![]() |
Class Adam
Optimizer that implements the Adam algorithm.
Inherits From: Optimizer
Aliases:
- Class
tf.compat.v1.keras.optimizers.Adam
- Class
tf.compat.v2.keras.optimizers.Adam
- Class
tf.compat.v2.optimizers.Adam
Adam optimization is a stochastic gradient descent method that is based on adaptive estimation of first-order and second-order moments. According to the paper Adam: A Method for Stochastic Optimization. Kingma et al., 2014, the method is "computationally efficient, has little memory requirement, invariant to diagonal rescaling of gradients, and is well suited for problems that are large in terms of data/parameters".
For AMSGrad see On The Convergence Of Adam And Beyond. Reddi et al., 5-8.
__init__
__init__(
learning_rate=0.001,
beta_1=0.9,
beta_2=0.999,
epsilon=1e-07,
amsgrad=False,
name='Adam',
**kwargs
)
Construct a new Adam optimizer.
If amsgrad = False: Initialization:
The update rule for variable
with gradient g
uses an optimization
described at the end of section 2 of the paper:
If amsgrad = True: Initialization:
The update rule for variable
with gradient g
uses an optimization
described at the end of section 2 of the paper:
The default value of 1e-7 for epsilon might not be a good default in general. For example, when training an Inception network on ImageNet a current good choice is 1.0 or 0.1. Note that since AdamOptimizer uses the formulation just before Section 2.1 of the Kingma and Ba paper rather than the formulation in Algorithm 1, the "epsilon" referred to here is "epsilon hat" in the paper.
The sparse implementation of this algorithm (used when the gradient is an
IndexedSlices object, typically because of tf.gather
or an embedding
lookup in the forward pass) does apply momentum to variable slices even if
they were not used in the forward pass (meaning they have a gradient equal
to zero). Momentum decay (beta1) is also applied to the entire momentum
accumulator. This means that the sparse behavior is equivalent to the dense
behavior (in contrast to some momentum implementations which ignore momentum
unless a variable slice was actually used).
Args:
learning_rate
: A Tensor or a floating point value. The learning rate.beta_1
: A float value or a constant float tensor. The exponential decay rate for the 1st moment estimates.beta_2
: A float value or a constant float tensor. The exponential decay rate for the 2nd moment estimates.epsilon
: A small constant for numerical stability. This epsilon is "epsilon hat" in the Kingma and Ba paper (in the formula just before Section 2.1), not the epsilon in Algorithm 1 of the paper.amsgrad
: boolean. Whether to apply AMSGrad variant of this algorithm from the paper "On the Convergence of Adam and beyond".name
: Optional name for the operations created when applying gradients. Defaults to "Adam".**kwargs
: keyword arguments. Allowed to be {clipnorm
,clipvalue
,lr
,decay
}.clipnorm
is clip gradients by norm;clipvalue
is clip gradients by value,decay
is included for backward compatibility to allow time inverse decay of learning rate.lr
is included for backward compatibility, recommended to uselearning_rate
instead.
Eager Compatibility
When eager execution is enabled, learning_rate
, beta_1
, beta_2
,
and epsilon
can each be a callable that takes no arguments and
returns the actual value to use. This can be useful for changing these
values across different invocations of optimizer functions.
Properties
iterations
Variable. The number of training steps this Optimizer has run.
weights
Returns variables of this Optimizer based on the order created.
Methods
tf.keras.optimizers.Adam.add_slot
add_slot(
var,
slot_name,
initializer='zeros'
)
Add a new slot variable for var
.
tf.keras.optimizers.Adam.add_weight
add_weight(
name,
shape,
dtype=None,
initializer='zeros',
trainable=None,
synchronization=tf.VariableSynchronization.AUTO,
aggregation=tf.VariableAggregation.NONE
)
tf.keras.optimizers.Adam.apply_gradients
apply_gradients(
grads_and_vars,
name=None
)
Apply gradients to variables.
This is the second part of minimize()
. It returns an Operation
that
applies gradients.
Args:
grads_and_vars
: List of (gradient, variable) pairs.name
: Optional name for the returned operation. Default to the name passed to theOptimizer
constructor.
Returns:
An Operation
that applies the specified gradients. The iterations
will be automatically increased by 1.
Raises:
TypeError
: Ifgrads_and_vars
is malformed.ValueError
: If none of the variables have gradients.
tf.keras.optimizers.Adam.from_config
from_config(
cls,
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.
Arguments:
config
: A Python dictionary, typically the output of get_config.custom_objects
: A Python dictionary mapping names to additional Python objects used to create this optimizer, such as a function used for a hyperparameter.
Returns:
An optimizer instance.
tf.keras.optimizers.Adam.get_config
get_config()
Returns the config of the optimimizer.
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.
Returns:
Python dictionary.
tf.keras.optimizers.Adam.get_gradients
get_gradients(
loss,
params
)
Returns gradients of loss
with respect to params
.
Arguments:
loss
: Loss tensor.params
: List of variables.
Returns:
List of gradient tensors.
Raises:
ValueError
: In case any gradient cannot be computed (e.g. if gradient function not implemented).
tf.keras.optimizers.Adam.get_slot
get_slot(
var,
slot_name
)
tf.keras.optimizers.Adam.get_slot_names
get_slot_names()
A list of names for this optimizer's slots.
tf.keras.optimizers.Adam.get_updates
get_updates(
loss,
params
)
tf.keras.optimizers.Adam.get_weights
get_weights()
tf.keras.optimizers.Adam.minimize
minimize(
loss,
var_list,
grad_loss=None,
name=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
: A callable taking no arguments which returns the value to minimize.var_list
: list or tuple ofVariable
objects to update to minimizeloss
, or a callable returning the list or tuple ofVariable
objects. Use callable when the variable list would otherwise be incomplete beforeminimize
since the variables are created at the first timeloss
is called.grad_loss
: Optional. ATensor
holding the gradient computed forloss
.name
: Optional name for the returned operation.
Returns:
An Operation that updates the variables in var_list
. If global_step
was not None
, that operation also increments global_step
.
Raises:
ValueError
: If some of the variables are notVariable
objects.
tf.keras.optimizers.Adam.set_weights
set_weights(weights)
tf.keras.optimizers.Adam.variables
variables()
Returns variables of this Optimizer based on the order created.