Missed TensorFlow World? Check out the recap. Learn more

tf.keras.metrics.LogCoshError

TensorFlow 2.0 version View source on GitHub

Class LogCoshError

Computes the logarithm of the hyperbolic cosine of the prediction error.

Aliases:

  • Class tf.compat.v1.keras.metrics.LogCoshError
  • Class tf.compat.v2.keras.metrics.LogCoshError
  • Class tf.compat.v2.metrics.LogCoshError

logcosh = log((exp(x) + exp(-x))/2), where x is the error (y_pred - y_true)

Usage:

m = tf.keras.metrics.LogCoshError()
m.update_state([0., 1., 1.], [1., 0., 1.])
print('Final result: ', m.result().numpy())  # Final result: 0.289

Usage with tf.keras API:

model = tf.keras.Model(inputs, outputs)
model.compile('sgd', metrics=[tf.keras.metrics.LogCoshError()])

__init__

View source

__init__(
    name='logcosh',
    dtype=None
)

Methods

reset_states

View source

reset_states()

Resets all of the metric state variables.

This function is called between epochs/steps, when a metric is evaluated during training.

result

View source

result()

update_state

View source

update_state(
    y_true,
    y_pred,
    sample_weight=None
)

Accumulates metric statistics.

y_true and y_pred should have the same shape.

Args:

  • y_true: The ground truth values.
  • y_pred: The predicted values.
  • sample_weight: Optional weighting of each example. Defaults to 1. Can be a Tensor whose rank is either 0, or the same rank as y_true, and must be broadcastable to y_true.

Returns:

Update op.