def test_normalized_mean_filter(self, device, dtype):
kernel = torch.ones(1, 3, 3, 3, device=device, dtype=dtype)
input = torch.tensor([[[[
[0., 0., 0., 0., 0.],
[0., 0., 0., 0., 0.],
[0., 0., 0., 0., 0.],
[0., 0., 0., 0., 0.],
[0., 0., 0., 0., 0.],
],
[
[0., 0., 0., 0., 0.],
[0., 0., 0., 0., 0.],
[0., 0., 5., 0., 0.],
[0., 0., 0., 0., 0.],
[0., 0., 0., 0., 0.],
],
[
[0., 0., 0., 0., 0.],
[0., 0., 0., 0., 0.],
[0., 0., 0., 0., 0.],
[0., 0., 0., 0., 0.],
[0., 0., 0., 0., 0.],
]]]],
device=device,
dtype=dtype)
input = input.expand(2, 2, -1, -1, -1)
nv = 5. / 27 # normalization value
expected = torch.tensor([[[[
[0., 0., 0., 0., 0.],
[0., nv, nv, nv, 0.],
[0., nv, nv, nv, 0.],
[0., nv, nv, nv, 0.],
[0., 0., 0., 0., 0.],
],
[
[0., 0., 0., 0., 0.],
[0., nv, nv, nv, 0.],
[0., nv, nv, nv, 0.],
[0., nv, nv, nv, 0.],
[0., 0., 0., 0., 0.],
],
[
[0., 0., 0., 0., 0.],
[0., nv, nv, nv, 0.],
[0., nv, nv, nv, 0.],
[0., nv, nv, nv, 0.],
[0., 0., 0., 0., 0.],
]]]],
device=device,
dtype=dtype)
expected = expected.expand(2, 2, -1, -1, -1)
actual = kornia.filter3D(input, kernel, normalized=True)
tol_val: float = utils._get_precision_by_name(device, 'xla', 1e-1,
1e-4)
assert_allclose(actual, expected, rtol=tol_val, atol=tol_val)
def test_noncontiguous(self, device, dtype):
batch_size = 3
inp = torch.rand(3, 5, 5, 5, device=device,
dtype=dtype).expand(batch_size, -1, -1, -1, -1)
kernel = torch.ones(1, 2, 2, 2, device=device, dtype=dtype)
actual = kornia.filter3D(inp, kernel)
expected = actual
assert_allclose(actual, expected)
def test_mean_filter_2batch_2ch(self, device, dtype):
kernel = torch.ones(1, 3, 3, 3, device=device, dtype=dtype)
input = torch.tensor([[[[
[0., 0., 0., 0., 0.],
[0., 0., 0., 0., 0.],
[0., 0., 0., 0., 0.],
[0., 0., 0., 0., 0.],
[0., 0., 0., 0., 0.],
],
[
[0., 0., 0., 0., 0.],
[0., 0., 0., 0., 0.],
[0., 0., 5., 0., 0.],
[0., 0., 0., 0., 0.],
[0., 0., 0., 0., 0.],
],
[
[0., 0., 0., 0., 0.],
[0., 0., 0., 0., 0.],
[0., 0., 0., 0., 0.],
[0., 0., 0., 0., 0.],
[0., 0., 0., 0., 0.],
]]]],
device=device,
dtype=dtype)
input = input.expand(2, 2, -1, -1, -1)
expected = torch.tensor([[[[
[0., 0., 0., 0., 0.],
[0., 5., 5., 5., 0.],
[0., 5., 5., 5., 0.],
[0., 5., 5., 5., 0.],
[0., 0., 0., 0., 0.],
],
[
[0., 0., 0., 0., 0.],
[0., 5., 5., 5., 0.],
[0., 5., 5., 5., 0.],
[0., 5., 5., 5., 0.],
[0., 0., 0., 0., 0.],
],
[
[0., 0., 0., 0., 0.],
[0., 5., 5., 5., 0.],
[0., 5., 5., 5., 0.],
[0., 5., 5., 5., 0.],
[0., 0., 0., 0., 0.],
]]]],
device=device,
dtype=dtype)
expected = expected.expand(2, 2, -1, -1, -1)
actual = kornia.filter3D(input, kernel)
assert_allclose(actual, expected)
def test_normalized_mean_filter(self, device, dtype):
kernel = torch.ones(1, 3, 3, 3, device=device, dtype=dtype)
input = torch.tensor([[[[
[0., 0., 0., 0., 0.],
[0., 0., 0., 0., 0.],
[0., 0., 0., 0., 0.],
[0., 0., 0., 0., 0.],
[0., 0., 0., 0., 0.],
],
[
[0., 0., 0., 0., 0.],
[0., 0., 0., 0., 0.],
[0., 0., 5., 0., 0.],
[0., 0., 0., 0., 0.],
[0., 0., 0., 0., 0.],
],
[
[0., 0., 0., 0., 0.],
[0., 0., 0., 0., 0.],
[0., 0., 0., 0., 0.],
[0., 0., 0., 0., 0.],
[0., 0., 0., 0., 0.],
]]]],
device=device,
dtype=dtype)
input = input.expand(2, 2, -1, -1, -1)
nv = 5. / 27 # normalization value
expected = torch.tensor([[[[
[0., 0., 0., 0., 0.],
[0., nv, nv, nv, 0.],
[0., nv, nv, nv, 0.],
[0., nv, nv, nv, 0.],
[0., 0., 0., 0., 0.],
],
[
[0., 0., 0., 0., 0.],
[0., nv, nv, nv, 0.],
[0., nv, nv, nv, 0.],
[0., nv, nv, nv, 0.],
[0., 0., 0., 0., 0.],
],
[
[0., 0., 0., 0., 0.],
[0., nv, nv, nv, 0.],
[0., nv, nv, nv, 0.],
