tf.keras.metrics.MeanSquaredLogarithmicError

Computes the mean squared logarithmic error between y_true and y_pred.

name (Optional) string name of the metric instance.
dtype (Optional) data type of the metric result.

Standalone usage:

m = tf.keras.metrics.MeanSquaredLogarithmicError()
m.update_state([[0, 1], [0, 0]], [[1, 1], [0, 0]])
m.result().numpy()
0.12011322
m.reset_states()
m.update_state([[0, 1], [0, 0]], [[1, 1], [0, 0]],
               sample_weight=[1, 0])
m.result().numpy()
0.24022643

Usage with compile() API:

model.compile(
    optimizer='sgd',
    loss='mse',
    metrics=[tf.keras.metrics.MeanSquaredLogarithmicError()])

Methods

reset_states

View source

Resets all of the metric state variables.

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

result

View source

Computes and returns the metric