View source on GitHub |
Optimizer that implements the Adafactor algorithm.
Inherits From: Optimizer
tf.keras.optimizers.Adafactor(
learning_rate=0.001,
beta_2_decay=-0.8,
epsilon_1=1e-30,
epsilon_2=0.001,
clip_threshold=1.0,
relative_step=True,
weight_decay=None,
clipnorm=None,
clipvalue=None,
global_clipnorm=None,
use_ema=False,
ema_momentum=0.99,
ema_overwrite_frequency=None,
jit_compile=True,
name='Adafactor',
**kwargs
)
Adafactor is commonly used in NLP tasks, and has the advantage of taking less memory because it only saves partial information of previous gradients.
The default argument setup is based on the original paper (see reference). When gradients are of dimension > 2, Adafactor optimizer will delete the last 2 dimensions separately in its accumulator variables.
Args | |
---|---|
learning_rate: Initial value for the learning rate:
either a floating point value,
or a tf.keras.optimizers.schedules.LearningRateSchedule instance.
Defaults to 0.001.
beta_2_decay: float, defaults to -0.8. The decay rate of beta_2 .
epsilon_1: float, defaults to 1e-30. A small offset to keep denominator
away from 0.
epsilon_2: float, defaults to 1e-3. A small offset to avoid learning
rate becoming too small by time.
clip_threshold: float, defaults to 1.0. Clipping threshold. This is a
part of Adafactor algorithm, independent from clipnorm ,
clipvalue and global_clipnorm .
relative_step: bool, defaults to True. If learning_rate is a
constant and relative_step=True , learning rate will be adjusted
based on current iterations. This is a default learning rate decay
in Adafactor.
|
|
name
|
String. The name to use for momentum accumulator weights created by the optimizer. |
weight_decay
|
Float, defaults to None. If set, weight decay is applied. |
clipnorm
|
Float. If set, the gradient of each weight is individually clipped so that its norm is no higher than this value. |
clipvalue
|
Float. If set, the gradient of each weight is clipped to be no higher than this value. |
global_clipnorm
|
Float. If set, the gradient of all weights is clipped so that their global norm is no higher than this value. |
use_ema
|
Boolean, defaults to False. If True, exponential moving average (EMA) is applied. EMA consists of computing an exponential moving average of the weights of the model (as the weight values change after each training batch), and periodically overwriting the weights with their moving average. |
ema_momentum
|
Float, defaults to 0.99. Only used if use_ema=True .
This is the momentum to use when computing
the EMA of the model's weights:
new_average = ema_momentum * old_average + (1 - ema_momentum) *
current_variable_value .
|
ema_overwrite_frequency
|
Int or None, defaults to None. Only used if
use_ema=True . Every ema_overwrite_frequency steps of iterations,
we overwrite the model variable by its moving average.
If None, the optimizer
does not overwrite model variables in the middle of training, and you
need to explicitly overwrite the variables at the end of training
by calling optimizer.finalize_variable_values()
(which updates the model
variables in-place). When using the built-in fit() training loop,
this happens automatically after the last epoch,
and you don't need to do anything.
|
jit_compile
|
Boolean, defaults to True. If True, the optimizer will use XLA compilation. If no GPU device is found, this flag will be ignored. |
mesh
|
optional tf.experimental.dtensor.Mesh instance. When provided,
the optimizer will be run in DTensor mode, e.g. state
tracking variable will be a DVariable, and aggregation/reduction will
happen in the global DTensor context.
|
**kwargs
|
keyword arguments only used for backward compatibility. |
Reference | |
---|---|
Methods
add_variable
add_variable(
shape, dtype=None, initializer='zeros', name=None
)
Create an optimizer variable.
Args | |
---|---|
shape
|
A list of integers, a tuple of integers, or a 1-D Tensor of type int32. Defaults to scalar if unspecified. |
dtype
|
The DType of the optimizer variable to be created. Defaults to
tf.keras.backend.floatx if unspecified.
|
initializer
|
string or callable. Initializer instance. |
name
|
The name of the optimizer variable to be created. |
Returns | |
---|---|
An optimizer variable, in the format of tf.Variable. |
build
build(
var_list
)
Initialize optimizer variables.
