Orthogonal

public class Orthogonal

Initializer that generates an orthogonal matrix.

If the shape of the tensor to initialize is two-dimensional, it is initialized with an orthogonal matrix obtained from the QR decomposition of a matrix of random numbers drawn from a normal distribution. If the matrix has fewer rows than columns then the output will have orthogonal rows. Otherwise, the output will have orthogonal columns.

If the shape of the tensor to initialize is more than two-dimensional, a matrix of shape (shape.size(0) * ... * shape.size(n - 2), shape.size(n - 1)) is initialized, where n is the length of the shape vector. The matrix is subsequently reshaped to give a tensor of the desired shape.

Examples:

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

Constants

double GAIN_DEFAULT

Public Constructors

Orthogonal(Ops tf, long seed)
Creates an Orthogonal Initializer using GAIN_DEFAULT for the gain.
Orthogonal(Ops tf, double gain, long seed)
Creates an Orthogonal Initializer

Public Methods

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

Inherited Methods

Constants

public static final double GAIN_DEFAULT

Constant Value: 1.0

Public Constructors

public Orthogonal (Ops tf, long seed)

Creates an Orthogonal Initializer using GAIN_DEFAULT for the gain.

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 Orthogonal (Ops tf, double gain, long seed)

Creates an Orthogonal Initializer

Parameters
tf the TensorFlow Ops
gain the gain to be applied to the Matrix.
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)