public class
RandomNormal
Initializer that generates tensors with a normal distribution.
Examples:
long seed = 1001l; RandomNormal<TFloat32, TFloat32> initializer = new org.tensorflow.framework.initializers.RandomNormal<>(tf, seed); Operand<TFloat32> values = initializer.call(tf.constant(Shape.of(2,2)), TFloat32.class);
Constants
double | MEAN_DEFAULT | |
double | STDDEV_DEFAULT |
Public Constructors
RandomNormal(Ops tf, long seed)
Creates the RandomUniform initializer using
MEAN_DEFAULT for the mean and STDDEV_DEFAULT for the standard deviation. |
|
RandomNormal(Ops tf, double mean, long seed)
Creates the RandomUniform initializer using
STDDEV_DEFAULT for the standard deviation. |
|
RandomNormal(Ops tf, double mean, double stddev, long seed)
creates the RandomUniform initializer
|
Public Methods
Operand<T> |
Inherited Methods
Constants
public static final double MEAN_DEFAULT
Constant Value:
0.0
public static final double STDDEV_DEFAULT
Constant Value:
1.0
Public Constructors
public RandomNormal (Ops tf, long seed)
Creates the RandomUniform 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 RandomNormal (Ops tf, double mean, long seed)
Creates the RandomUniform initializer using STDDEV_DEFAULT
for the standard deviation.
Parameters
tf | the TensorFlow Ops |
---|---|
mean | Mean 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 RandomNormal (Ops tf, double mean, double stddev, long seed)
creates the RandomUniform 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. |