tf.contrib.metrics.streaming_mean_cosine_distance( predictions, labels, dim, weights=None, metrics_collections=None, updates_collections=None, name=None )
See the guide: Metrics (contrib) > Metric
Computes the cosine distance between the labels and predictions.
streaming_mean_cosine_distance function creates two local variables,
count that are used to compute the average cosine distance
labels. This average is weighted by
and it is ultimately returned as
mean_distance, which is an 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
None, weights default to 1. Use weights of 0 to mask values.
Tensorof the same shape as
Tensorof arbitrary shape.
dim: The dimension along which the cosine distance is computed.
weights: An optional
Tensorwhose shape is broadcastable to
predictions, and whose dimension
metrics_collections: An optional list of collections that the metric value variable should be added to.
updates_collections: An optional list of collections that the metric update ops should be added to.
name: An optional variable_scope name.
Tensorrepresenting the current mean, the value of
update_op: An operation that increments the
labelshave mismatched shapes, or if
Noneand its shape doesn't match
predictions, or if either
updates_collectionsare not a list or tuple.