|TensorFlow 1 version||View source on GitHub|
Computes the mean relative error by normalizing with the given values.
See Migration guide for more details.
tf.keras.metrics.MeanRelativeError( normalizer, name=None, dtype=None )
This metric creates two local variables,
count that are used to
compute the mean relative error. This is weighted by
it is ultimately returned as
an idempotent operation that simply divides
None, weights default to 1.
sample_weight of 0 to mask values.
||The normalizer values with same shape as predictions.|
||(Optional) string name of the metric instance.|
||(Optional) data type of the metric result.|
m = tf.keras.metrics.MeanRelativeError(normalizer=[1, 3, 2, 3])
m.update_state([1, 3, 2, 3], [2, 4, 6, 8])
# metric = mean(|y_pred - y_true| / normalizer)
# = mean([1, 1, 4, 5] / [1, 3, 2, 3]) = mean([1, 1/3, 2, 5/3])
# = 5/4 = 1.25
model.compile( optimizer='sgd', loss='mse', metrics=[tf.keras.metrics.MeanRelativeError(normalizer=[1, 3])])
merge_state( metrics )
Merges the state from one or more metrics.
This method can be used by distributed systems to merge the state computed by different metric instances. Typically the state will be stored in the form of the metric's weights. For example, a tf.keras.metrics.Mean metric contains a list of two weight values: a total and a count. If there were two instances of a tf.keras.metrics.Accuracy that each independently aggregated partial state for an overall accuracy calculation, these two metric's states could be combined as follows:
m1 = tf.keras.metrics.Accuracy()
_ = m1.update_state([, ], [, ])
m2 = tf.keras.metrics.Accuracy()
_ = m2.update_state([, ], [, ])
||an iterable of metrics. The metrics must have compatible state.|
||If the provided iterable does not contain metrics matching the metric's required specifications.|
Resets all of the metric state variables.
This function is called between epochs/steps, when a metric is evaluated during training.