SupervisedProblem#

Formulation of a Supervised Problem in PINA.

class SupervisedProblem(input_, output_, input_variables=None, output_variables=None)[source]#

Bases: AbstractProblem

Definition of a supervised-learning problem.

This class provides a simple way to define a supervised problem using a single condition of type InputTargetCondition.

Example:
>>> import torch
>>> input_data = torch.rand((100, 10))
>>> output_data = torch.rand((100, 10))
>>> problem = SupervisedProblem(input_data, output_data)

Initialization of the SupervisedProblem class.

Parameters:

  • input (torch.Tensor | LabelTensor | Graph | Data) – Input data of the problem.

  • output (torch.Tensor | LabelTensor | Graph | Data) – Output data of the problem.

  • input_variables (list[str]) – List of names of the input variables. If None, the input variables are inferred from input_. Default is None.

  • output_variables (list[str]) – List of names of the output variables. If None, the output variables are inferred from output_. Default is None.

input_variables = None#
output_variables = None#