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