|View source on GitHub|
Calculates how often
tf.contrib.metrics.streaming_accuracy( predictions, labels, weights=None, metrics_collections=None, updates_collections=None, name=None )
streaming_accuracy function creates two local variables,
count that are used to compute the frequency with which
labels. This frequency is ultimately returned as
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
is_correct operation computes a
Tensor with elements 1.0
where the corresponding elements of
labels match and 0.0
total with the reduced sum of the
is_correct, and it increments
count with the
reduced sum of
None, weights default to 1. Use weights of 0 to mask values.
predictions: The predicted values, a
Tensorof any shape.
labels: The ground truth values, a
Tensorwhose shape matches
Tensorwhose rank is either 0, or the same rank as
labels, and must be broadcastable to
labels(i.e., all dimensions must be either
1, or the same as the corresponding
metrics_collections: An optional list of collections that
accuracyshould be added to.
updates_collections: An optional list of collections that
update_opshould be added to.
name: An optional variable_scope name.
Tensorrepresenting the accuracy, the value of
update_op: An operation that increments the
countvariables appropriately and whose value matches
labelshave mismatched shapes, or if
Noneand its shape doesn't match
predictions, or if either
updates_collectionsare not a list or tuple.