phlower.nn.NaNToNum

class phlower.nn.NaNToNum(nodes=None, nan=0.0, posinf=None, neginf=None)

Bases: Module, IGenericPhlowerCoreModule[IPhlowerLayerParameters, PhlowerTensor]

NaNToNum is a neural network module that replaces NaN and infinite values in the input tensor with specified numerical values.

Parameters:

• nan (float) – The value to replace NaN values with. Default is 0.0.

• posinf (float | None) – The value to replace positive infinity values with. Default is None, which means positive infinity values are not replaced.

• neginf (float | None) – The value to replace negative infinity values with. Default is None, which means negative infinity values are not replaced.

• nodes (list[int] | None)

Examples

>>> nan_to_num = NaNToNum(nan=0.0, posinf=1e6, neginf=-1e6)
>>> nan_to_num(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 (NaNToNumSetting) – setting object

Returns:

MLP object

Return type:

Self

classmethod get_nn_name()

Return neural network name

Returns:

name

Return type:

str