metrics_utils#

Module containing metrics utils.

Members

get_scorers_dict(dataset[, alternative_scorers])

Get scorers list according to model object and label column.

metric_results_to_df(results, dataset)

Get dict of metric name to tensor of classes scores, and convert it to dataframe.

ObjectDetectionAveragePrecision

Calculate average precision and recall for object detection.

AveragePrecisionRecall

Abstract class to calculate average precision and recall for various vision tasks.

ObjectDetectionTpFpFn

Calculate the TP, FP, FN and runs an evaluating function on the result.

TpFpFn

Abstract class to calculate the TP, FP, FN and runs an evaluating function on the result.

AVAILABLE_EVALUATING_FUNCTIONS

CustomClassificationScorer

Scorer that runs a custom metric for the vision classification task.

CustomMetric

Abstract class for defining custom metrics.