tf.keras.losses.hinge

TensorFlow 2 version View source on GitHub

Computes the hinge loss between y_true and y_pred.

Main aliases

tf.keras.metrics.hinge

Compat aliases for migration

See Migration guide for more details.

tf.compat.v1.keras.losses.hinge, tf.compat.v1.keras.metrics.hinge, `tf.compat.v2.keras.losses.hinge`, `tf.compat.v2.keras.metrics.hinge`, `tf.compat.v2.losses.hinge`, `tf.compat.v2.metrics.hinge`

 
tf.keras.losses.hinge(
    y_true, y_pred
)

y_true The ground truth values. y_true values are expected to be -1 or 1. If binary (0 or 1) labels are provided they will be converted to -1 or 1.
y_pred The predicted values.

Tensor with one scalar loss entry per sample.