phlower.settings.ModuleSetting

class phlower.settings.ModuleSetting(*, nn_type, name, input_keys=<factory>, output_key='', destinations=<factory>, no_grad=False, nn_parameters_same_as=None, nn_parameters=<factory>, coeff=1.0, debug_parameters=<factory>)[source]

Bases: IModuleSetting, BaseModel

Methods

get_destinations()

get_input_keys()

get_name()

get_output_info()

resolve(*resolved_outputs[, parent])

Attributes

model_computed_fields

model_config

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

model_extra

Get extra fields set during validation.

model_fields

model_fields_set

Returns the set of fields that have been explicitly set on this model instance.

nn_type

name of neural network type.

name

name of group

input_keys

key names of input variables

output_key

key names of output variables

destinations

name of destination modules.

no_grad

A Flag not to calculate gradient.

nn_parameters_same_as

name of another module to copy nn_parameters.

nn_parameters

parameters for neural networks.

coeff

coefficient to be applied to the module.

debug_parameters

parameters to debug networks.
Parameters:

  • nn_type (str)

  • name (str)

  • input_keys (list[str])

  • output_key (str)

  • destinations (list[str])

  • no_grad (bool)

  • nn_parameters_same_as (str | None)

  • nn_parameters (Annotated[IPhlowerLayerParameters | dict, PlainValidator(func=~phlower.settings._module_parameter_setting._validate, json_schema_input_type=~typing.Any), PlainSerializer(func=~phlower.settings._module_parameter_setting._serialize, return_type=PydanticUndefined, when_used=always)])

  • coeff (float)

  • debug_parameters (PhlowerModuleDebugParameters)

coeff: float

coefficient to be applied to the module.

debug_parameters: PhlowerModuleDebugParameters

parameters to debug networks.

destinations: list[str]

name of destination modules.

input_keys: list[str]

key names of input variables

model_config: ClassVar[ConfigDict] = {'arbitrary_types_allowed': True, 'extra': 'forbid', 'validate_assignment': True}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

name: str

name of group

nn_parameters: PhlowerModuleParameters

parameters for neural networks. Allowed items depend on nn_type.

nn_parameters_same_as: str | None

name of another module to copy nn_parameters.

nn_type: str

name of neural network type. For example, GCN, MLP.

no_grad: bool

A Flag not to calculate gradient. Defauls to False.

output_key: str

key names of output variables