tfma.metrics.MaxRecall

Computes the max recall of the predictions with respect to the labels.

Inherits From: Recall, Metric

The metric uses true positives and false negatives to compute recall by dividing the true positives by the sum of true positives and false negatives.

Effectively the recall at threshold = epsilon(1.0e-12). It is equilvalent to the recall defined in COCO metrics.

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

top_k (Optional) Used with a multi-class model to specify that the top-k values should be used to compute the confusion matrix. The net effect is that the non-top-k values are set to -inf and the matrix is then constructed from the average TP, FP, TN, FN across the classes. When top_k is used, metrics_specs.binarize settings must not be present. Only one of class_id or top_k should be configured.
class_id (Optional) Used with a multi-class model to specify which class to compute the confusion matrix for. When class_id is used, metrics_specs.binarize settings must not be present. Only one of class_id or top_k should be configured.
name (Optional) string name of the metric instance.
use_object_detection whether this problem is object detection or not. If it is, then we are expecting object_class_id(required), iou_thresholds, and area_range arguments.
iou_threshold (Optional) Used for object detection, thresholds for a detection and ground truth pair with specific iou to be considered as a match. Default to 0.5
object_class_id (Optional) Used for object detection, the class id for calculating metrics. It must be provided if use_object_detection is True.
object_class_weight (Optional) Used for object detection, the weight associated with the object class id.
area_range (Optional) Used for object detection, a tuple (inclusive) representing the area-range for objects to be considered for metrics. Default to (0, inf).
max_num_detections (Optional) Used for object detection, the maximum number of detections for a single image. Default to None.

compute_confidence_interval Whether to compute confidence intervals for this metric.

Note that this may not completely remove the computational overhead involved in computing a given metric. This is only respected by the jackknife confidence interval method.

Methods

computations

View source

Creates computations associated with metric.

get_config

View source

Returns serializable config.

result

View source

Function for computing metric value from TP, TN, FP, FN values.