Adam optimizer has 3 types of variables: momentums, velocities and velocity_hat (only set when amsgrad is applied),
Args | |
---|---|
var_list
|
list of model variables to build Adam variables on. |
compute_gradients
compute_gradients(
loss, var_list, tape=None
)
Compute gradients of loss on trainable variables.
Args | |
---|---|
loss
|
Tensor or callable. If a callable, loss should take no
arguments and return the value to minimize.
|
var_list
|
list or tuple of Variable objects to update to minimize
loss , or a callable returning the list or tuple of Variable
objects. Use callable when the variable list would otherwise be
incomplete before minimize since the variables are created at the
first time loss is called.
|
tape
|
(Optional) tf.GradientTape . If loss is provided as a
Tensor , the tape that computed the loss must be provided.
|
Returns | |
---|---|
A list of (gradient, variable) pairs. Variable is always present, but
gradient can be None .
|
exclude_from_weight_decay
exclude_from_weight_decay(
var_list=None, var_names=None
)
Exclude variables from weight decay.
This method must be called before the optimizer's build
method is
called. You can set specific variables to exclude out, or set a list of
strings as the anchor words, if any of which appear in a variable's
name, then the variable is excluded.
Args | |
---|---|
var_list
|
A list of tf.Variable s to exclude from weight decay.
|
var_names
|
A list of strings. If any string in var_names appear
in the model variable's name, then this model variable is
excluded from weight decay. For example, var_names=['bias']
excludes all bias variables from weight decay.
|
finalize_variable_values
finalize_variable_values(
var_list
)
Set the final value of model's trainable variables.
Sometimes there are some extra steps before ending the variable updates, such as overriding the model variables with its average value.
Args | |
---|---|
var_list
|
list of model variables. |
from_config
@classmethod
from_config( config, custom_objects=None )
Creates an optimizer from its config.
This method is the reverse of get_config
, capable of instantiating the
same optimizer from the config dictionary.
Args | |
---|---|
config
|
A Python dictionary, typically the output of get_config. |
custom_objects
|
A Python dictionary mapping names to additional user-defined Python objects needed to recreate this optimizer. |
Returns | |
---|---|
An optimizer instance. |
get_config
get_config()
Returns the config of the optimizer.
An optimizer config is a Python dictionary (serializable) containing the configuration of an optimizer. The same optimizer can be reinstantiated later (without any saved state) from this configuration.
Subclass optimizer should override this method to include other hyperparameters.
Returns | |
---|---|
Python dictionary. |
load_own_variables
load_own_variables(
store
)
Set the state of this optimizer object.
minimize
minimize(
loss, var_list, tape=None
)
Minimize loss
by updating var_list
.
This method simply computes gradient using tf.GradientTape
and calls
apply_gradients()
. If you want to process the gradient before applying
then call tf.GradientTape
and apply_gradients()
explicitly instead
of using this function.
Args | |
---|---|
loss
|
Tensor or callable. If a callable, loss should take no
arguments and return the value to minimize.
|
var_list
|
list or tuple of Variable objects to update to minimize
loss , or a callable returning the list or tuple of Variable
objects. Use callable when the variable list would otherwise be
incomplete before minimize since the variables are created at the
first time loss is called.
|
tape
|
(Optional) tf.GradientTape .
|
Returns | |
---|---|
None |
save_own_variables
save_own_variables(
store
)
Get the state of this optimizer object.
set_weights
set_weights(
weights
)
Set the weights of the optimizer.
Args | |
---|---|
weights
|
a list of tf.Variable s or numpy arrays, the target values
of optimizer variables. It should have the same order as
self._variables .
|
update_step
update_step(
gradient, variable
)
Update step given gradient and the associated model variable.