Multinomial

public final class Multinomial

Draws samples from a multinomial distribution.

Nested Classes

class Multinomial.Options Optional attributes for Multinomial  

Constants

String OP_NAME The name of this op, as known by TensorFlow core engine

Public Methods

Output<U>
asOutput()
Returns the symbolic handle of the tensor.
static <U extends TNumber> Multinomial<U>
create(Scope scope, Operand<? extends TNumber> logits, Operand<TInt32> numSamples, Class<U> outputDtype, Options... options)
Factory method to create a class wrapping a new Multinomial operation.
static Multinomial<TInt64>
create(Scope scope, Operand<? extends TNumber> logits, Operand<TInt32> numSamples, Options... options)
Factory method to create a class wrapping a new Multinomial operation using default output types.
Output<U>
output()
2-D Tensor with shape `[batch_size, num_samples]`.
static Multinomial.Options
seed(Long seed)
static Multinomial.Options
seed2(Long seed2)

Inherited Methods

Constants

public static final String OP_NAME

The name of this op, as known by TensorFlow core engine

Constant Value: "Multinomial"

Public Methods

public Output<U> asOutput ()

Returns the symbolic handle of the tensor.

Inputs to TensorFlow operations are outputs of another TensorFlow operation. This method is used to obtain a symbolic handle that represents the computation of the input.

public static Multinomial<U> create (Scope scope, Operand<? extends TNumber> logits, Operand<TInt32> numSamples, Class<U> outputDtype, Options... options)

Factory method to create a class wrapping a new Multinomial operation.

Parameters
scope current scope
logits 2-D Tensor with shape `[batch_size, num_classes]`. Each slice `[i, :]` represents the unnormalized log probabilities for all classes.
numSamples 0-D. Number of independent samples to draw for each row slice.
options carries optional attributes values
Returns
  • a new instance of Multinomial

public static Multinomial<TInt64> create (Scope scope, Operand<? extends TNumber> logits, Operand<TInt32> numSamples, Options... options)

Factory method to create a class wrapping a new Multinomial operation using default output types.

Parameters
scope current scope
logits 2-D Tensor with shape `[batch_size, num_classes]`. Each slice `[i, :]` represents the unnormalized log probabilities for all classes.
numSamples 0-D. Number of independent samples to draw for each row slice.
options carries optional attributes values
Returns
  • a new instance of Multinomial

public Output<U> output ()

2-D Tensor with shape `[batch_size, num_samples]`. Each slice `[i, :]` contains the drawn class labels with range `[0, num_classes)`.

public static Multinomial.Options seed (Long seed)

Parameters
seed If either seed or seed2 is set to be non-zero, the internal random number generator is seeded by the given seed. Otherwise, a random seed is used.

public static Multinomial.Options seed2 (Long seed2)

Parameters
seed2 A second seed to avoid seed collision.