def test_multilabel_accuracy_mean(
outputs_list: Iterable[torch.Tensor],
targets_list: Iterable[torch.Tensor],
thresholds: Union[float, torch.Tensor],
true_values_list: Iterable[float],
) -> None:
"""
This test checks that all the intermediate metrics values are correct during accumulation.
Args:
outputs_list: list of output tensors
targets_list: list of true answer tensors
thresholds: threshold
true_values_list: true intermediate metric results
"""
metric = MultilabelAccuracyMetric(threshold=thresholds)
for outputs, targets, true_value in zip(outputs_list, targets_list,
true_values_list):
metric.update(outputs=outputs, targets=targets)
mean, _ = metric.compute()
assert np.isclose(mean, true_value)
def test_multilabel_accuracy_std(
outputs_list: Iterable[torch.Tensor],
targets_list: Iterable[torch.Tensor],
thresholds: Union[float, torch.Tensor],
true_values_list: Iterable[float],
) -> None:
"""
This test checks that all the intermediate metrics values are correct during accumulation.
Note that now `accuracy/std` is not std exactly so it can fail if you fix it.
Args:
outputs_list: list of output tensors
targets_list: list of true answer tensors
thresholds: threshold
true_values_list: true intermediate metric results
"""
metric = MultilabelAccuracyMetric(threshold=thresholds)
for outputs, targets, true_value in zip(outputs_list, targets_list,
true_values_list):
metric.update(outputs=outputs, targets=targets)
_, std = metric.compute()
assert np.isclose(std, true_value)