tf.keras.losses.LogCosh

Computes the logarithm of the hyperbolic cosine of the prediction error.

Inherits From: Loss

tf.keras.losses.LogCosh(
    reduction='sum_over_batch_size', name='log_cosh'
)

Formula:

error = y_pred - y_true
logcosh = mean(log((exp(error) + exp(-error))/2), axis=-1)`

where x is the error y_pred - y_true.

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.