tf.contrib.metrics.sparse_recall_at_top_k(
labels,
top_k_predictions,
class_id=None,
weights=None,
metrics_collections=None,
updates_collections=None,
name=None
)
Defined in tensorflow/contrib/metrics/python/ops/metric_ops.py
.
Computes recall@k of top-k predictions with respect to sparse labels.
If class_id
is specified, we calculate recall by considering only the
entries in the batch for which class_id
is in the label, and computing
the fraction of them for which class_id
is in the top-k predictions
.
If class_id
is not specified, we'll calculate recall as how often on
average a class among the labels of a batch entry is in the top-k
predictions
.
sparse_recall_at_top_k
creates two local variables, true_positive_at_<k>
and false_negative_at_<k>
, that are used to compute the recall_at_k
frequency. This frequency is ultimately returned as recall_at_<k>
: an
idempotent operation that simply divides true_positive_at_<k>
by total
(true_positive_at_<k>
+ false_negative_at_<k>
).
For estimation of the metric over a stream of data, the function creates an
update_op
operation that updates these variables and returns the
recall_at_<k>
. Set operations applied to top_k
and labels
calculate the
true positives and false negatives weighted by weights
. Then update_op
increments true_positive_at_<k>
and false_negative_at_<k>
using these
values.
If weights
is None
, weights default to 1. Use weights of 0 to mask values.
Args:
labels
:int64
Tensor
orSparseTensor
with shape [D1, ... DN, num_labels], where N >= 1 and num_labels is the number of target classes for the associated prediction. Commonly, N=1 andlabels
has shape [batch_size, num_labels]. [D1, ... DN] must matchtop_k_predictions
. Values should be in range [0, num_classes), where num_classes is the last dimension ofpredictions
. Values outside this range always count towardsfalse_negative_at_<k>
.top_k_predictions
: IntegerTensor
with shape [D1, ... DN, k] where N >= 1. Commonly, N=1 and top_k_predictions has shape [batch size, k]. The final dimension contains the indices of top-k labels. [D1, ... DN] must matchlabels
.class_id
: Integer class ID for which we want binary metrics. This should be in range [0, num_classes), where num_classes is the last dimension ofpredictions
. If class_id is outside this range, the method returns NAN.weights
:Tensor
whose rank is either 0, or n-1, where n is the rank oflabels
. If the latter, it 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 that values should be added to.updates_collections
: An optional list of collections that updates should be added to.name
: Name of new update operation, and namespace for other dependent ops.
Returns:
recall
: Scalarfloat64
Tensor
with the value oftrue_positives
divided by the sum oftrue_positives
andfalse_negatives
.update_op
:Operation
that incrementstrue_positives
andfalse_negatives
variables appropriately, and whose value matchesrecall
.
Raises:
ValueError
: Ifweights
is notNone
and its shape doesn't matchpredictions
, or if eithermetrics_collections
orupdates_collections
are not a list or tuple.