SingleSolverInterface

class SingleSolverInterface(problem, model, optimizer=None, scheduler=None, weighting=None, use_lt=True)

Bases: SolverInterface

Base class for PINA solvers using a single torch.nn.Module.

Initialization of the SingleSolverInterface class.

Parameters:

• problem (AbstractProblem) – The problem to be solved.

• model (torch.nn.Module) – The neural network model to be used.

• optimizer (Optimizer) – The optimizer to be used. If None, the torch.optim.Adam optimizer is used. Default is None.

• scheduler (Scheduler) – The scheduler to be used. If None, the torch.optim.lr_scheduler.ConstantLR scheduler is used. Default is None.

• weighting (WeightingInterface) – The weighting schema to be used. If None, no weighting schema is used. Default is None.

• use_lt (bool) – If True, the solver uses LabelTensors as input.

forward(x)

Forward pass implementation.

Parameters:

x (torch.Tensor | LabelTensor | Graph | Data) – Input tensor.

Returns:

Solver solution.

Return type:

torch.Tensor | LabelTensor | Graph | Data

configure_optimizers()

Optimizer configuration for the solver.

Returns:

The optimizer and the scheduler

Return type:

tuple[list[Optimizer], list[Scheduler]]

property model

The model used for training.

Returns:

The model used for training.

Return type:

torch.nn.Module

property scheduler

The scheduler used for training.

Returns:

The scheduler used for training.

Return type:

Scheduler

property optimizer

The optimizer used for training.

Returns:

The optimizer used for training.

Return type:

Optimizer