tfa.optimizers.ExponentialCyclicalLearningRate

Stay organized with collections Save and categorize content based on your preferences.

A LearningRateSchedule that uses cyclical schedule.

Inherits From: CyclicalLearningRate

tfa.optimizers.ExponentialCyclicalLearningRate(
    initial_learning_rate: Union[FloatTensorLike, Callable],
    maximal_learning_rate: Union[FloatTensorLike, Callable],
    step_size: tfa.types.FloatTensorLike,
    scale_mode: str = 'iterations',
    gamma: tfa.types.FloatTensorLike = 1.0,
    name: str = 'ExponentialCyclicalLearningRate'
)

initial_learning_rate A scalar float32 or float64 Tensor or a Python number. The initial learning rate.
maximal_learning_rate A scalar float32 or float64 Tensor or a Python number. The maximum learning rate.
step_size A scalar float32 or float64 Tensor or a Python number. Step size denotes the number of training iterations it takes to get to maximal_learning_rate
scale_mode ['cycle', 'iterations']. Mode to apply during cyclic schedule
gamma A scalar float32 or float64 Tensor or a Python number. Gamma value.
name (Optional) Name for the operation.

Methods

from_config

@classmethod
from_config(
    config
)

Instantiates a LearningRateSchedule from its config.

Args
config Output of get_config().

Returns
A LearningRateSchedule instance.

get_config

View source

get_config()

__call__

View source

__call__(
    step
)

Call self as a function.