tf.keras.metrics.RootMeanSquaredError

TensorFlow 1 version View source on GitHub

Computes root mean squared error metric between y_true and y_pred.

Inherits From: Mean

tf.keras.metrics.RootMeanSquaredError(
    name='root_mean_squared_error', dtype=None
)

Usage:

m = tf.keras.metrics.RootMeanSquaredError() 
_ = m.update_state([[0, 1], [0, 0]], [[1, 1], [0, 0]]) 
m.result().numpy() 
0.5 
m.reset_states() 
_ = m.update_state([[0, 1], [0, 0]], [[1, 1], [0, 0]], 
                   sample_weight=[1, 0]) 
m.result().numpy() 
0.70710677 

Usage with tf.keras API:

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

Args:

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

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()

Computes and returns the metric value tensor.

Result computation is an idempotent operation that simply calculates the metric value using the state variables.

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.