def test_compute():
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 = WaveHedgesDistance()
m.update((torch.from_numpy(a), torch.from_numpy(ground_truth)))
np_sum = (np.abs(ground_truth - a) /
np.maximum.reduce([a, ground_truth])).sum()
assert m.compute() == pytest.approx(np_sum)
m.update((torch.from_numpy(b), torch.from_numpy(ground_truth)))
np_sum += (np.abs(ground_truth - b) /
np.maximum.reduce([b, ground_truth])).sum()
assert m.compute() == pytest.approx(np_sum)
m.update((torch.from_numpy(c), torch.from_numpy(ground_truth)))
np_sum += (np.abs(ground_truth - c) /
np.maximum.reduce([c, ground_truth])).sum()
assert m.compute() == pytest.approx(np_sum)
m.update((torch.from_numpy(d), torch.from_numpy(ground_truth)))
np_sum += (np.abs(ground_truth - d) /
np.maximum.reduce([d, ground_truth])).sum()
assert m.compute() == pytest.approx(np_sum)
def _test(metric_device):
metric_device = torch.device(metric_device)
m = WaveHedgesDistance(device=metric_device)
torch.manual_seed(10 + rank)
y_pred = torch.randint(0, 10, size=(10,), device=device).float()
y = torch.randint(0, 10, size=(10,), device=device).float()
m.update((y_pred, y))
# gather y_pred, y
y_pred = idist.all_gather(y_pred)
y = idist.all_gather(y)
np_y_pred = y_pred.cpu().numpy()
np_y = y.cpu().numpy()
res = m.compute()
np_sum = (np.abs(np_y - np_y_pred) / (np.maximum.reduce([np_y_pred, np_y]) + 1e-30)).sum()
assert np_sum == pytest.approx(res)