RSVP for your your local TensorFlow Everywhere event today!


TensorFlow 1 version View source on GitHub

Computes the mean relative error by normalizing with the given values.

Inherits From: Mean

This metric creates two local variables, total and count that are used to compute the mean relative error. This is weighted by sample_weight, and it is ultimately returned as mean_relative_error: an idempotent operation that simply divides total by count.

If sample_weight is None, weights default to 1. Use sample_weight of 0 to mask values.


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

Usage with tf.keras API:

model = tf.keras.Model(inputs, outputs)
  metrics=[tf.keras.metrics.MeanRelativeError(normalizer=[1, 3])])

normalizer The normalizer values with same shape as predictions.
name (Optional) string name of the metric instance.
dtype (Optional) data type of the metric result.



View source

Resets all of the metric state variables.

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


View source

Computes and returns the metric value tensor.

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


View source

Accumulates metric statistics.

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.

Update op.