tf.keras.metrics.MeanRelativeError  |  TensorFlow v2.0.0 (original) (raw)

tf.keras.metrics.MeanRelativeError

Stay organized with collections Save and categorize content based on your preferences.

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

Inherits From: Mean

View aliases

Main aliases

tf.metrics.MeanRelativeError

Compat aliases for migration

SeeMigration guide for more details.

tf.compat.v1.keras.metrics.MeanRelativeError

tf.keras.metrics.MeanRelativeError(
    normalizer, name=None, dtype=None
)

This metric creates two local variables, total and count that are used to compute the mean relative absolute error. This average is weighted bysample_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.

Usage:

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
print('Final result: ', m.result().numpy())  # Final result: 1.25

Usage with tf.keras API:

model = tf.keras.Model(inputs, outputs)
model.compile(
  'sgd',
  loss='mse',
  metrics=[tf.keras.metrics.MeanRelativeError(normalizer=[1, 3])])

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 metric statistics.