deepmd.pt.modifier

Submodules

• deepmd.pt.modifier.base_modifier

Classes

BaseModifier

Base class for data modifier.

Functions

get_data_modifier(→ base_modifier.BaseModifier)

Package Contents

class deepmd.pt.modifier.BaseModifier(use_cache: bool = True)

Bases: torch.nn.Module, make_base_modifier()

Base class for data modifier.

modifier_type = 'base'

jitable = True

use_cache = True

serialize() → dict

Serialize the modifier.

Returns:

dict

The serialized data

classmethod deserialize(data: dict) → BaseModifier

Deserialize the modifier.

Parameters:

datadict

The serialized data

Returns:

BaseModifier

The deserialized modifier

abstractmethod forward(coord: torch.Tensor, atype: torch.Tensor, box: torch.Tensor | None = None, fparam: torch.Tensor | None = None, aparam: torch.Tensor | None = None, do_atomic_virial: bool = False, charge_spin: torch.Tensor | None = None) → dict[str, torch.Tensor]

Compute energy, force, and virial corrections.

modify_data(data: dict[str, deepmd.dpmodel.array_api.Array | float], data_sys: deepmd.utils.data.DeepmdData) → None

Modify data of single frame.

Parameters:

data

Internal data of DeepmdData. Be a dict, has the following keys - coord coordinates (nat, 3) - box simulation box (9,) - atype atom types (nat,) - fparam frame parameter (nfp,) - aparam atom parameter (nat, nap) - find_energy tells if data has energy - find_force tells if data has force - find_virial tells if data has virial - energy energy (1,) - force force (nat, 3) - virial virial (9,)

deepmd.pt.modifier.get_data_modifier(_modifier_params: dict[str, Any]) → base_modifier.BaseModifier