Class Metrics

java.lang.Object

org.tensorflow.framework.metrics.Metrics

public class Metrics
extends Object

Static methods for computing metrics.

Constructor Summary

Constructors

Constructor	Description
Metrics()

Method Summary

Modifier and Type	Method	Description
static <T extends TNumber, U extends TNumber> Operand<T>	sparseTopKCategoricalAccuracy(Ops tf, Operand<U> labels, Operand<T> predictions, int k)	Computes how often integer targets are in the top K predictions.
static <T extends TNumber> Operand<T>	topKCategoricalAccuracy(Ops tf, Operand<? extends TNumber> labels, Operand<T> predictions, long k)	Computes how often targets are in the top K predictions.

Methods inherited from class Object

clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Constructor Details

Metrics

public Metrics()

Method Details

topKCategoricalAccuracy

public static <T extends TNumber> Operand<T> topKCategoricalAccuracy(Ops tf,
 Operand<? extends TNumber> labels,
 Operand<T> predictions,
 long k)

Computes how often targets are in the top K predictions.

Standalone usage:

    Operand<TInt32> labels = tf.constant(new int[][]
                                   {{0, 0, 1}, {0, 1, 0}});
    Operand<TFloat32> predictions = tf.constant(new float[][]
                                   {{0.1f, 0.9f, 0.8f}, {0.05f, 0.95f, 0f}});
    Operand<TFloat32> m = Metrics.topKCategoricalAccuracy(
                                   labels, predictions, 3)
    //m.shape().toString == "[2]"

Type Parameters:

T - the data type for the predictions and results

Parameters:

tf - the TensorFlow Ops encapsulating a Graph environment..

labels - the ground truth values.

predictions - The prediction values.

k - Number of top elements to look at for computing accuracy.

Returns:

the Operand for the Top K categorical accuracy value.

Throws:

IllegalArgumentException - if the TensorFlow Ops scope does not encapsulate a Graph environment.

sparseTopKCategoricalAccuracy

public static <T extends TNumber, U extends TNumber>
Operand<T> sparseTopKCategoricalAccuracy(Ops tf,
 Operand<U> labels,
 Operand<T> predictions,
 int k)

Computes how often integer targets are in the top K predictions.

Standalone usage:

    Operand<TInt32> labels = tf.constant(new int[]{2, 1});
    Operand<TFloat32> predictions = tf.constant(new float[][]
                           {{0.1f, 0.9f, 0.f8}, {0.05f, 0.95f, 0f}});
    Operand<TFloat32> m = Metrics.topKCategoricalAccuracy(
                                   labels, predictions, 3)
    //m.shape().toString == "[2]"

Type Parameters:

T - the data type for the predictions and results

U - the data type ofr the labels.

Parameters:

tf - the TensorFlow Ops encapsulating a Graph environment..

labels - the ground truth values.

predictions - The prediction values.

k - Number of top elements to look at for computing accuracy.

Returns:

the Operand for the Sparse top K categorical accuracy value.

Throws:

IllegalArgumentException - if the TensorFlow Ops scope does not encapsulate a Graph environment.