|View source on GitHub|
Logarithm of the hyperbolic cosine of the prediction error.
See Migration guide for more details.
tf.keras.losses.log_cosh( y_true, y_pred )
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 = np.random.random(size=(2, 3))