tf.keras.losses.logcosh( y_true, y_pred )
Logarithm of the hyperbolic cosine of the prediction error.
log(cosh(x)) is approximately equal to
(x ** 2) / 2 for small
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.