Class FalseNegatives<T extends TNumber>

java.lang.Object

org.tensorflow.framework.metrics.BaseMetric

org.tensorflow.framework.metrics.FalseNegatives<T>

Type Parameters:

T - The data type for the metric result

All Implemented Interfaces:

Metric

public class FalseNegatives<T extends TNumber>
extends BaseMetric

Metric that calculates the number of false negatives.

If sampleWeights is given, calculates the sum of the weights of false negatives. This metric creates one local variable, accumulator that is used to keep track of the number of false negatives.

If sampleWeights is null, weights default to 1. Use sampleWeights of 0 to mask values.

Field Summary

Fields

Modifier and Type	Field	Description
static final String	ACCUMULATOR
static final float	DEFAULT_THRESHOLD

Constructor Summary

Constructors

Constructor	Description
FalseNegatives(float[] thresholds, long seed, Class<T> type)	Creates a FalseNegatives metric, using Class.getSimpleName() for the metric name
FalseNegatives(float threshold, long seed, Class<T> type)	Creates a FalseNegatives metric, using Class.getSimpleName() for the metric name
FalseNegatives(long seed, Class<T> type)	Creates a FalseNegatives metric, using Class.getSimpleName() for the metric name and a default threshold of DEFAULT_THRESHOLD.
FalseNegatives(String name, float[] thresholds, long seed, Class<T> type)	Creates a FalseNegatives metric
FalseNegatives(String name, float threshold, long seed, Class<T> type)	Creates a FalseNegatives metric
FalseNegatives(String name, long seed, Class<T> type)	Creates a FalseNegatives metric, using a default threshold of DEFAULT_THRESHOLD.

Method Summary

Modifier and Type	Method	Description
String	getAccumulatorName()	Gets the accumulatorName
float[]	getThresholds()	get the thresholds
protected void	init(Ops tf)	Initialize the TensorFlow Ops
Op	resetStates(Ops tf)	Resets any state variables to their initial values
<U extends TNumber> Operand<U>	result(Ops tf, Class<U> type)	Gets the current result of the metric
List<Op>	updateStateList(Ops tf, Operand<? extends TNumber> labels, Operand<? extends TNumber> predictions, Operand<? extends TNumber> sampleWeights)	Accumulates the metric statistics.

Methods inherited from class BaseMetric

callOnce, checkIsGraph, getName, getSeed, getTF, getVariableName, isInitialized, setInitialized, setName, setTF, updateState, updateState, updateStateList

Methods inherited from class Object

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

Field Details

ACCUMULATOR

public static final String ACCUMULATOR

See Also:

• Constant Field Values

DEFAULT_THRESHOLD

public static final float DEFAULT_THRESHOLD

See Also:

• Constant Field Values

Constructor Details

FalseNegatives

public FalseNegatives(long seed,
 Class<T> type)

Creates a FalseNegatives metric, using Class.getSimpleName() for the metric name and a default threshold of DEFAULT_THRESHOLD.

Parameters:

seed - the seed for random number generation. An initializer created with a given seed will always produce the same random tensor for a given shape and data type.

type - the data type for the variables

FalseNegatives

public FalseNegatives(float threshold,
 long seed,
 Class<T> type)

Creates a FalseNegatives metric, using Class.getSimpleName() for the metric name

Parameters:

threshold - a threshold value in the range [0, 1]. A threshold is compared with prediction values to determine the truth value of predictions (i.e., above the threshold is true, below is false). One metric value is generated for each threshold value

seed - the seed for random number generation. An initializer created with a given seed will always produce the same random tensor for a given shape and data type.

type - the data type for the variables

FalseNegatives

public FalseNegatives(float[] thresholds,
 long seed,
 Class<T> type)

Creates a FalseNegatives metric, using Class.getSimpleName() for the metric name

Parameters:

thresholds - threshold values in the range [0, 1]. A threshold is compared with prediction values to determine the truth value of predictions (i.e., above the threshold is true, below is false). One metric value is generated for each threshold value

seed - the seed for random number generation. An initializer created with a given seed will always produce the same random tensor for a given shape and data type.

type - the data type for the variables

FalseNegatives

public FalseNegatives(String name,
 long seed,
 Class<T> type)

Creates a FalseNegatives metric, using a default threshold of DEFAULT_THRESHOLD.

Parameters:

name - the name of the metric, if null then Class.getSimpleName() is used

seed - the seed for random number generation. An initializer created with a given seed will always produce the same random tensor for a given shape and data type.

type - the data type for the variables

FalseNegatives

public FalseNegatives(String name,
 float threshold,
 long seed,
 Class<T> type)

Creates a FalseNegatives metric

Parameters:

name - the name of the metric, if null then Class.getSimpleName() is used

threshold - a threshold value in the range [0, 1]. A threshold is compared with prediction values to determine the truth value of predictions (i.e., above the threshold is true, below is false). One metric value is generated for each threshold value

seed - the seed for random number generation. An initializer created with a given seed will always produce the same random tensor for a given shape and data type.

type - the data type for the variables

FalseNegatives

public FalseNegatives(String name,
 float[] thresholds,
 long seed,
 Class<T> type)

Creates a FalseNegatives metric

Parameters:

name - the name of the metric, if null then Class.getSimpleName() is used

thresholds - threshold values in the range [0, 1]. A threshold is compared with prediction values to determine the truth value of predictions (i.e., above the threshold is true, below is false). One metric value is generated for each threshold value

seed - the seed for random number generation. An initializer created with a given seed will always produce the same random tensor for a given shape and data type.

type - the data type for the variables

Method Details

init

protected void init(Ops tf)

Initialize the TensorFlow Ops

Specified by:

init in class BaseMetric

Parameters:

tf - the TensorFlow Ops encapsulating a Graph environment.

updateStateList

public List<Op> updateStateList(Ops tf,
 Operand<? extends TNumber> labels,
 Operand<? extends TNumber> predictions,
 Operand<? extends TNumber> sampleWeights)

Accumulates the metric statistics.

Specified by:

updateStateList in interface Metric

Overrides:

updateStateList in class BaseMetric

Parameters:

tf - the TensorFlow Ops encapsulating a Graph environment.

labels - The ground truth values.

predictions - the predictions

sampleWeights - Optional weighting of each example. Defaults to 1. Rank is either 0, or the same rank as labels, and must be broadcastable to labels.

Returns:

a List of Operations to update the metric state.

result

public <U extends TNumber> Operand<U> result(Ops tf,
 Class<U> type)

Gets the current result of the metric

Type Parameters:

U - the date type for the result

Parameters:

tf - the TensorFlow Ops encapsulating a Graph environment.

type - the data type for the result

Returns:

the result, possibly with control dependencies

resetStates

public Op resetStates(Ops tf)

Resets any state variables to their initial values

Parameters:

tf - the TensorFlow Ops encapsulating a Graph environment.

Returns:

the operation for doing the reset

getThresholds

public float[] getThresholds()

get the thresholds

Returns:

the thresholds

getAccumulatorName

public String getAccumulatorName()

Gets the accumulatorName

Returns:

the accumulatorName