phlower.nn.Contraction

class phlower.nn.Contraction(activation, nodes=None)

Bases: IPhlowerCoreModule, Module

Contraction is a neural network module that performs a contraction operation on the input tensor.

This module is designed to reduce the dimensionality of the input tensor by summing over specified dimensions.

Parameters:

• nodes (list[int] | None (optional)) – List of feature dimension sizes (The last value of tensor shape). Defaults to None.

• activation (str (optional)) – Name of the activation function to apply to the output. Defaults to “identity” (no activation).

Examples

>>> contraction = Contraction(activation="relu")
>>> contraction(data)

Methods

forward(data, *[, field_data])	forward function which overloads torch.nn.Module
from_setting(setting)	Create Contraction from setting object
get_nn_name()	Return name of Contraction

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)

Create Contraction from setting object

Parameters:

setting (ContractionSetting) – setting object

Returns:

Contraction

Return type:

Self

classmethod get_nn_name()

Return name of Contraction

Returns:

name

Return type:

str