tf.keras.losses.squared_hinge

TensorFlow 1 version View source on GitHub

Computes the squared hinge loss between y_true and y_pred.

Main aliases

tf.keras.metrics.squared_hinge, tf.losses.squared_hinge, tf.metrics.squared_hinge

Compat aliases for migration

See Migration guide for more details.

tf.compat.v1.keras.losses.squared_hinge, tf.compat.v1.keras.metrics.squared_hinge

 
tf.keras.losses.squared_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 we will convert them to -1 or 1.
y_pred The predicted values.

Tensor with one scalar loss entry per sample.