Keras 3 API documentation
Models API Layers API Callbacks API Ops API Optimizers Metrics Base Metric class Accuracy metrics Probabilistic metrics Regression metrics Classification metrics based on True/False positives & negatives Image segmentation metrics Hinge metrics for "maximum-margin" classification Metric wrappers and reduction metrics Losses Data loading Built-in small datasets Keras Applications Mixed precision Multi-device distribution RNG API Quantizers Scope Rematerialization Utilities
Keras 2 API documentation
► Keras 3 API documentation / Metrics / Hinge metrics for "maximum-margin" classification

Hinge metrics for "maximum-margin" classification

[source]

Hinge class

keras.metrics.Hinge(name="hinge", dtype=None)

Computes the hinge metric between y_true and y_pred.

y_true values are expected to be -1 or 1. If binary (0 or 1) labels are provided we will convert them to -1 or 1.

Arguments

  • name: (Optional) string name of the metric instance.
  • dtype: (Optional) data type of the metric result.

Examples

>>> m = keras.metrics.Hinge() >>> m.update_state([[0, 1], [0, 0]], [[0.6, 0.4], [0.4, 0.6]]) >>> m.result() 1.3 >>> m.reset_state() >>> m.update_state([[0, 1], [0, 0]], [[0.6, 0.4], [0.4, 0.6]], ... sample_weight=[1, 0]) >>> m.result() 1.1

[source]

SquaredHinge class

keras.metrics.SquaredHinge(name="squared_hinge", dtype=None)

Computes the hinge metric between y_true and y_pred.

y_true values are expected to be -1 or 1. If binary (0 or 1) labels are provided we will convert them to -1 or 1.

Arguments

  • name: (Optional) string name of the metric instance.
  • dtype: (Optional) data type of the metric result.

Example

>>> m = keras.metrics.SquaredHinge() >>> m.update_state([[0, 1], [0, 0]], [[0.6, 0.4], [0.4, 0.6]]) >>> m.result() 1.86 >>> m.reset_state() >>> m.update_state([[0, 1], [0, 0]], [[0.6, 0.4], [0.4, 0.6]], ... sample_weight=[1, 0]) >>> m.result() 1.46

[source]

CategoricalHinge class

keras.metrics.CategoricalHinge(name="categorical_hinge", dtype=None)

Computes the categorical hinge metric between y_true and y_pred.

Arguments

  • name: (Optional) string name of the metric instance.
  • dtype: (Optional) data type of the metric result.

Example

>>> m = keras.metrics.CategoricalHinge() >>> m.update_state([[0, 1], [0, 0]], [[0.6, 0.4], [0.4, 0.6]]) >>> m.result().numpy() 1.4000001 >>> m.reset_state() >>> m.update_state([[0, 1], [0, 0]], [[0.6, 0.4], [0.4, 0.6]], ... sample_weight=[1, 0]) >>> m.result() 1.2
Hinge metrics for "maximum-margin" classification
Hinge class
SquaredHinge class
CategoricalHinge class