TensorFlow 1 version View source on GitHub

Logarithm of the hyperbolic cosine of the prediction error.

    y_true, y_pred

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.