TruncatedNormal

public class TruncatedNormal

Initializer that generates a truncated normal distribution.

Examples:

     long seed = 1001l;
     TruncatedNormal<TFloat32, TFloat32> initializer =
              new org.tensorflow.framework.initializers.TruncatedNormal<>(tf, seed);
     Operand<TFloat32> values =
              initializer.call(tf.constant(Shape.of(2,2)), TFloat32.class);
 

Constants

double	MEAN_DEFAULT
double	STDDEV_DEFAULT

Public Constructors

	TruncatedNormal(Ops tf, long seed) Creates a TruncatedNormal Initializer using MEAN_DEFAULT for the mean and STDDEV_DEFAULT for the standard deviation.
	TruncatedNormal(Ops tf, double mean, double stddev, long seed) Creates a TruncatedNormal Initializer.

Public Methods

Operand<T>

call(Operand<TInt64> dims, Class<T> type)

Inherited Methods

From class org.tensorflow.framework.initializers.BaseInitializer

Ops	getTF() Gets the TensorFlow Ops

From class java.lang.Object

boolean	equals(Object arg0)
final Class<?>	getClass()
int	hashCode()
final void	notify()
final void	notifyAll()
String	toString()
final void	wait(long arg0, int arg1)
final void	wait(long arg0)
final void	wait()

From interface org.tensorflow.framework.initializers.Initializer

abstract Operand<T>

call(Operand<TInt64> dims, Class<T> type) Generates the operation used to perform the initialization.

Constants

public static final double MEAN_DEFAULT

Constant Value: 0.0

public static final double STDDEV_DEFAULT

Constant Value: 0.05

Public Constructors

public TruncatedNormal (Ops tf, long seed)

Creates a TruncatedNormal Initializer using MEAN_DEFAULT for the mean and STDDEV_DEFAULT for the standard deviation.

Parameters

tf	the TensorFlow Ops
seed	the seed for random number generation. An initializer created with a given seed will always produce the same random tensor for a given shape and dtype.

public TruncatedNormal (Ops tf, double mean, double stddev, long seed)

Creates a TruncatedNormal Initializer.

Parameters

tf	the TensorFlow Ops
mean	Mean of the random values to generate.
stddev	Standard deviation of the random values to generate.
seed	the seed for random number generation. An initializer created with a given seed will always produce the same random tensor for a given shape and dtype.

Public Methods

public Operand<T> call (Operand<TInt64> dims, Class<T> type)