org.tensorflow.op.core

Class SoftmaxCrossEntropyWithLogits<T extends Number>

java.lang.Object

org.tensorflow.op.PrimitiveOp

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

Type Parameters:

T - data type for loss() output

All Implemented Interfaces:

Op

@Operator
public final class SoftmaxCrossEntropyWithLogits<T extends Number>
extends PrimitiveOp

Computes softmax cross entropy cost and gradients to backpropagate.

Inputs are the logits, not probabilities.

Field Summary

Fields inherited from class org.tensorflow.op.PrimitiveOp

operation

Method Summary

Modifier and Type	Method and Description
Output<T>	backprop() backpropagated gradients (batch_size x num_classes matrix).
static <T extends Number> SoftmaxCrossEntropyWithLogits<T>	create(Scope scope, Operand<T> features, Operand<T> labels) Factory method to create a class to wrap a new SoftmaxCrossEntropyWithLogits operation to the graph.
Output<T>	loss() Per example loss (batch_size vector).

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> SoftmaxCrossEntropyWithLogits<T> create(Scope scope,
                                                                         Operand<T> features,
                                                                         Operand<T> labels)

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

Parameters:

scope - current graph scope

features - batch_size x num_classes matrix

labels - batch_size x num_classes matrix The caller must ensure that each batch of labels represents a valid probability distribution.

Returns:

a new instance of SoftmaxCrossEntropyWithLogits

loss

public Output<T> loss()

Per example loss (batch_size vector).

backprop

public Output<T> backprop()

backpropagated gradients (batch_size x num_classes matrix).