tf.compat.v1.metrics.mean_tensor

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

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

tf.compat.v1.metrics.mean_tensor(
    values,
    weights=None,
    metrics_collections=None,
    updates_collections=None,
    name=None
)

In contrast to the mean function which returns a scalar with the mean, this function returns an average tensor with the same shape as the input tensors.

The mean_tensor function creates two local variables,total_tensor and count_tensor that are used to compute the average ofvalues. This average is ultimately returned as mean which is an idempotent operation that simply divides total by count.

For estimation of the metric over a stream of data, the function creates anupdate_op operation that updates these variables and returns the mean.update_op increments total with the reduced sum of the product of valuesand weights, and it increments count with the reduced sum of weights.

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

Args
values	A Tensor of arbitrary dimensions.
weights	Optional Tensor whose rank is either 0, or the same rank asvalues, and must be broadcastable to values (i.e., all dimensions must be either 1, or the same as the corresponding values dimension).
metrics_collections	An optional list of collections that meanshould be added to.
updates_collections	An optional list of collections that update_opshould be added to.
name	An optional variable_scope name.

Returns
mean	A float Tensor representing the current mean, the value of totaldivided by count.
update_op	An operation that increments the total and count variables appropriately and whose value matches mean_value.

Raises
ValueError	If weights is not None and its shape doesn't match values, or if either metrics_collections or updates_collections are not a list or tuple.
RuntimeError	If eager execution is enabled.

tf.compat.v1.metrics.mean_tensor | TensorFlow v2.16.1 (original) (raw)