80e5ce816b6bf170c1f2a962e455bcd88bc11795,tests/ignite/contrib/metrics/test_average_precision.py,,_test_distrib_binary_input_N,#Any#,205

Before Change

        assert isinstance(res, float)
        assert average_precision_score(np_y, np_y_pred) == pytest.approx(res)

    test_cases = [
        (torch.randint(0, 2, size=(10,)).long(), torch.randint(0, 2, size=(10,)).long(), 1),
        (torch.randint(0, 2, size=(100,)).long(), torch.randint(0, 2, size=(100,)).long(), 1),
        (torch.randint(0, 2, size=(10, 1)).long(), torch.randint(0, 2, size=(10, 1)).long(), 1),
        (torch.randint(0, 2, size=(100, 1)).long(), torch.randint(0, 2, size=(100, 1)).long(), 1),
        // updated batches
        (torch.randint(0, 2, size=(10,)).long(), torch.randint(0, 2, size=(10,)).long(), 16),
        (torch.randint(0, 2, size=(100,)).long(), torch.randint(0, 2, size=(100,)).long(), 16),
        (torch.randint(0, 2, size=(10, 1)).long(), torch.randint(0, 2, size=(10, 1)).long(), 16),
        (torch.randint(0, 2, size=(100, 1)).long(), torch.randint(0, 2, size=(100, 1)).long(), 16),
    ]

    for y_pred, y, batch_size in test_cases:
        for _ in range(3):
            _test(y_pred, y, batch_size, "cpu")
            if device.type != "xla":
                _test(y_pred, y, batch_size, idist.device())


def _test_distrib_multilabel_input_N(device):

    rank = idist.get_rank()
    torch.manual_seed(12)

After Change

        ]
        return test_cases

    for _ in range(3):
        test_cases = get_test_cases()
        for y_pred, y, batch_size in test_cases:
            _test(y_pred, y, batch_size, "cpu")
            if device.type != "xla":
                _test(y_pred, y, batch_size, idist.device())


def _test_distrib_multilabel_input_N(device):

    rank = idist.get_rank()
    torch.manual_seed(12)

Instances