Welcome to our Support Center

# Metric resume

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

 Β ICONS RESUME Accuracy Calculates how often predictions equal labels. BinaryAccuracy Calculates how often predictions match binary labels. BinaryCrossentropy Computes the crossentropy metric between the labels and predictions. BinaryIoU Computes the Intersection-Over-Union metric for class 0 and/or 1. CategoricalAccuracy Calculates how often predictions match one-hot labels. CategoricalCrossentropy Computes the crossentropy metric between the labels and predictions. CategoricalHinge Computes the categorical hinge metric between y_true and y_pred. CosineSimilarity Computes the cosine similarity between the labels and predictions. FalseNegatives Calculates the number of false negatives. FalsePositives Calculates the number of false positives. Hinge Computes the hinge metric between y_true and y_pred. Huber Computes the huber metrics between y_true and y_pred. IoU Computes the Intersection-Over-Union metric for specific target classes. KLDivergence Computes Kullback-Leibler divergence metric between y_true and y_pred. LogCoshError Computes the logarithm of the hyperbolic cosine of the prediction error. Mean Computes the mean of the given values. MeanAbsoluteError Computes the mean absolute error between the labels and predictions. MeanAbsolutePercentageError Computes the mean absolute percentage error between y_true and y_pred. MeanIoU Computes the mean Intersection-Over-Union metric. MeanRelativeError Computes the mean relative error by normalizing with the given values. MeanSquaredError Computes the mean squared error between y_true and y_pred. MeanSquaredLogarithmicError Computes the mean squared logarithmic error between y_true and y_pred. MeanTensor Computes the element-wise mean of the given tensors. OneHotIoU Computes the Intersection-Over-Union metric for one-hot encoded labels. OneHotMeanIoU Computes mean Intersection-Over-Union metric for one-hot encoded labels. Poisson Computes the poisson metric between y_true and y_pred. Precision Computes the precision of the predictions with respect to the labels. PrecisionAtRecall Computes best precision where recall is > specified value. Recall Computes the recall of the predictions with respect to the labels. RecallAtPrecision Computes best recall where precision is > specified value. RootMeanSquaredError Computes root mean squared error metric between y_true and y_pred. SensitivityAtSpecificity Computes best sensitivity where specificity is > specified value. SparseCategoricalAccuracy Calculates how often predictions match integer labels. SparseCategoricalCrossentropy Computes the crossentropy metric between the labels and predictions. SparseTopKCategoricalAccuracy Computes how often integer targets are in the top K predictions. Specificity Computes the specificity of the predictions with respect to the labels. SpecificityAtSensitivity Computes best specificity where sensitivity is > specified value. SquaredHinge Computes the squared hinge metric between y_true and y_pred. Sum Computes the sum of the given values. TopKCategoricalAccuracy Computes how often targets are in the top K predictions. TrueNegatives Calculates the number of true negatives. TruePositives Calculates the number of true positives.