ML Community Day is November 9! Join us for updates from TensorFlow, JAX, and more Learn more


TensorFlow 1 version View source on GitHub

Computes the element-wise (weighted) mean of the given tensors.

Inherits From: Metric

MeanTensor returns a tensor with the same shape of the input tensors. The mean value is updated by keeping local variables total and count. The total tracks the sum of the weighted values, and count stores the sum of the weighted counts.


m = tf.keras.metrics.MeanTensor()
m.update_state([0, 1, 2, 3])
m.update_state([4, 5, 6, 7])
print('Result: ', m.result().numpy())  # Result: [2, 3, 4, 5]
m.update_state([12, 10, 8, 6], sample_weights= [0, 0.2, 0.5, 1])
print('Result: ', m.result().numpy())  # Result: [2, 3.636, 4.8, 5.333]

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 statistics for computing the element-wise mean.

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

Update op.