MeanAverageRecallReport

class MeanAverageRecallReport

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

Parameters

area_range: tuple, default: (32**2, 96**2)

Slices for small/medium/large buckets.

__init__(area_range: Tuple = (1024, 9216), **kwargs)

__new__(*args, **kwargs)

Methods

MeanAverageRecallReport.add_condition(name, ...)	Add new condition function to the check.
MeanAverageRecallReport.add_condition_test_average_recall_greater_than(...)	Add condition - AR score is greater than given score.
MeanAverageRecallReport.clean_conditions()	Remove all conditions from this check instance.
MeanAverageRecallReport.compute(context, ...)	Compute the metric result using the ignite metrics compute method and create display.
MeanAverageRecallReport.conditions_decision(result)	Run conditions on given result.
MeanAverageRecallReport.config([...])	Return check configuration (conditions' configuration not yet supported).
MeanAverageRecallReport.from_config(conf[, ...])	Return check object from a CheckConfig object.
MeanAverageRecallReport.from_json(conf[, ...])	Deserialize check instance from JSON string.
MeanAverageRecallReport.initialize_run(context)	Initialize run by asserting task type and initializing metric.
MeanAverageRecallReport.metadata([with_doc_link])	Return check metadata.
MeanAverageRecallReport.name()	Name of class in split camel case.
MeanAverageRecallReport.params([show_defaults])	Return parameters to show when printing the check.
MeanAverageRecallReport.remove_condition(index)	Remove given condition by index.
MeanAverageRecallReport.run(dataset[, ...])	Run check.
MeanAverageRecallReport.to_json([indent, ...])	Serialize check instance to JSON string.
MeanAverageRecallReport.update(context, ...)	Update the metrics by passing the batch to ignite metric update method.

Examples

Mean Average Recall Report

previous

MeanAveragePrecisionReport.update

next

MeanAverageRecallReport.add_condition