Module: tf.keras.metrics

Built-in metrics.

Classes

class Accuracy: Calculates how often predictions matches labels.

class BinaryAccuracy: Calculates how often predictions matches labels.

class CategoricalAccuracy: Calculates how often predictions matches labels.

class FalseNegatives: Calculates the number of false negatives.

class FalsePositives: Calculates the number of false positives.

class Mean: Computes the (weighted) mean of the given values.

class Precision: Computes the precision of the predictions with respect to the labels.

class Recall: Computes the recall of the predictions with respect to the labels.

class SensitivityAtSpecificity: Computes the sensitivity at a given specificity.

class SparseCategoricalAccuracy: Calculates how often predictions matches integer labels.

class SpecificityAtSensitivity: Computes the specificity at a given sensitivity.

class TrueNegatives: Calculates the number of true negatives.

class TruePositives: Calculates the number of true positives.

Functions

KLD(...)

MAE(...)

MAPE(...)

MSE(...)

MSLE(...)

binary_accuracy(...)

binary_crossentropy(...)

categorical_accuracy(...)

categorical_crossentropy(...)

cosine(...)

cosine_proximity(...)

deserialize(...)

get(...)

hinge(...)

kld(...)

kullback_leibler_divergence(...)

mae(...)

mape(...)

mean_absolute_error(...)

mean_absolute_percentage_error(...)

mean_squared_error(...)

mean_squared_logarithmic_error(...)

mse(...)

msle(...)

poisson(...)

serialize(...)

sparse_categorical_accuracy(...)

sparse_categorical_crossentropy(...)

sparse_top_k_categorical_accuracy(...)

squared_hinge(...)

top_k_categorical_accuracy(...)