def test_mean_error():
a = np.random.randn(4)
b = np.random.randn(4)
c = np.random.randn(4)
d = np.random.randn(4)
ground_truth = np.random.randn(4)
m = MeanError()
m.update((torch.from_numpy(a), torch.from_numpy(ground_truth)))
np_sum = (ground_truth - a).sum()
np_len = len(a)
np_ans = np_sum / np_len
assert m.compute() == pytest.approx(np_ans)
m.update((torch.from_numpy(b), torch.from_numpy(ground_truth)))
np_sum += (ground_truth - b).sum()
np_len += len(b)
np_ans = np_sum / np_len
assert m.compute() == pytest.approx(np_ans)
m.update((torch.from_numpy(c), torch.from_numpy(ground_truth)))
np_sum += (ground_truth - c).sum()
np_len += len(c)
np_ans = np_sum / np_len
assert m.compute() == pytest.approx(np_ans)
m.update((torch.from_numpy(d), torch.from_numpy(ground_truth)))
np_sum += (ground_truth - d).sum()
np_len += len(d)
np_ans = np_sum / np_len
assert m.compute() == pytest.approx(np_ans)
def test_zero_sample():
m = MeanError()
with pytest.raises(
NotComputableError,
match=
r"MeanError must have at least one example before it can be computed"
):
m.compute()
def _test(metric_device):
metric_device = torch.device(metric_device)
m = MeanError(device=metric_device)
torch.manual_seed(10 + rank)
y_pred = torch.rand(size=(100,), device=device)
y = torch.rand(size=(100,), device=device)
m.update((y_pred, y))
y_pred = idist.all_gather(y_pred)
y = idist.all_gather(y)
np_y = y.cpu().numpy()
np_y_pred = y_pred.cpu().numpy()
np_sum = (np_y - np_y_pred).sum()
np_len = len(np_y_pred)
np_ans = np_sum / np_len
assert m.compute() == pytest.approx(np_ans)
def test_zero_div():
m = MeanError()
with pytest.raises(NotComputableError):
m.compute()