def test_jit_warp_homography(self, device, batch_size, align_corners,
normalized_coordinates):
# generate input data
height, width = 128, 64
eye_size = 3 # identity 3x3
# create checkerboard
board = utils.create_checkerboard(height, width, 4)
patch_src = torch.from_numpy(board).view(1, 1, height, width).expand(
batch_size, 1, height, width).to(device)
# create base homography
dst_homo_src = utils.create_eye_batch(batch_size, eye_size).to(device)
for i in range(self.num_tests):
# generate homography noise
homo_delta = torch.rand_like(dst_homo_src) * 0.3
dst_homo_src_i = dst_homo_src + homo_delta
# transform the points with and without jit
patch_dst = kornia.homography_warp(
patch_src,
dst_homo_src_i, (height, width),
align_corners=align_corners,
normalized_coordinates=normalized_coordinates)
patch_dst_jit = torch.jit.script(kornia.homography_warp)(
patch_src,
dst_homo_src_i, (height, width),
align_corners=align_corners,
normalized_coordinates=normalized_coordinates)
assert_allclose(patch_dst, patch_dst_jit)
def test_jit_warp_homography(self, batch_size, align_corners, normalized_coordinates, device, dtype):
# generate input data
height, width = 128, 64
eye_size = 3 # identity 3x3
patch_src = torch.rand(batch_size, 1, height, width, device=device, dtype=dtype)
# create base homography
dst_homo_src = utils.create_eye_batch(batch_size, eye_size, device=device, dtype=dtype)
for _ in range(self.num_tests):
# generate homography noise
homo_delta = torch.rand_like(dst_homo_src) * 0.3
dst_homo_src_i = dst_homo_src + homo_delta
# transform the points with and without jit
patch_dst = kornia.homography_warp(
patch_src,
dst_homo_src_i,
(height, width),
align_corners=align_corners,
normalized_coordinates=normalized_coordinates,
)
patch_dst_jit = torch.jit.script(kornia.homography_warp)(
patch_src,
dst_homo_src_i,
(height, width),
align_corners=align_corners,
normalized_coordinates=normalized_coordinates,
)
assert_close(patch_dst, patch_dst_jit, atol=1e-4, rtol=1e-4)
def homography_warp(self, x):
xs = self.localization_homography(x)
H = self.fc_loc_homography(xs.view(-1, 10 * 3 * 3)).view(-1, 3, 3)
# warp using homography
x = kornia.homography_warp(x, H, self.out_size)
return x
def test_homography_warper(self, batch_size, device, dtype):
# generate input data
height, width = 128, 64
eye_size = 3 # identity 3x3
# create checkerboard
board = utils.create_checkerboard(height, width, 4)
patch_src = torch.from_numpy(board).to(
device=device,
dtype=dtype).view(1, 1, height,
width).expand(batch_size, 1, height, width)
# create base homography
dst_homo_src = utils.create_eye_batch(batch_size,
eye_size,
device=device,
dtype=dtype)
# instantiate warper
warper = kornia.HomographyWarper(height, width, align_corners=True)
for i in range(self.num_tests):
# generate homography noise
homo_delta = torch.rand_like(dst_homo_src) * 0.3
dst_homo_src_i = dst_homo_src + homo_delta
# transform the points from dst to ref
patch_dst = warper(patch_src, dst_homo_src_i)
patch_dst_to_src = warper(patch_dst,
_torch_inverse_cast(dst_homo_src_i))
# same transform precomputing the grid
warper.precompute_warp_grid(_torch_inverse_cast(dst_homo_src_i))
patch_dst_to_src_precomputed = warper(patch_dst)
assert (patch_dst_to_src_precomputed == patch_dst_to_src).all()
# projected should be equal as initial
error = utils.compute_patch_error(patch_src, patch_dst_to_src,
height, width)
assert error.item() < self.threshold
# check functional api
patch_dst_to_src_functional = kornia.homography_warp(
patch_dst,
_torch_inverse_cast(dst_homo_src_i), (height, width),
align_corners=True)
assert_allclose(patch_dst_to_src,
patch_dst_to_src_functional,
atol=1e-4,
rtol=1e-4)
def test_homography_warper(self, batch_size, device_type):
# generate input data
height, width = 128, 64
eye_size = 3 # identity 3x3
device = torch.device(device_type)
# create checkerboard
board = utils.create_checkerboard(height, width, 4)
patch_src = torch.from_numpy(board).view(1, 1, height, width).expand(
batch_size, 1, height, width)
patch_src = patch_src.to(device)
# create base homography
dst_homo_src = utils.create_eye_batch(batch_size, eye_size).to(device)
# instantiate warper
warper = kornia.HomographyWarper(height, width)
for i in range(self.num_tests):
# generate homography noise
homo_delta = torch.zeros_like(dst_homo_src)
homo_delta[:, -1, -1] = 0.0
dst_homo_src_i = dst_homo_src + homo_delta
# transform the points from dst to ref
patch_dst = warper(patch_src, dst_homo_src_i)
patch_dst_to_src = warper(patch_dst, torch.inverse(dst_homo_src_i))
# projected should be equal as initial
error = utils.compute_patch_error(patch_dst, patch_dst_to_src,
height, width)
assert error.item() < self.threshold
# check functional api
patch_dst_to_src_functional = kornia.homography_warp(
patch_dst, torch.inverse(dst_homo_src_i), (height, width))
assert utils.check_equal_torch(patch_dst_to_src,
patch_dst_to_src_functional)
def _transform(self, x, beta, inverse=False):
beta = beta.view(-1, 3, 3) + self.identity
if inverse:
beta = torch.inverse(beta)
return homography_warp(x, beta, dsize=(x.size(2), x.size(3)), padding_mode=self.padding_mode)
