phlower.nn.SPMM

class phlower.nn.SPMM(factor, support_name, transpose=False, **kwards)

Bases: Module, IPhlowerCoreModule

Sparse Matrix Multiplication Network

Parameters:

• factor (float) – Factor to multiply the support matrix.

• support_name (str) – Name of the support matrix.

• transpose (bool) – Whether to transpose the support matrix.

Examples

>>> spmm = SPMM(factor=1.0, support_name="support", transpose=False)
>>> spmm(data)

Methods

forward(data, *, field_data, **kwards)	forward function which overload torch.nn.Module
from_setting(setting)	Create SPMM from SPMMSetting instance
get_nn_name()	Return neural network name

Attributes

T_destination
call_super_init
dump_patches
training

forward(data, *, field_data, **kwards)

forward function which overload torch.nn.Module

Parameters:

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

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

Returns:

Tensor object

Return type:

PhlowerTensor

classmethod from_setting(setting)

Create SPMM from SPMMSetting instance

Parameters:

setting (SPMMSetting) – setting object for SPMM

Returns:

SPMM model

Return type:

SPMM

classmethod get_nn_name()

Return neural network name

Returns:

name

Return type:

str