Data Condition#

Module for the Data Condition class.

class DataCondition(input, conditional_variables=None)[source]#

Bases: BaseCondition

The class DataCondition defines an unsupervised condition based on input data. This condition is typically used in data-driven problems, where the model is trained using a custom unsupervised loss determined by the chosen BaseSolver, while leveraging the provided data during training. Optional conditional_variables can be specified when the model depends on additional parameters.

Example:

>>> from pina import Condition, LabelTensor
>>> import torch

>>> pts = LabelTensor(torch.randn(100, 2), labels=["x", "y"])
>>> cond_vars = LabelTensor(torch.randn(100, 1), labels=["w"])
>>> condition = Condition(input=pts, conditional_variables=cond_vars)

Initialization of the BaseCondition class.

Parameters:: kwargs (dict) – The keyword arguments representing the data to be stored in the condition.

store_data(**kwargs)[source]#

Store the input data and the conditional variables in a dictionary-like structure.

Parameters:: kwargs (dict) – The keyword arguments containing the data to be stored.
Returns:: A dictionary-like structure containing the stored data.
Return type:: _DataManager

evaluate(batch, solver)[source]#

Evaluate the residual of the condition on the given batch using the solver.

This method computes the non-aggregated, element-wise residual of the condition. A forward pass of the solver’s model is performed on the input samples, and the condition residual is evaluated accordingly.

The returned tensor is not reduced, preserving the per-sample residual values.

Parameters:

batch (dict) – The batch containing the data required by the condition evaluation.
solver (BaseSolver) – The solver used to perform the forward pass and compute the residual. The solver provides access to the model and its parameters, which may be necessary for evaluating the condition residual.

Returns:

The non-aggregated residual tensor.

Return type:

torch.Tensor | LabelTensor

property conditional_variables#

The conditional variables associated with the condition.

Returns:: The conditional variables.
Return type:: torch.Tensor | LabelTensor | None

property input#

The input data associated with the condition.

Returns:: The input data.
Return type:: torch.Tensor | LabelTensor | Graph | Data | list[Graph] | list[Data] | tuple[Graph] | tuple[Data]