class Preprocessing[source]

Preprocessing(preprocessing_type:str, name:str=None, normalize:bool=False)

A parent class for all data preprocessing strategies.

Type Default Details
preprocessing_type str The type of the preprocessing, which can either be "problem" or "solution". Problem preprocessing preprocesses the data based on problem information like forces etc., while solution preprocessing uses solution specific information like stresses, densities etc.
name str None The name of the preprocessing.
normalize bool False Whether to normalize the output of the preprocessing.

Preprocessing.__call__[source]

Preprocessing.__call__(problem_or_solution:Union[ForwardRef('dl4to.problem.Problem'), ForwardRef('dl4to.solution.Solution')])

Applies the preprocessing and returns a torch.Tensor object.

Type Default Details
problem_or_solution typing.Union[ForwardRef('dl4to.problem.Problem'), ForwardRef('dl4to.solution.Solution')] A problem or solution object.

Preprocessing.__add__[source]

Preprocessing.__add__(preprocessing:dl4to.preprocessing.Preprocessing)

Summation of two preprocessings results in a new combined preprocessing that concatenates the output of both. Returns a dl4to.preprocessing.CombinedPreprocessing object.

Type Default Details
preprocessing dl4to.preprocessing.Preprocessing The preprocessing that should be added to the current one.

class CombinedPreprocessing[source]

CombinedPreprocessing(preprocessing1:dl4to.preprocessing.Preprocessing, preprocessing2:dl4to.preprocessing.Preprocessing) :: Preprocessing

A class that results from the summation of two criteria.

Type Default Details
preprocessing1 dl4to.preprocessing.Preprocessing The first preprocessing.
preprocessing2 dl4to.preprocessing.Preprocessing The second preprocessing.