About Keras Getting started Developer guides Keras 3 API documentation Keras 2 API documentation Models API Layers API Callbacks API Optimizers Metrics Accuracy metrics Probabilistic metrics Regression metrics Classification metrics based on True/False positives & negatives Image segmentation metrics Hinge metrics for "maximum-margin" classification Losses Data loading Built-in small datasets Keras Applications Mixed precision Utilities Code examples KerasTuner: Hyperparameter Tuning KerasHub: Pretrained Models KerasCV: Computer Vision Workflows KerasNLP: Natural Language Workflows
► Keras 2 API documentation / Metrics

Metrics

Accuracy metrics

  • Accuracy class
  • BinaryAccuracy class
  • CategoricalAccuracy class
  • SparseCategoricalAccuracy class
  • TopKCategoricalAccuracy class
  • SparseTopKCategoricalAccuracy class

Probabilistic metrics

  • BinaryCrossentropy class
  • CategoricalCrossentropy class
  • SparseCategoricalCrossentropy class
  • KLDivergence class
  • Poisson class

Regression metrics

  • MeanSquaredError class
  • RootMeanSquaredError class
  • MeanAbsoluteError class
  • MeanAbsolutePercentageError class
  • MeanSquaredLogarithmicError class
  • CosineSimilarity class
  • LogCoshError class

Classification metrics based on True/False positives & negatives

  • AUC class
  • Precision class
  • Recall class
  • TruePositives class
  • TrueNegatives class
  • FalsePositives class
  • FalseNegatives class
  • PrecisionAtRecall class
  • SensitivityAtSpecificity class
  • SpecificityAtSensitivity class

Image segmentation metrics

  • MeanIoU class

Hinge metrics for "maximum-margin" classification

  • Hinge class
  • SquaredHinge class
  • CategoricalHinge class
Metrics
Accuracy metrics
Probabilistic metrics
Regression metrics
Classification metrics based on True/False positives & negatives
Image segmentation metrics
Hinge metrics for "maximum-margin" classification
Terms | Privacy