Momentum

public class Momentum

Stochastic gradient descent plus momentum, either nesterov or traditional.

See the paper for details of nesterov momentum.

Constants

float LEARNING_RATE_DEFAULT
String MOMENTUM
float MOMENTUM_DEFAULT
boolean NESTEROV_DEFAULT

Inherited Constants

Public Constructors

Momentum(Graph graph)
Creates a Momentum Optimizer
Momentum(Graph graph, float learningRate)
Creates a Momentum Optimizer
Momentum(Graph graph, float learningRate, float momentum)
Creates a Momentum Optimizer
Momentum(Graph graph, float learningRate, float momentum, boolean useNesterov)
Creates a Momentum Optimizer
Momentum(Graph graph, String name, float learningRate, float momentum, boolean useNesterov)
Creates a Momentum Optimizer

Public Methods

String
getOptimizerName()
Get the Name of the optimizer.
String

Inherited Methods

Constants

public static final float LEARNING_RATE_DEFAULT

Constant Value: 0.01

public static final String MOMENTUM

Constant Value: "momentum"

public static final float MOMENTUM_DEFAULT

Constant Value: 0.0

public static final boolean NESTEROV_DEFAULT

Constant Value: false

Public Constructors

public Momentum (Graph graph)

Creates a Momentum Optimizer

Parameters
graph the TensorFlow graph

public Momentum (Graph graph, float learningRate)

Creates a Momentum Optimizer

Parameters
graph the TensorFlow graph
learningRate the learning rate

public Momentum (Graph graph, float learningRate, float momentum)

Creates a Momentum Optimizer

Parameters
graph the TensorFlow graph
learningRate the learning rate
momentum hyperparameter that accelerates gradient descent in the relevant direction and dampens oscillations, Must be greater than or equal to zero. Default is 0.

public Momentum (Graph graph, float learningRate, float momentum, boolean useNesterov)

Creates a Momentum Optimizer

Parameters
graph the TensorFlow graph
learningRate the learning rate
momentum hyperparameter that accelerates gradient descent in the relevant direction and dampens oscillations, Must be greater than or equal to zero. Default is 0.
useNesterov Whether to apply Nesterov momentum. Defaults to false.

public Momentum (Graph graph, String name, float learningRate, float momentum, boolean useNesterov)

Creates a Momentum Optimizer

Parameters
graph the TensorFlow graph
name the name for this Optimizer
learningRate the learning rate
momentum hyperparameter that accelerates gradient descent in the relevant direction and dampens oscillations, Must be greater than or equal to zero. Default is 0.
useNesterov Whether to apply Nesterov momentum. Defaults to false.

Public Methods

public String getOptimizerName ()

Get the Name of the optimizer.

Returns
  • The optimizer name.

public String toString ()