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',
    dtype=None
)

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 the loss. In almost all cases this should be "sum_over_batch_size". Supported options are "sum", "sum_over_batch_size", "mean", "mean_with_sample_weight" or None. "sum" sums the loss, "sum_over_batch_size" and "mean" sum the loss and divide by the sample size, and "mean_with_sample_weight" sums the loss and divides by the sum of the sample weights. "none" and None perform no aggregation. Defaults to "sum_over_batch_size".
name	Optional name for the instance.
dtype	The dtype of the loss's computations. Defaults to None, which means using keras.backend.floatx(). keras.backend.floatx() is a "float32" unless set to different value (via keras.backend.set_floatx()). If a keras.DTypePolicy is provided, then the compute_dtype will be utilized.

Attributes
dtype

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.