Missed TensorFlow World? Check out the recap. Learn more

tf.keras.losses.SquaredHinge

TensorFlow 2.0 version View source on GitHub

Class SquaredHinge

Computes the squared hinge loss between y_true and y_pred.

Aliases:

  • Class tf.compat.v1.keras.losses.SquaredHinge
  • Class tf.compat.v2.keras.losses.SquaredHinge
  • Class tf.compat.v2.losses.SquaredHinge

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.

Usage:

sh = tf.keras.losses.SquaredHinge()
loss = sh([-1., 1., 1.], [0.6, -0.7, -0.5])

# loss = (max(0, 1 - y_true * y_pred))^2 = [1.6^2 + 1.7^2 + 1.5^2] / 3

print('Loss: ', loss.numpy())  # Loss: 2.566666

Usage with tf.keras API:

model = tf.keras.Model(inputs, outputs)
model.compile('sgd', loss=tf.keras.losses.SquaredHinge())

__init__

View source

__init__(
    reduction=losses_utils.ReductionV2.AUTO,
    name='squared_hinge'
)

Methods

__call__

View source

__call__(
    y_true,
    y_pred,
    sample_weight=None
)

Invokes the Loss instance.

Args:

  • y_true: Ground truth values.
  • y_pred: The predicted values.
  • sample_weight: Optional Tensor whose rank is either 0, or the same rank as y_true, or is broadcastable to y_true. sample_weight acts as a coefficient for the loss. If a scalar is provided, then the loss is simply scaled by the given value. If sample_weight is a tensor of size [batch_size], then the total loss for each sample of the batch is rescaled by the corresponding element in the sample_weight vector. If the shape of sample_weight matches the shape of y_pred, then the loss of each measurable element of y_pred is scaled by the corresponding value of sample_weight.

Returns:

Weighted loss float Tensor. If reduction is NONE, this has the same shape as y_true; otherwise, it is scalar.

Raises:

  • ValueError: If the shape of sample_weight is invalid.

from_config

View source

from_config(
    cls,
    config
)

Instantiates a Loss from its config (output of get_config()).

Args:

  • config: Output of get_config().

Returns:

A Loss instance.

get_config

View source

get_config()