Welcome to our Support Center
Updated

Metric resume

In this section you’ll find a list of all metric fonctionalities.

Β ICONSRESUME
AccuracyCalculates how often predictions equal labels.
BinaryAccuracyCalculates how often predictions match binary labels.
BinaryCrossentropyComputes the crossentropy metric between the labels and predictions.
BinaryIoUComputes the Intersection-Over-Union metric for class 0 and/or 1.
CategoricalAccuracyCalculates how often predictions match one-hot labels.
CategoricalCrossentropyComputes the crossentropy metric between the labels and predictions.
CategoricalHingeComputes the categorical hinge metric between y_true and y_pred.
CosineSimilarityComputes the cosine similarity between the labels and predictions.
FalseNegativesCalculates the number of false negatives.
FalsePositivesCalculates the number of false positives.
HingeComputes the hinge metric between y_true and y_pred.
HuberComputes the huber metrics between y_true and y_pred.
IoUComputes the Intersection-Over-Union metric for specific target classes.
KLDivergenceComputes Kullback-Leibler divergence metric between y_true and y_pred.
LogCoshErrorComputes the logarithm of the hyperbolic cosine of the prediction error.
MeanComputes the mean of the given values.
MeanAbsoluteErrorComputes the mean absolute error between the labels and predictions.
MeanAbsolutePercentageErrorComputes the mean absolute percentage error between y_true and y_pred.
MeanIoUComputes the mean Intersection-Over-Union metric.
MeanRelativeErrorComputes the mean relative error by normalizing with the given values.
MeanSquaredErrorComputes the mean squared error between y_true and y_pred.
MeanSquaredLogarithmicErrorComputes the mean squared logarithmic error between y_true and y_pred.
MeanTensorComputes the element-wise mean of the given tensors.
OneHotIoUComputes the Intersection-Over-Union metric for one-hot encoded labels.
OneHotMeanIoUComputes mean Intersection-Over-Union metric for one-hot encoded labels.
PoissonComputes the poisson metric between y_true and y_pred.
PrecisionComputes the precision of the predictions with respect to the labels.
PrecisionAtRecallComputes best precision where recall is > specified value.
RecallComputes the recall of the predictions with respect to the labels.
RecallAtPrecisionComputes best recall where precision is > specified value.
RootMeanSquaredErrorComputes root mean squared error metric between y_true and y_pred.
SensitivityAtSpecificityComputes best sensitivity where specificity is > specified value.
SparseCategoricalAccuracyCalculates how often predictions match integer labels.
SparseCategoricalCrossentropyComputes the crossentropy metric between the labels and predictions.
SparseTopKCategoricalAccuracyComputes how often integer targets are in the top K predictions.
SpecificityComputes the specificity of the predictions with respect to the labels.
SpecificityAtSensitivityComputes best specificity where sensitivity is > specified value.
SquaredHingeComputes the squared hinge metric between y_true and y_pred.
SumComputes the sum of the given values.
TopKCategoricalAccuracyComputes how often targets are in the top K predictions.
TrueNegativesCalculates the number of true negatives.
TruePositivesCalculates the number of true positives.
Table of Contents

Table of Contents

← Index