View source on GitHub
|
Base class to make optimizers weight decay ready.
Classes
class AdamW: Optimizer that implements the Adam algorithm with weight decay.
class DecoupledWeightDecayExtension: This class allows to extend optimizers with decoupled weight decay.
class SGDW: Optimizer that implements the Momentum algorithm with weight_decay.
Functions
extend_with_decoupled_weight_decay(...): Factory function returning an optimizer class with decoupled weight
Type Aliases
FloatTensorLike: The central part of internal API.