Package ai.djl.training.evaluator
Contains classes for evaluating the effectiveness of models.
It contains a main interface Evaluator
and various
evaluators that extend it. More evaluators are located within ai.djl.training.loss
which
have the additional property that those evaluators are suited for training.
-
Class Summary Class Description AbstractAccuracy Accuracy
is anEvaluator
that computes the accuracy score.Accuracy Accuracy
is theAbstractAccuracy
with multiple classes.BinaryAccuracy BinaryAccuracy
is theAbstractAccuracy
with two classes.BoundingBoxError BoundingBoxError
is anEvaluator
that computes the error in the prediction of bounding boxes in SingleShotDetection model.Coverage Coverage for a Regression problem: it measures the percent of predictions greater than the actual target, to determine whether the predictor is over-forecasting or under-forecasting.Evaluator Base class for allEvaluator
s that can be used to evaluate the performance of a model.IndexEvaluator SingleShotDetectionAccuracy SingleShotDetectionAccuracy
is an implementation ofAbstractAccuracy
.TopKAccuracy TopKAccuracy
is anEvaluator
that computes the accuracy of the top k predictions.