phlower.nn.MLP

class phlower.nn.MLP(nodes, activations=None, dropouts=None, bias=True)

Bases: IPhlowerCoreModule, Module

Multi Layer Perceptron

Parameters:

• nodes (list[int]) – List of feature dimension sizes (The last value of tensor shape).

• activations (list[str] | None (optional)) – List of activation functions to apply to the output. Defaults to None.

• dropouts (list[float] | None (optional)) – List of dropout rates to apply to the output. Defaults to None.

• bias (bool) – Whether to use bias.

Examples

>>> mlp = MLP(
...     nodes=[10, 20, 30],
...     activations=["relu", "relu", "relu"],
...     dropouts=[0.1, 0.1, 0.1],
...     bias=True
... )
>>> mlp(data)

Methods

forward(data, *[, field_data])	forward function which overloads torch.nn.Module
from_setting(setting)	Generate MLP from setting object
get_nn_name()	Return neural network name

Attributes

T_destination
call_super_init
dump_patches
training

forward(data, *, field_data=None, **kwards)

forward function which overloads torch.nn.Module

Parameters:

• data (IPhlowerTensorCollections) – IPhlowerTensorCollections data which receives from predecessors

• field_data (ISimulationField | None) – ISimulationField | None Constant information through training or prediction

Returns:

Tensor object

Return type:

PhlowerTensor

classmethod from_setting(setting)

Generate MLP from setting object

Parameters:

setting (MLPSetting) – setting object

Returns:

MLP object

Return type:

Self

classmethod get_nn_name()

Return neural network name

Returns:

name

Return type:

str