Namespace AiDotNet.LearningRateSchedulers

Classes

ConstantLRScheduler

Maintains a constant learning rate throughout training.

CosineAnnealingLRScheduler

Sets the learning rate using a cosine annealing schedule.

CosineAnnealingWarmRestartsScheduler

Sets the learning rate using cosine annealing with warm restarts.

CyclicLRScheduler

Implements cyclical learning rate policy.

ExponentialLRScheduler

Decays the learning rate exponentially every step.

LambdaLRScheduler

Sets the learning rate using a user-defined lambda function.

LearningRateSchedulerBase

Base class for learning rate schedulers providing common functionality.

LearningRateSchedulerFactory

Factory for creating learning rate schedulers with common configurations.

LinearWarmupScheduler

Implements linear learning rate warmup followed by constant or decay schedule.

MultiStepLRScheduler

Decays the learning rate by gamma at each milestone step.

OneCycleLRScheduler

Implements the 1cycle learning rate policy.

PolynomialLRScheduler

Decays the learning rate using a polynomial function.

ReduceOnPlateauScheduler

Reduces learning rate when a metric has stopped improving.

SequentialLRScheduler

Chains multiple learning rate schedulers together in sequence.

StepLRScheduler

Decays the learning rate by a factor (gamma) every specified number of steps.

Interfaces

ILearningRateScheduler

Interface for learning rate schedulers that adjust the learning rate during training.

Enums

CyclicLRScheduler.CyclicMode

Mode for cyclic learning rate.

LearningRateSchedulerType

Enumeration of available learning rate scheduler types.

LinearWarmupScheduler.DecayMode

Decay mode after warmup phase.

OneCycleLRScheduler.AnnealingStrategy

Annealing strategy for the decay phase.

ReduceOnPlateauScheduler.Mode

Optimization mode.

ReduceOnPlateauScheduler.ThresholdMode

Threshold comparison mode.

SchedulerStepMode

Specifies when the learning rate scheduler should be stepped during training.