|TensorFlow 1 version||View source on GitHub|
Computes the recall of the predictions with respect to the labels.
See Migration guide for more details.
tf.keras.metrics.Recall( thresholds=None, top_k=None, class_id=None, name=None, dtype=None )
Used in the notebooks
|Used in the tutorials|
This metric creates two local variables,
false_negatives, that are used to compute the recall. This value is
ultimately returned as
recall, an idempotent operation that simply divides
true_positives by the sum of
None, weights default to 1.
sample_weight of 0 to mask values.
top_k is set, recall will be computed as how often on average a class
among the labels of a batch entry is in the top-k predictions.
class_id is specified, we calculate recall by considering only the
entries in the batch for which
class_id is in the label, and computing the
fraction of them for which
class_id is above the threshold and/or in the
(Optional) A float value or a python list/tuple of float
threshold values in [0, 1]. A threshold is compared with prediction
values to determine the truth value of predictions (i.e., above the
||(Optional) Unset by default. An int value specifying the top-k predictions to consider when calculating recall.|
(Optional) Integer class ID for which we want binary metrics.
This must be in the half-open interval
||(Optional) string name of the metric instance.|
||(Optional) data type of the metric result.|
m = tf.keras.metrics.Recall()
m.update_state([0, 1, 1, 1], [1, 0, 1, 1])
m.update_state([0, 1, 1, 1], [1, 0, 1, 1], sample_weight=[0, 0, 1, 0])
model.compile(optimizer='sgd', loss='mse', metrics=[tf.keras.metrics.Recall()])
Resets all of the metric state variables.
This function is called between epochs/steps, when a metric is evaluated during training.