ROC Curve

The Receiver Operating Characteristic (ROC) curve evaluates the model performances at different threshold values by considering two parameters, the true positive rate and the false positive rate, which are defined as:

true_positive_rate = tp/(tp + fn) = recall
false_positive_rate = fp/(fp + tn)

roc_curve

Example

from odin.classes import Curves

my_curve = Curves.ROC_CURVE
# use my_curve as 'curve' parameter in the analyses

Tasks supported

Binary Classification	Single-label Classification	Multi-label Classification	Object Detection	Instance Segmentation
yes	yes	yes	no	no