nip.parameters.types

Enum types for experiment parameters.

Used when a parameter can only take on a specific set of values.

Module Attributes

ScenarioType	Type for the scenario to run.
SpgVariantType	Type for SPG variants.
IhvpVariantType	Type for the variants of the inverse Hessian-vector product computation.
GuessType	Type for the possible guesses of the verifier in binary cases.
TrainerType	Type for the RL trainer to use.
TestSchemeType	Enum specifying on which iterations to test the model during training.
PpoLossType	Type for the PPO loss function to use.
BinarificationMethodType	Type for ways of turning a multi-class classification task into a binary one.
ActivationType	Type for the activation function to use.
InteractionProtocolType	Type for the interaction protocol to use in the environment.
ImageBuildingBlockType	Type for the type of building block to use in the image classification network.
MessageRegressionMethodType	Type for the method to use to do regression analysis on the messages.
BaseRunType	Enum for how to base the current experiment on a previous W&B run.