tf.contrib.metrics.streaming_sparse_precision_at_top_k( top_k_predictions, labels, class_id=None, weights=None, metrics_collections=None, updates_collections=None, name=None )
See the guide: Metrics (contrib) > Metric
Computes [email protected] of top-k predictions with respect to sparse labels.
class_id is not specified, we calculate precision as the ratio of true positives (i.e., correct predictions, items in
top_k_predictions that are found in the corresponding row in
labels) to positives (all
class_id is specified, we calculate precision by considering only the rows in the batch for which
class_id is in the top
predictions, and computing the fraction of them for which
class_id is in the corresponding row in
We expect precision to decrease as
streaming_sparse_precision_at_top_k creates two local variables,
false_positive_at_k, that are used to compute the [email protected] frequency. This frequency is ultimately returned as
precision_at_k: an idempotent operation that simply divides
true_positive_at_k by total (
For estimation of the metric over a stream of data, the function creates an
update_op operation that updates these variables and returns the
precision_at_k. Internally, set operations applied to
labels calculate the true positives and false positives weighted by
false_positive_at_k using these values.
None, weights default to 1. Use weights of 0 to mask values.
Tensorwith 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 match
SparseTensorwith shape [D1, ... DN, num_labels], where N >= 1 and num_labels is the number of target classes for the associated prediction. Commonly, N=1 and
labelshas shape [batch_size, num_labels]. [D1, ... DN] must match
top_k_predictions. Values should be in range [0, num_classes), where num_classes is the last dimension of
predictions. Values outside this range are ignored.
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 of
class_idis outside this range, the method returns NAN.
Tensorwhose rank is either 0, or n-1, where n is the rank of
labels. If the latter, it 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 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.
Tensorwith the value of
true_positivesdivided by the sum of
false_positivesvariables appropriately, and whose value matches
Noneand its shape doesn't match
predictions, or if either
updates_collectionsare not a list or tuple.
top_k_predictionshas rank < 2.
© 2018 The TensorFlow Authors. All rights reserved.
Licensed under the Creative Commons Attribution License 3.0.
Code samples licensed under the Apache 2.0 License.