TorchUncertaintySampleRepresenter

class probly.integrations.torch_uncertainty.TorchUncertaintySampleRepresenter(predictor: Predictor[In, Out], kind: TorchUncertaintySampleKind = 'values')

Bases: Representer[Any, In, Out, Any], Generic[In, Out]

Representer for torch-uncertainty wrappers with batched estimator outputs.

Initialize the representer with a predictor.

Parameters:

predictor – The predictor to be used for building representations.

__call__(*args: In.args, **kwargs: In.kwargs) → R

Alias for the represent method.

predict(*args: In.args, **kwargs: In.kwargs) → R

Predict the representation for a given input.

predictor: Predictor[In, Out]

represent(*args: In.args, **kwargs: In.kwargs) → Any

Build a representation for a given input.