![]() |
Computes various fnr values for different thresholds
on predictions
.
tf.contrib.metrics.streaming_false_negative_rate_at_thresholds(
predictions,
labels,
thresholds,
weights=None,
metrics_collections=None,
updates_collections=None,
name=None
)
The streaming_false_negative_rate_at_thresholds
function creates two
local variables, false_negatives
, true_positives
, for various values of
thresholds. false_negative_rate[i]
is defined as the total weight
of values in predictions
above thresholds[i]
whose corresponding entry in
labels
is False
, divided by the total weight of True
values in labels
(false_negatives[i] / (false_negatives[i] + true_positives[i])
).
For estimation of the metric over a stream of data, the function creates an
update_op
operation that updates these variables and returns the
false_positive_rate
.
If weights
is None
, weights default to 1. Use weights of 0 to mask values.
Args:
predictions
: A floating pointTensor
of arbitrary shape and whose values are in the range[0, 1]
.labels
: Abool
Tensor
whose shape matchespredictions
.thresholds
: A python list or tuple of float thresholds in[0, 1]
.weights
:Tensor
whose rank is either 0, or the same rank aslabels
, and must be broadcastable tolabels
(i.e., all dimensions must be either1
, or the same as the correspondinglabels
dimension).metrics_collections
: An optional list of collections thatfalse_negative_rate
should be added to.updates_collections
: An optional list of collections thatupdate_op
should be added to.name
: An optional variable_scope name.
Returns:
false_negative_rate
: A floatTensor
of shape[len(thresholds)]
.update_op
: An operation that increments thefalse_negatives
andtrue_positives
variables that are used in the computation offalse_negative_rate
.
Raises:
ValueError
: Ifpredictions
andlabels
have mismatched shapes, or ifweights
is notNone
and its shape doesn't matchpredictions
, or if eithermetrics_collections
orupdates_collections
are not a list or tuple.