tfa.optimizers.AdamW

Optimizer that implements the Adam algorithm with weight decay.

Inherits From: DecoupledWeightDecayExtension

tfa.optimizers.AdamW(
    weight_decay: Union[FloatTensorLike, Callable],
    learning_rate: Union[FloatTensorLike, Callable] = 0.001,
    beta_1: Union[FloatTensorLike, Callable] = 0.9,
    beta_2: Union[FloatTensorLike, Callable] = 0.999,
    epsilon: tfa.types.FloatTensorLike = 1e-07,
    amsgrad: bool = False,
    name: str = 'AdamW',
    **kwargs
)

This is an implementation of the AdamW optimizer described in "Decoupled Weight Decay Regularization" by Loshchilov & Hutter.

It computes the update step of tf.keras.optimizers.Adam and additionally decays the variable. Note that this is different from adding L2 regularization on the variables to the loss: it regularizes variables with large gradients more than L2 regularization would, which was shown to yield better training loss and generalization error in the paper above.

For further information see the documentation of the Adam Optimizer.

This optimizer can also be instantiated as

extend_with_decoupled_weight_decay(tf.keras.optimizers.Adam,
                                   weight_decay=weight_decay)

step = tf.Variable(0, trainable=False)
schedule = tf.optimizers.schedules.PiecewiseConstantDecay(
    [10000, 15000], [1e-0, 1e-1, 1e-2])
# lr and wd can be a function or a tensor
lr = 1e-1 * schedule(step)
wd = lambda: 1e-4 * schedule(step)

# ...

optimizer = tfa.optimizers.AdamW(learning_rate=lr, weight_decay=wd)

weight_decay A Tensor or a floating point value. The weight decay.
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 "AdamW".
**kwargs keyword arguments. Allowed to be {clipnorm, clipvalue, lr, decay, exclude_from_weight_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 use learning_rate instead. exclude_from_weight_decay accepts list of regex patterns of variables excluded from weight decay.

clipnorm float or None. If set, clips gradients to a maximum norm.
clipvalue float or None. If set, clips gradients to a maximum value.
global_clipnorm float or None.

If set, clips gradients to a maximum norm.

Check tf.clip_by_global_norm for more details.

iterations Variable. The number of training steps this Optimizer has run.
weights Returns variables of this Optimizer based on the order created.

Methods

add_slot

add_slot(
    var, slot_name, initializer='zeros', shape=None
)

Add a new slot variable for var.

A slot variable is an additional variable associated with var to train. It is allocated and managed by optimizers, e.g. Adam.

Args
var a Variable object.
slot_name name of the slot variable.
initializer initializer of the slot variable
shape (Optional) shape of the slot variable. If not set, it will default to the shape of var.

Returns
A slot variable.

add_weight

add_weight(
    name,
    shape,
    dtype=None,
    initializer='zeros',
    trainable=None,
    synchronization=tf.VariableSynchronization.AUTO,
    aggregation=tf.VariableAggregation.NONE
)

apply_gradients

View source

apply_gradients(
    grads_and_vars, name=None, decay_var_list=None, **kwargs
)

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 the Optimizer constructor.
decay_var_list Optional list of variables to be decayed. Defaults to all variables in var_list. Note decay_var_list takes priority over exclude_from_weight_decay if specified.
**kwargs Additional arguments to pass to the base optimizer's apply_gradient method, e.g., TF2.2 added an argument experimental_aggregate_gradients.

Returns
An Operation that applies the specified gradients.

Raises
TypeError If grads_and_vars is malformed.
ValueError If none of the variables have gradients.

from_config

View source

@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 Python objects used to create this optimizer, such as a function used for a hyperparameter.

Returns
An optimizer instance.

get_config

View source

get_config()

get_gradients

get_gradients(
    loss, params
)

Returns gradients of loss with respect to params.

Should be used only in legacy v1 graph mode.

Args
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).

get_slot

get_slot(
    var, slot_name
)

get_slot_names

get_slot_names()

A list of names for this optimizer's slots.

get_updates

get_updates(
    loss, params
)

get_weights

get_weights()

Returns the current weights of the optimizer.

The weights of an optimizer are its state (ie, variables). This function returns the weight values associated with this optimizer as a list of Numpy arrays. The first value is always the iterations count of the optimizer, followed by the optimizer's state variables in the order they were created. The returned list can in turn be used to load state into similarly parameterized optimizers.

For example, the RMSprop optimizer for this simple model returns a list of three values-- the iteration count, followed by the root-mean-square value of the kernel and bias of the single Dense layer:

opt = tf.keras.optimizers.legacy.RMSprop()
m = tf.keras.models.Sequential([tf.keras.layers.Dense(10)])
m.compile(opt, loss='mse')
data = np.arange(100).reshape(5, 20)
labels = np.zeros(5)
results = m.fit(data, labels)  # Training.
len(opt.get_weights())
3

Returns
Weights values as a list of numpy arrays.

minimize

View source

minimize(
    loss, var_list, grad_loss=None, name=None, decay_var_list=None, 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. If a Tensor, the tape argument must be passed.
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.
grad_loss Optional. A Tensor holding the gradient computed for loss.
decay_var_list Optional list of variables to be decayed. Defaults to all variables in var_list. Note decay_var_list takes priority over exclude_from_weight_decay if specified.
name Optional name for the returned operation.
tape (Optional) tf.GradientTape. If loss is provided as a Tensor, the tape that computed the loss must be provided.

Returns
An Operation that updates the variables in var_list.

Raises
ValueError If some of the variables are not Variable objects.

set_weights

set_weights(
    weights
)

Set the weights of the optimizer.

The weights of an optimizer are its state (ie, variables). This function takes the weight values associated with this optimizer as a list of Numpy arrays. The first value is always the iterations count of the optimizer, followed by the optimizer's state variables in the order they are created. The passed values are used to set the new state of the optimizer.

For example, the RMSprop optimizer for this simple model takes a list of three values-- the iteration count, followed by the root-mean-square value of the kernel and bias of the single Dense layer:

opt = tf.keras.optimizers.legacy.RMSprop()
m = tf.keras.models.Sequential([tf.keras.layers.Dense(10)])
m.compile(opt, loss='mse')
data = np.arange(100).reshape(5, 20)
labels = np.zeros(5)
results = m.fit(data, labels)  # Training.
new_weights = [np.array(10), np.ones([20, 10]), np.zeros([10])]
opt.set_weights(new_weights)
opt.iterations
<tf.Variable 'RMSprop/iter:0' shape=() dtype=int64, numpy=10>

Args
weights weight values as a list of numpy arrays.

variables

variables()

Returns variables of this Optimizer based on the order created.