tf.keras.losses.logcosh

tf.keras.losses.logcosh(
    y_true,
    y_pred
)

Defined in tensorflow/python/keras/_impl/keras/losses.py.

Logarithm of the hyperbolic cosine of the prediction error.

log(cosh(x)) is approximately equal to (x ** 2) / 2 for small x and to abs(x) - log(2) for large x. This means that 'logcosh' works mostly like the mean squared error, but will not be so strongly affected by the occasional wildly incorrect prediction.

Arguments:

• y_true: tensor of true targets.
• y_pred: tensor of predicted targets.

Returns:

Tensor with one scalar loss entry per sample.