tfm.optimization.DirectPowerDecay

Learning rate schedule follows lr * (step)^power.

tfm.optimization.DirectPowerDecay(
    initial_learning_rate: float,
    power: float = 1.0,
    name: str = 'DirectPowerDecay'
)

initial_learning_rate The initial learning rate.
power The order of the polynomial.
name Optional, name of learning rate schedule.

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()

Get the configuration of the learning rate schedule.

__call__

View source

__call__(
    step
)

Call self as a function.