public class BinaryAccuracy extends AbstractAccuracy
BinaryAccuracy
is the AbstractAccuracy
with two classes.
It is assumed that the classes are identified with a labels array of 0s and 1s and a
prediction array where values above the threshold are the positive (1) examples and values below
the threshold are the negative (0) examples. If you have a different encoding, you may want to
look at the Accuracy
.
axis, correctInstances, index
totalInstances
Constructor and Description |
---|
BinaryAccuracy()
Creates a binary (two class) accuracy evaluator with 0 threshold.
|
BinaryAccuracy(float threshold)
Creates a binary (two class) accuracy evaluator that computes accuracy across axis 1 along
the 0th index.
|
BinaryAccuracy(java.lang.String name,
float threshold,
int index)
Creates a binary (two class) accuracy evaluator that computes accuracy across axis 1 along
given index.
|
BinaryAccuracy(java.lang.String name,
float threshold,
int index,
int axis)
Creates a binary (two class) accuracy evaluator.
|
Modifier and Type | Method and Description |
---|---|
protected ai.djl.util.Pair<java.lang.Long,NDArray> |
accuracyHelper(NDList labels,
NDList predictions)
A helper for classes extending
AbstractAccuracy . |
addAccumulator, evaluate, getAccumulator, resetAccumulator, updateAccumulator
checkLabelShapes, checkLabelShapes, getName
public BinaryAccuracy(java.lang.String name, float threshold, int index, int axis)
name
- the name of the evaluator, default is "Accuracy"threshold
- the value differentiating the posive and negative classes (usually 0 or .5)index
- the index of the NDArray in labels to compute accuracy foraxis
- the axis that represent classes in prediction, default 1public BinaryAccuracy(java.lang.String name, float threshold, int index)
name
- the name of the evaluator, default is "Accuracy"threshold
- the value differentiating the posive and negative classes (usually 0 or .5)index
- the index of the NDArray in labels to compute accuracy forpublic BinaryAccuracy(float threshold)
threshold
- the value differentiating the posive and negative classes (usually 0 or .5)public BinaryAccuracy()
protected ai.djl.util.Pair<java.lang.Long,NDArray> accuracyHelper(NDList labels, NDList predictions)
AbstractAccuracy
.accuracyHelper
in class AbstractAccuracy
labels
- the labels to get accuracy forpredictions
- the predictions to get accuracy for