TensorFlow 2.0 Beta is available Learn more

tf.keras.metrics.RootMeanSquaredError

TensorFlow 2.0 version View source on GitHub

Class RootMeanSquaredError

Computes root mean squared error metric between y_true and y_pred.

Inherits From: Mean

Aliases:

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

Usage:

m = tf.keras.metrics.RootMeanSquaredError()
m.update_state([2., 4., 6.], [1., 3., 2.])
print('Final result: ', m.result().numpy())  # Final result: 2.449

Usage with tf.keras API:

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

__init__

View source

__init__(
    name='root_mean_squared_error',
    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 root mean squared error statistics.

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.