phlower.nn.Einsum

class phlower.nn.Einsum(activation, equation, **kwards)

Bases: IPhlowerCoreModule, Module

Einsum is a neural network module that performs a einsum operation on the input tensors.

Parameters:

• activation (str) – Name of the activation function to apply to the output.

• equation (str) – Equation of the einsum operation.

Examples

>>> einsum = Einsum(activation="relu", equation="ij,jk->ik")
>>> einsum(data)

Methods

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

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 Einsum from setting object

Parameters:

setting (EinsumSetting) – setting object

Returns:

Einsum

Return type:

Self

classmethod get_nn_name()

Return name of Einsum

Returns:

name

Return type:

str