org.tensorflow.op.core

Class Softmax<T extends Number>

java.lang.Object

org.tensorflow.op.PrimitiveOp

org.tensorflow.op.core.Softmax<T>

Type Parameters:

T - data type for softmax() output

All Implemented Interfaces:

Op, Operand<T>

@Operator
public final class Softmax<T extends Number>
extends PrimitiveOp
implements Operand<T>

Computes softmax activations.

For each batch `i` and class `j` we have

$$softmax[i, j] = exp(logits[i, j]) / sum_j(exp(logits[i, j]))$$

Field Summary

Fields inherited from class org.tensorflow.op.PrimitiveOp

operation

Method Summary

Modifier and Type	Method and Description
Output<T>	asOutput() Returns the symbolic handle of a tensor.
static <T extends Number> Softmax<T>	create(Scope scope, Operand<T> logits) Factory method to create a class to wrap a new Softmax operation to the graph.
Output<T>	softmax() Same shape as `logits`.

Methods inherited from class org.tensorflow.op.PrimitiveOp

equals, hashCode, toString

Methods inherited from class java.lang.Object

clone, finalize, getClass, notify, notifyAll, wait, wait, wait

Method Detail

create

public static <T extends Number> Softmax<T> create(Scope scope,
                                                   Operand<T> logits)

Factory method to create a class to wrap a new Softmax operation to the graph.

Parameters:

scope - current graph scope

logits - 2-D with shape `[batch_size, num_classes]`.

Returns:

a new instance of Softmax

softmax

public Output<T> softmax()

Same shape as `logits`.

asOutput

public Output<T> asOutput()

Description copied from interface: Operand

Returns the symbolic handle of a 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.

Specified by:

asOutput in interface Operand<T extends Number>

See Also:

OperationBuilder.addInput(Output)