tf.contrib.opt.AdamWOptimizer

Class AdamWOptimizer

Inherits From: DecoupledWeightDecayExtension, AdamOptimizer

Defined in tensorflow/contrib/opt/python/training/weight_decay_optimizers.py.

Optimizer that implements the Adam algorithm with weight decay.

This is an implementation of the AdamW optimizer described in "Fixing Weight Decay Regularization in Adam" by Loshchilov & Hutter (https://arxiv.org/abs/1711.05101) ([pdf])(https://arxiv.org/pdf/1711.05101.pdf).

It computes the update step of train.AdamOptimizer 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.

Note that this optimizer can also be instantiated as

extend_with_weight_decay(tf.train.AdamOptimizer, weight_decay=weight_decay)

Methods

__init__

__init__(
    weight_decay,
    learning_rate=0.001,
    beta1=0.9,
    beta2=0.999,
    epsilon=1e-08,
    use_locking=False,
    name='AdamW'
)

Construct a new AdamW optimizer.

For further information see the documentation of the Adam Optimizer.

Args:

  • weight_decay: A Tensor or a floating point value. The weight decay.
  • learning_rate: A Tensor or a floating point value. The learning rate.
  • beta1: A float value or a constant float tensor. The exponential decay rate for the 1st moment estimates.
  • beta2: 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.
  • use_locking: If True use locks for update operations.
  • name: Optional name for the operations created when applying gradients. Defaults to "Adam".

apply_gradients

apply_gradients(
    grads_and_vars,
    global_step=None,
    name=None,
    decay_var_list=None
)

Apply gradients to variables and decay the variables.

This function is the same as Optimizer.apply_gradients except that it allows to specify the variables that should be decayed using decay_var_list. If decay_var_list is None, all variables in var_list are decayed.

For more information see the documentation of Optimizer.apply_gradients.

Args:

  • grads_and_vars: List of (gradient, variable) pairs as returned by compute_gradients().
  • global_step: Optional Variable to increment by one after the variables have been updated.
  • name: Optional name for the returned operation. Default to the name passed to the Optimizer constructor.
  • decay_var_list: Optional list of decay variables.

Returns:

An Operation that applies the specified gradients. If global_step was not None, that operation also increments global_step.

compute_gradients

compute_gradients(
    loss,
    var_list=None,
    gate_gradients=GATE_OP,
    aggregation_method=None,
    colocate_gradients_with_ops=False,
    grad_loss=None
)

Compute gradients of loss for the variables in var_list.

This is the first part of minimize(). It returns a list of (gradient, variable) pairs where "gradient" is the gradient for "variable". Note that "gradient" can be a Tensor, an IndexedSlices, or None if there is no gradient for the given variable.

Args:

  • loss: A Tensor containing the value to minimize or a callable taking no arguments which returns the value to minimize. When eager execution is enabled it must be a callable.
  • var_list: Optional list or tuple of tf.Variable to update to minimize loss. Defaults to the list of variables collected in the graph under the key GraphKeys.TRAINABLE_VARIABLES.
  • gate_gradients: How to gate the computation of gradients. Can be GATE_NONE, GATE_OP, or GATE_GRAPH.
  • aggregation_method: Specifies the method used to combine gradient terms. Valid values are defined in the class AggregationMethod.
  • colocate_gradients_with_ops: If True, try colocating gradients with the corresponding op.
  • grad_loss: Optional. A Tensor holding the gradient computed for loss.

Returns:

A list of (gradient, variable) pairs. Variable is always present, but gradient can be None.

Raises:

  • TypeError: If var_list contains anything else than Variable objects.
  • ValueError: If some arguments are invalid.
  • RuntimeError: If called with eager execution enabled and loss is not callable.

Eager Compatibility

When eager execution is enabled, gate_gradients, aggregation_method, and colocate_gradients_with_ops are ignored.

get_name

get_name()

get_slot

get_slot(
    var,
    name
)

Return a slot named name created for var by the Optimizer.

Some Optimizer subclasses use additional variables. For example Momentum and Adagrad use variables to accumulate updates. This method gives access to these Variable objects if for some reason you need them.

Use get_slot_names() to get the list of slot names created by the Optimizer.

Args:

  • var: A variable passed to minimize() or apply_gradients().
  • name: A string.

Returns:

The Variable for the slot if it was created, None otherwise.

get_slot_names

get_slot_names()

Return a list of the names of slots created by the Optimizer.

See get_slot().

Returns:

A list of strings.

minimize

minimize(
    loss,
    global_step=None,
    var_list=None,
    gate_gradients=optimizer.Optimizer.GATE_OP,
    aggregation_method=None,
    colocate_gradients_with_ops=False,
    name=None,
    grad_loss=None,
    decay_var_list=None
)

Add operations to minimize loss by updating var_list with decay.

This function is the same as Optimizer.minimize except that it allows to specify the variables that should be decayed using decay_var_list. If decay_var_list is None, all variables in var_list are decayed.

For more information see the documentation of Optimizer.minimize.

Args:

  • loss: A Tensor containing the value to minimize.
  • global_step: Optional Variable to increment by one after the variables have been updated.
  • var_list: Optional list or tuple of Variable objects to update to minimize loss. Defaults to the list of variables collected in the graph under the key GraphKeys.TRAINABLE_VARIABLES.
  • gate_gradients: How to gate the computation of gradients. Can be GATE_NONE, GATE_OP, or GATE_GRAPH.
  • aggregation_method: Specifies the method used to combine gradient terms. Valid values are defined in the class AggregationMethod.
  • colocate_gradients_with_ops: If True, try colocating gradients with the corresponding op.
  • name: Optional name for the returned operation.
  • grad_loss: Optional. A Tensor holding the gradient computed for loss.
  • decay_var_list: Optional list of decay variables.

Returns:

An Operation that updates the variables in var_list. If global_step was not None, that operation also increments global_step.

variables

variables()

A list of variables which encode the current state of Optimizer.

Includes slot variables and additional global variables created by the optimizer in the current default graph.

Returns:

A list of variables.

Class Members

GATE_GRAPH

GATE_NONE

GATE_OP