{ }
View source on GitHub |
Computes true negatives at provided threshold values.
tf.compat.v1.metrics.true_negatives_at_thresholds(
labels,
predictions,
thresholds,
weights=None,
metrics_collections=None,
updates_collections=None,
name=None
)
If weights
is None
, weights default to 1. Use weights of 0 to mask values.
Returns | |
---|---|
true_negatives
|
A float Tensor of shape [len(thresholds)] .
|
update_op
|
An operation that updates the true_negatives variable and
returns its current value.
|