TF 2.0 is out! Get hands-on practice at TF World, Oct 28-31. Use code TF20 for 20% off select passes. Register now


View source on GitHub

Computes the false positive rate of predictions with respect to labels.


The false_positive_rate function creates two local variables, false_positives and true_negatives, that are used to compute the false positive rate. This value is ultimately returned as false_positive_rate, an idempotent operation that simply divides false_positives by the sum of false_positives and true_negatives.

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. update_op weights each prediction by the corresponding value in weights.

If weights is None, weights default to 1. Use weights of 0 to mask values.


  • predictions: The predicted values, a Tensor of arbitrary dimensions. Will be cast to bool.
  • labels: The ground truth values, a Tensor whose dimensions must match predictions. Will be cast to bool.
  • weights: Optional Tensor whose rank is either 0, or the same rank as labels, and must be broadcastable to labels (i.e., all dimensions must be either 1, or the same as the corresponding labels dimension).
  • metrics_collections: An optional list of collections that false_positive_rate should be added to.
  • updates_collections: An optional list of collections that update_op should be added to.
  • name: An optional variable_scope name.


  • false_positive_rate: Scalar float Tensor with the value of false_positives divided by the sum of false_positives and true_negatives.
  • update_op: Operation that increments false_positives and true_negatives variables appropriately and whose value matches false_positive_rate.


  • ValueError: If predictions and labels have mismatched shapes, or if weights is not None and its shape doesn't match predictions, or if either metrics_collections or updates_collections are not a list or tuple.