tf.keras.losses.Huber

Computes the Huber loss between y_true & y_pred.

Inherits From: Loss

tf.keras.losses.Huber(
    delta=1.0,
    reduction='sum_over_batch_size',
    name='huber_loss'
)

Used in the notebooks

Used in the tutorials
Playing CartPole with the Actor-Critic method Parametrized Quantum Circuits for Reinforcement Learning

Formula:

for x in error:
    if abs(x) <= delta:
        loss.append(0.5 * x^2)
    elif abs(x) > delta:
        loss.append(delta * abs(x) - 0.5 * delta^2)

loss = mean(loss, axis=-1)

See: Huber loss.

Args
`delta`	A float, the point where the Huber loss function changes from a quadratic to linear.
`reduction`	Type of reduction to apply to loss. Options are `"sum"`, `"sum_over_batch_size"` or `None`. Defaults to `"sum_over_batch_size"`.
`name`	Optional name for the instance.

Methods

`call`

View source

call(
    y_true, y_pred
)

`from_config`

View source

@classmethod
from_config(
    config
)

`get_config`

View source

get_config()

`call`

View source

__call__(
    y_true, y_pred, sample_weight=None
)

Call self as a function.

© 2022 The TensorFlow Authors. All rights reserved.
Licensed under the Creative Commons Attribution License 4.0.
Code samples licensed under the Apache 2.0 License.
https://www.tensorflow.org/api_docs/python/tf/keras/losses/Huber