TensorFlow 1 version | View source on GitHub |
A LearningRateSchedule that uses a cosine decay schedule with restarts.
Inherits From: LearningRateSchedule
tf.keras.experimental.CosineDecayRestarts(
initial_learning_rate, first_decay_steps, t_mul=2.0, m_mul=1.0, alpha=0.0,
name=None
)
Args | |
---|---|
initial_learning_rate
|
A scalar float32 or float64 Tensor or a Python
number. The initial learning rate.
|
first_decay_steps
|
A scalar int32 or int64 Tensor or a Python
number. Number of steps to decay over.
|
t_mul
|
A scalar float32 or float64 Tensor or a Python number.
Used to derive the number of iterations in the i-th period
|
m_mul
|
A scalar float32 or float64 Tensor or a Python number.
Used to derive the initial learning rate of the i-th period:
|
alpha
|
A scalar float32 or float64 Tensor or a Python number.
Minimum learning rate value as a fraction of the initial_learning_rate.
|
name
|
String. Optional name of the operation. Defaults to 'SGDRDecay'. |
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
get_config()
__call__
__call__(
step
)
Call self as a function.