|View source on GitHub|
Calculates the mean of the per-class accuracies.
tf.compat.v1.metrics.mean_per_class_accuracy( labels, predictions, num_classes, weights=None, metrics_collections=None, updates_collections=None, name=None )
Calculates the accuracy for each class, then takes the mean of that.
For estimation of the metric over a stream of data, the function creates an
update_op operation that updates the accuracy of each class and returns
None, weights default to 1. Use weights of 0 to mask values.