phlower.nn.Residual¶

class phlower.nn.Residual(symbols_from_input, symbols_from_field, equation, nodes=None)[source]¶

Bases: IGenericPhlowerCoreModule[IPhlowerLayerParameters, PhlowerTensor], Module

Residual module computes the residual of a given equation based on the input data and field data.

Parameters:

symbols_from_inputs (list[str]) – List of symbols corresponding to the input data.
symbols_from_field (list[str]) – List of symbols corresponding to the field data.
equation (str) – The equation to compute the residual.
nodes (list[int], optional) – List of feature dimension sizes (The last value of tensor shape).
symbols_from_input (list[str])

Examples

>>> residual = Residual(
>>>     symbols_from_inputs=["x", "y"],
>>>     symbols_from_field=["c"],
>>>     equation="Diff(u, x) + Diff(u, y) - c",
>>> )
>>> residual(data, field_data)

Methods

`forward`(data, *[, field_data])	forward function which overloads torch.nn.Module
`from_setting`(setting)
`get_nn_name`()

Attributes

`T_destination`
`all_symbols`
`call_super_init`
`dump_patches`
`training`

forward(data, *, field_data=None, **kwards)[source]¶

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