tf.keras.losses.logcosh

View source on GitHub

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.

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

Tensor with one scalar loss entry per sample.