model_evaluation#

Module containing the model evaluation checks in the vision package.

Classes

TrainTestPredictionDrift

The TrainTestPredictionDrift check is deprecated and will be removed in the 0.14 version.

PredictionDrift

Calculate prediction drift between train dataset and test dataset, using statistical measures.

ClassPerformance

Summarize given metrics on a dataset and model.

ConfusionMatrixReport

Calculate the confusion matrix of the model on the given dataset.

MeanAveragePrecisionReport

Summarize mean average precision metrics on a dataset and model per IoU and bounding box area.

MeanAverageRecallReport

Summarize mean average recall metrics on a dataset and model per detections and area range.

SimpleModelComparison

Compare given model score to simple model score (according to given model type).

SingleDatasetPerformance

Calculate performance metrics of a given model on a given dataset.

WeakSegmentsPerformance

Search for segments with low performance scores.