def test_transform_points(batch_size, num_points, num_dims, device_type):
# generate input data
eye_size = num_dims + 1
points_src = torch.rand(batch_size, num_points, num_dims)
points_src = points_src.to(torch.device(device_type))
dst_homo_src = utils.create_random_homography(batch_size, eye_size)
dst_homo_src = dst_homo_src.to(torch.device(device_type))
# transform the points from dst to ref
points_dst = tgm.transform_points(dst_homo_src, points_src)
# transform the points from ref to dst
src_homo_dst = torch.inverse(dst_homo_src)
points_dst_to_src = tgm.transform_points(src_homo_dst, points_dst)
# projected should be equal as initial
error = utils.compute_mse(points_src, points_dst_to_src)
assert pytest.approx(error.item(), 0.0)
# functional
assert torch.allclose(points_dst,
tgm.TransformPoints(dst_homo_src)(points_src))
# evaluate function gradient
points_src = utils.tensor_to_gradcheck_var(points_src) # to var
dst_homo_src = utils.tensor_to_gradcheck_var(dst_homo_src) # to var
assert gradcheck(tgm.transform_points, (
dst_homo_src,
points_src,
),
raise_exception=True)
def test_inverse_gradcheck(self):
# generate input data
batch_size = 2
eye_size = 3 # identity 3x3
homographies = utils.create_random_homography(batch_size, eye_size)
homographies = utils.tensor_to_gradcheck_var(homographies) # to var
# evaluate function gradient
res = gradcheck(tgm.inverse, (homographies, ), raise_exception=True)
self.assertTrue(res)
def test_gradcheck(self):
# generate input data
batch_size, num_points, num_dims = 2, 3, 2
eye_size = num_dims + 1
points_src = torch.rand(batch_size, num_points, num_dims)
dst_homo_src = utils.create_random_homography(batch_size, eye_size)
# evaluate function gradient
points_src = utils.tensor_to_gradcheck_var(points_src) # to var
dst_homo_src = utils.tensor_to_gradcheck_var(dst_homo_src) # to var
assert gradcheck(tgm.TransformPoints(dst_homo_src), (points_src, ),
raise_exception=True)
def test_inverse_pose(self):
# generate input data
batch_size = 1
eye_size = 4 # identity 4x4
dst_pose_src = utils.create_random_homography(batch_size, eye_size)
dst_pose_src[:, -1] = 0.0
dst_pose_src[:, -1, -1] = 1.0
# compute the inverse of the pose
src_pose_dst = tgm.inverse_pose(dst_pose_src)
# H_inv * H == I
eye = torch.matmul(src_pose_dst, dst_pose_src)
res = utils.check_equal_torch(eye, torch.eye(4), eps=1e-3)
def test_inverse_pose(self):
# generate input data
batch_size = 1
eye_size = 4 # identity 4x4
dst_pose_src = utils.create_random_homography(batch_size, eye_size)
dst_pose_src[:, -1] = 0.0
dst_pose_src[:, -1, -1] = 1.0
# compute the inverse of the pose
src_pose_dst = tgm.inverse_pose(dst_pose_src)
# H_inv * H == I
res = torch.matmul(src_pose_dst, dst_pose_src)
error = compute_mse(res, utils.create_eye_batch(batch_size, eye_size))
self.assertAlmostEqual(error.item(), 0.0, places=4)
def test_inverse(self):
# generate input data
batch_size = 2
eye_size = 3 # identity 3x3
homographies = utils.create_random_homography(batch_size, eye_size)
homographies_inv = tgm.inverse(homographies)
# H_inv * H == I
res = torch.matmul(homographies_inv, homographies)
eye = utils.create_eye_batch(batch_size, eye_size)
error = utils.compute_mse(res, eye)
self.assertAlmostEqual(error.item(), 0.0, places=4)
# functional
self.assertTrue(
torch.allclose(homographies_inv,
tgm.Inverse()(homographies)))
def test_transform_points_gradcheck(self):
# generate input data
batch_size = 2
num_points = 2
num_dims = 2
eye_size = 3 # identity 3x3
points_src = torch.rand(batch_size, 2, num_dims)
points_src = utils.tensor_to_gradcheck_var(points_src) # to var
dst_homo_src = utils.create_random_homography(batch_size, eye_size)
dst_homo_src = utils.tensor_to_gradcheck_var(dst_homo_src) # to var
# evaluate function gradient
res = gradcheck(tgm.transform_points, (
dst_homo_src,
points_src,
),
raise_exception=True)
self.assertTrue(res)
def test_inverse_pose(batch_size, device_type):
# generate input data
eye_size = 4 # identity 4x4
dst_pose_src = utils.create_random_homography(batch_size, eye_size)
dst_pose_src = dst_pose_src.to(torch.device(device_type))
dst_pose_src[:, -1] = 0.0
dst_pose_src[:, -1, -1] = 1.0
# compute the inverse of the pose
src_pose_dst = tgm.inverse_pose(dst_pose_src)
# H_inv * H == I
eye = torch.matmul(src_pose_dst, dst_pose_src)
assert utils.check_equal_torch(eye, torch.eye(4), eps=1e-3)
# evaluate function gradient
dst_pose_src = utils.tensor_to_gradcheck_var(dst_pose_src) # to var
assert gradcheck(tgm.inverse_pose, (dst_pose_src,),
raise_exception=True)
def test_transform_points(self, batch_size, num_points, num_dims,
device_type):
# generate input data
eye_size = num_dims + 1
points_src = torch.rand(batch_size, num_points, num_dims)
points_src = points_src.to(torch.device(device_type))
dst_homo_src = utils.create_random_homography(batch_size, eye_size)
dst_homo_src = dst_homo_src.to(torch.device(device_type))
# transform the points from dst to ref
points_dst = tgm.transform_points(dst_homo_src, points_src)
# transform the points from ref to dst
src_homo_dst = torch.inverse(dst_homo_src)
points_dst_to_src = tgm.transform_points(src_homo_dst, points_dst)
# projected should be equal as initial
error = utils.compute_mse(points_src, points_dst_to_src)
assert pytest.approx(error.item(), 0.0)
def test_transform_points(self):
# generate input data
batch_size = 2
num_points = 2
num_dims = 2
eye_size = 3 # identity 3x3
points_src = torch.rand(batch_size, 2, num_dims)
dst_homo_src = utils.create_random_homography(batch_size, eye_size)
# transform the points from dst to ref
points_dst = tgm.transform_points(dst_homo_src, points_src)
# transform the points from ref to dst
src_homo_dst = tgm.inverse(dst_homo_src)
points_dst_to_src = tgm.transform_points(src_homo_dst, points_dst)
# projected should be equal as initial
error = utils.compute_mse(points_src, points_dst_to_src)
self.assertAlmostEqual(error.item(), 0.0, places=4)
# functional
self.assertTrue(
torch.allclose(points_dst,
tgm.TransformPoints()(dst_homo_src, points_src)))
