Draws samples from a multinomial distribution.
Constants
String | OP_NAME | The name of this op, as known by TensorFlow core engine |
Public Methods
Output<V> |
asOutput()
Returns the symbolic handle of the tensor.
|
static StatelessMultinomial<TInt64> | |
static <V extends TNumber> StatelessMultinomial<V> | |
Output<V> |
output()
2-D Tensor with shape `[batch_size, num_samples]`.
|
Inherited Methods
Constants
public static final String OP_NAME
The name of this op, as known by TensorFlow core engine
Public Methods
public Output<V> 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 StatelessMultinomial<TInt64> create (Scope scope, Operand<? extends TNumber> logits, Operand<TInt32> numSamples, Operand<? extends TNumber> seed)
Factory method to create a class wrapping a new StatelessMultinomial 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. |
seed | 2 seeds (shape [2]). |
Returns
- a new instance of StatelessMultinomial
public static StatelessMultinomial<V> create (Scope scope, Operand<? extends TNumber> logits, Operand<TInt32> numSamples, Operand<? extends TNumber> seed, Class<V> outputDtype)
Factory method to create a class wrapping a new StatelessMultinomial 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. |
seed | 2 seeds (shape [2]). |
Returns
- a new instance of StatelessMultinomial
public Output<V> output ()
2-D Tensor with shape `[batch_size, num_samples]`. Each slice `[i, :]` contains the drawn class labels with range `[0, num_classes)`.