tf.metrics.mean_tensor( values, weights=None, metrics_collections=None, updates_collections=None, name=None )
Computes the element-wise (weighted) mean of the given tensors.
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
mean_tensor function creates two local variables,
count_tensor that are used to compute the average of
values. This average is ultimately returned as
mean which is an idempotent
operation that simply divides
For estimation of the metric over a stream of data, the function creates an
update_op operation that updates these variables and returns the
total with the reduced sum of the product of
weights, and it increments
count with the reduced sum of
None, weights default to 1. Use weights of 0 to mask values.
Tensorof arbitrary dimensions.
Tensorwhose rank is either 0, or the same rank as
values, and must be broadcastable to
values(i.e., all dimensions must be either
1, or the same as the corresponding
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.
mean: A float
Tensorrepresenting the current mean, the value of
update_op: An operation that increments the
countvariables appropriately and whose value matches
Noneand its shape doesn't match
values, or if either
updates_collectionsare not a list or tuple.
RuntimeError: If eager execution is enabled.