label, natoms, learning_rate=0.0, mae=False)[source]

Return loss on properties .

Parameters:

input_dictdict[str, torch.Tensor]: Model inputs.
modeltorch.nn.Module: Model to be used to output the predictions.
labeldict[str, torch.Tensor]: Labels.
natomsint: The local atom number.

Returns:

model_pred: dict[str, torch.Tensor]: Model predictions.
loss: torch.Tensor: Loss for model to minimize.
more_loss: dict[str, torch.Tensor]: Other losses for display.

property label_requirement: List[deepmd.utils.data.DataRequirementItem]: Return data label requirements needed for this loss calculation.

class deepmd.pt.loss.TensorLoss(tensor_name: str, tensor_size: int, label_name: str, pref_atomic: float = 0.0, pref: float = 0.0, inference=False, **kwargs)[source]

Bases: deepmd.pt.loss.loss.TaskLoss

Helper class that provides a standard way to create an ABC using inheritance.

tensor_name

tensor_size

label_name

local_weight

global_weight

inference

has_local_weight

has_global_weight

forward(input_dict, model, label, natoms, learning_rate=0.0, mae=False)[source]

Return loss on local and global tensors.

Parameters:

input_dictdict[str, torch.Tensor]: Model inputs.
modeltorch.nn.Module: Model to be used to output the predictions.
labeldict[str, torch.Tensor]: Labels.
natomsint: The local atom number.

Returns:

model_pred: dict[str, torch.Tensor]: Model predictions.
loss: torch.Tensor: Loss for model to minimize.
more_loss: dict[str, torch.Tensor]: Other losses for display.

property label_requirement: List[deepmd.utils.data.DataRequirementItem]: Return data label requirements needed for this loss calculation.