tf.keras.losses.log_cosh

Logarithm of the hyperbolic cosine of the prediction error.

View aliases

Main aliases

tf.keras.losses.logcosh, tf.keras.metrics.log_cosh, tf.keras.metrics.logcosh, tf.losses.log_cosh, tf.losses.logcosh, tf.metrics.log_cosh, tf.metrics.logcosh

Compat aliases for migration

See Migration guide for more details.

tf.compat.v1.keras.losses.log_cosh, tf.compat.v1.keras.losses.logcosh, tf.compat.v1.keras.metrics.log_cosh, tf.compat.v1.keras.metrics.logcosh

tf.keras.losses.log_cosh(
    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.

Standalone usage:

y_true = np.random.random(size=(2, 3))
y_pred = np.random.random(size=(2, 3))
loss = tf.keras.losses.logcosh(y_true, y_pred)
assert loss.shape == (2,)
x = y_pred - y_true
assert np.allclose(
    loss.numpy(),
    np.mean(x + np.log(np.exp(-2. * x) + 1.) - math_ops.log(2.), axis=-1),
    atol=1e-5)

Args
y_true	Ground truth values. shape = [batch_size, d0, .. dN].
y_pred	The predicted values. shape = [batch_size, d0, .. dN].

Returns
Logcosh error values. shape = [batch_size, d0, .. dN-1].