def test_duplicate_detections(self):
gt = make_representation(["0 0 0 5 5"], is_ground_truth=True)
pred = make_representation(["0 0 0 5 5; 0 0 0 5 5"], score=1)
metric = _test_metric_wrapper(Recall, single_class_dataset())
assert 1 == metric(gt, pred)[0]
assert metric.meta.get('names') == ['dog']
def test_false_negative(self):
gt = make_representation(["0 10 10 20 20; 0 0 0 5 5"],
is_ground_truth=True)
pred = make_representation(["0 0 0 5 5"], score=1)
metric = _test_metric_wrapper(Recall, single_class_dataset())
assert 0.5 == metric(gt, pred)[0]
assert metric.meta.get('names') == ['dog']
def test_selects_all_detections(self):
gt = make_representation(["0 0 0 5 5"], is_ground_truth=True)
pred = make_representation(["0 0 0 5 5; 0 0 0 5 5"], score=1)
metric = _test_metric_wrapper(DetectionMAP, single_class_dataset())
metric(gt, pred)
assert not metric.distinct_conf
assert metric.overlap_threshold == 0.5
assert metric.ignore_difficult
assert metric.meta.get('names') == ['dog']
def test_false_positive(self):
gt2 = make_representation(["0 10 10 20 20"], is_ground_truth=True)
pred2 = make_representation(["0 0 0 5 5"], score=1)
metric = _test_metric_wrapper(Recall, single_class_dataset())
assert 0 == metric(gt2, pred2)[0]
assert metric.meta.get('names') == ['dog']
gt1 = make_representation(["0 0 0 5 5"], is_ground_truth=True)
pred1 = make_representation(["0 0 0 5 5; 0 10 10 20 20"], score=1)
assert 1 == metric(gt1, pred1)[0]
assert metric.meta.get('names') == ['dog']
def test_two_objects(self):
gt = make_representation(["0 0 0 5 5; 0 10 10 20 20"],
is_ground_truth=True)
pred = make_representation(["0 0 0 5 5; 0 10 10 20 20"], score=1)
assert 1 == _test_metric_wrapper(Recall,
single_class_dataset())(gt, pred)[0]
