|View source on GitHub|
Computes the precision at a given recall.
tf.contrib.metrics.precision_at_recall( labels, predictions, target_recall, weights=None, num_thresholds=200, metrics_collections=None, updates_collections=None, name=None )
This function creates variables to track the true positives, false positives,
true negatives, and false negatives at a set of thresholds. Among those
thresholds where recall is at least
target_recall, precision is computed
at the threshold where recall is closest to
For estimation of the metric over a stream of data, the function creates an
update_op operation that updates these variables and returns the
update_op increments the counts of true
positives, false positives, true negatives, and false negatives with the
weight of each case found in the
None, weights default to 1. Use weights of 0 to mask values.
For additional information about precision and recall, see http://en.wikipedia.org/wiki/Precision_and_recall
labels: The ground truth values, a
Tensorwhose dimensions must match
predictions. Will be cast to
predictions: A floating point
Tensorof arbitrary shape and whose values are in the range
target_recall: A scalar value in range
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
num_thresholds: The number of thresholds to use for matching the given recall.
metrics_collections: An optional list of collections to which
precisionshould be added.
updates_collections: An optional list of collections to which
update_opshould be added.
name: An optional variable_scope name.
precision: A scalar
Tensorrepresenting the precision at the given
update_op: An operation that increments the variables for tracking the true positives, false positives, true negatives, and false negatives and whose value matches
labelshave mismatched shapes, if
Noneand its shape doesn't match
predictions, or if
target_recallis not between 0 and 1, or if either
updates_collectionsare not a list or tuple.
RuntimeError: If eager execution is enabled.