TF 2.0 is out! Get hands-on practice at TF World, Oct 28-31. Use code TF20 for 20% off select passes. Register now

tf.keras.metrics.Mean

TensorFlow 1 version View source on GitHub

Class Mean

Computes the (weighted) mean of the given values.

Aliases:

Used in the guide:

Used in the tutorials:

For example, if values is [1, 3, 5, 7] then the mean is 4. If the weights were specified as [1, 1, 0, 0] then the mean would be 2.

This metric creates two variables, total and count that are used to compute the average of values. This average is ultimately returned as mean which is 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.Mean()
m.update_state([1, 3, 5, 7])
print('Final result: ', m.result().numpy())  # Final result: 4.0

Usage with tf.keras API:

model = tf.keras.Model(inputs, outputs)
model.add_metric(tf.keras.metrics.Mean(name='mean_1')(outputs))
model.compile('sgd', loss='mse')

__init__

View source

__init__(
    name='mean',
    dtype=None
)

Creates a Mean instance.

Args:

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

__new__

View source

__new__(
    cls,
    *args,
    **kwargs
)

Create and return a new object. See help(type) for accurate signature.

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(
    values,
    sample_weight=None
)

Accumulates statistics for computing the reduction metric.

For example, if values is [1, 3, 5, 7] and reduction=SUM_OVER_BATCH_SIZE, then the value of result() is 4. If the sample_weight is specified as [1, 1, 0, 0] then value of result() would be 2.

Args:

  • values: Per-example value.
  • sample_weight: Optional weighting of each example. Defaults to 1.

Returns:

Update op.