def test_points_noweights(self, batch_size, num_points, device, dtype):
B, N = batch_size, num_points
points1 = torch.rand(B, N, 2, device=device, dtype=dtype)
points2 = torch.rand(B, N, 2, device=device, dtype=dtype)
weights = torch.ones(B, N, device=device, dtype=dtype)
H_noweights = find_homography_dlt(points1, points2, None)
H_withweights = find_homography_dlt(points1, points2, weights)
assert H_noweights.shape == (B, 3, 3) and H_withweights.shape == (B, 3,
3)
assert_allclose(H_noweights, H_withweights, rtol=1e-3, atol=1e-4)
def test_shape(self, batch_size, num_points, device, dtype):
B, N = batch_size, num_points
points1 = torch.rand(B, N, 2, device=device, dtype=dtype)
points2 = torch.rand(B, N, 2, device=device, dtype=dtype)
weights = torch.ones(B, N, device=device, dtype=dtype)
H = find_homography_dlt(points1, points2, weights)
assert H.shape == (B, 3, 3)
def test_clean_points_and_gradcheck(self, batch_size, device):
# generate input data
H = (torch.eye(3, device=device)[None].repeat(batch_size, 1, 1) +
0.3 * torch.rand(batch_size, 3, 3, device=device))
H = H / H[:, 2:3, 2:3]
points_src = torch.rand(batch_size, 10, 2).to(device)
points_dst = kornia.transform_points(H, points_src)
weights = torch.ones(batch_size, 10, device=device)
# compute transform from source to target
dst_homo_src = find_homography_dlt(points_src, points_dst, weights)
assert_allclose(kornia.transform_points(dst_homo_src, points_src),
points_dst,
rtol=1e-3,
atol=1e-4)
# compute gradient check
points_src = utils.tensor_to_gradcheck_var(points_src) # to var
points_dst = utils.tensor_to_gradcheck_var(points_dst) # to var
weights = utils.tensor_to_gradcheck_var(weights) # to var
assert gradcheck(find_homography_dlt,
(points_src, points_dst, weights),
rtol=1e-1,
atol=1e-5,
raise_exception=True)
def test_nocrash(self, device, dtype):
points1 = torch.rand(1, 4, 2, device=device, dtype=dtype)
points2 = torch.rand(1, 4, 2, device=device, dtype=dtype)
weights = torch.ones(1, 4, device=device, dtype=dtype)
points1[0, 0, 0] = float('nan')
H = find_homography_dlt(points1, points2, weights)
assert H.shape == (1, 3, 3)
def test_clean_points(self, batch_size, device, dtype):
# generate input data
points_src = torch.rand(batch_size, 10, 2, device=device, dtype=dtype)
H = kornia.eye_like(3, points_src)
H = H * 0.3 * torch.rand_like(H)
H = H / H[:, 2:3, 2:3]
points_dst = kornia.transform_points(H, points_src)
weights = torch.ones(batch_size, 10, device=device, dtype=dtype)
# compute transform from source to target
dst_homo_src = find_homography_dlt(points_src, points_dst, weights)
assert_allclose(kornia.transform_points(dst_homo_src, points_src),
points_dst,
rtol=1e-3,
atol=1e-4)
def test_smoke(self, device, dtype):
points1 = torch.rand(1, 4, 2, device=device, dtype=dtype)
points2 = torch.rand(1, 4, 2, device=device, dtype=dtype)
weights = torch.ones(1, 4, device=device, dtype=dtype)
H = find_homography_dlt(points1, points2, weights)
assert H.shape == (1, 3, 3)