[0., nv, nv, nv, 0.],
[0., 0., 0., 0., 0.],
]]]],
device=device,
dtype=dtype)
actual = kornia.filter3D(input, kernel, normalized=True)
assert_allclose(actual, expected)
def test_even_sized_filter(self, device, dtype):
kernel = torch.ones(1, 2, 2, 2, device=device, dtype=dtype)
input = torch.tensor([[[[
[0., 0., 0., 0., 0.],
[0., 0., 0., 0., 0.],
[0., 0., 0., 0., 0.],
[0., 0., 0., 0., 0.],
[0., 0., 0., 0., 0.],
],
[
[0., 0., 0., 0., 0.],
[0., 0., 0., 0., 0.],
[0., 0., 5., 0., 0.],
[0., 0., 0., 0., 0.],
[0., 0., 0., 0., 0.],
],
[
[0., 0., 0., 0., 0.],
[0., 0., 0., 0., 0.],
[0., 0., 0., 0., 0.],
[0., 0., 0., 0., 0.],
[0., 0., 0., 0., 0.],
]]]],
device=device,
dtype=dtype)
expected = torch.tensor([[[[
[0., 0., 0., 0., 0.],
[0., 5., 5., 0., 0.],
[0., 5., 5., 0., 0.],
[0., 0., 0., 0., 0.],
[0., 0., 0., 0., 0.],
],
[
[0., 0., 0., 0., 0.],
[0., 5., 5., 0., 0.],
[0., 5., 5., 0., 0.],
[0., 0., 0., 0., 0.],
[0., 0., 0., 0., 0.],
],
[
[0., 0., 0., 0., 0.],
[0., 0., 0., 0., 0.],
[0., 0., 0., 0., 0.],
[0., 0., 0., 0., 0.],
[0., 0., 0., 0., 0.],
]]]],
device=device,
dtype=dtype)
actual = kornia.filter3D(input, kernel)
assert_allclose(actual, expected)
def motion_blur3d(input: torch.Tensor,
kernel_size: int,
angle: Union[Tuple[float, float, float], torch.Tensor],
direction: Union[float, torch.Tensor],
border_type: str = 'constant',
mode: str = 'nearest') -> torch.Tensor:
r"""Perform motion blur on 3D volumes (5D tensor).
Args:
input (torch.Tensor): the input tensor with shape :math:`(B, C, D, H, W)`.
kernel_size (int): motion kernel width, height and depth. It should be odd and positive.
angle (torch.Tensor or tuple): Range of yaw (x-axis), pitch (y-axis), roll (z-axis) to select from.
If tensor, it must be :math:`(B, 3)`.
direction (tensor or float): forward/backward direction of the motion blur.
Lower values towards -1.0 will point the motion blur towards the back (with angle provided via angle),
while higher values towards 1.0 will point the motion blur forward. A value of 0.0 leads to a
uniformly (but still angled) motion blur.
If tensor, it must be :math:`(B,)`.
border_type (str): the padding mode to be applied before convolving. The expected modes are:
``'constant'``, ``'reflect'``, ``'replicate'`` or ``'circular'``. Default: ``'constant'``.
mode (str): interpolation mode for rotating the kernel. ``'bilinear'`` or ``'nearest'``.
Default: ``'nearest'``
Return:
torch.Tensor: the blurred image with shape :math:`(B, C, D, H, W)`.
Example:
>>> input = torch.randn(1, 3, 120, 80, 90).repeat(2, 1, 1, 1, 1)
>>> # perform exact motion blur across the batch
>>> out_1 = motion_blur3d(input, 5, (0., 90., 90.), 1)
>>> torch.allclose(out_1[0], out_1[1])
True
>>> # perform element-wise motion blur across the batch
>>> out_1 = motion_blur3d(input, 5, torch.tensor([[0., 90., 90.], [90., 180., 0.]]), torch.tensor([1., -1.]))
>>> torch.allclose(out_1[0], out_1[1])
False
"""
assert border_type in ["constant", "reflect", "replicate", "circular"]
kernel: torch.Tensor = get_motion_kernel3d(kernel_size, angle, direction,
mode)
return kornia.filter3D(input, kernel, border_type)
def test_batch(self, batch_size, device, dtype):
B: int = batch_size
kernel = torch.rand(1, 3, 3, 3, device=device, dtype=dtype)
input = torch.ones(B, 3, 6, 7, 8, device=device, dtype=dtype)
assert kornia.filter3D(input, kernel).shape == input.shape
def test_smoke(self, device, dtype):
kernel = torch.rand(1, 3, 3, 3).to(device)
input = torch.ones(1, 1, 6, 7, 8).to(device)
assert kornia.filter3D(input, kernel).shape == input.shape