def compute_affine_transformation(
input: torch.Tensor, params: Dict[str, torch.Tensor]) -> torch.Tensor:
r"""Compute the applied transformation matrix :math: `(*, 3, 3)`.
Args:
input (torch.Tensor): Tensor to be transformed with shape (H, W), (C, H, W), (B, C, H, W).
params (Dict[str, torch.Tensor]):
- params['angle']: Degrees of rotation.
- params['translations']: Horizontal and vertical translations.
- params['center']: Rotation center.
- params['scale']: Scaling params.
- params['sx']: Shear param toward x-axis.
- params['sy']: Shear param toward y-axis.
- params['resample']: Integer tensor. NEAREST = 0, BILINEAR = 1.
- params['align_corners']: Boolean tensor.
Returns:
torch.Tensor: The applied transformation matrix :math: `(*, 3, 3)`
"""
input = _transform_input(input)
_validate_input_dtype(
input, accepted_dtypes=[torch.float16, torch.float32, torch.float64])
transform = get_affine_matrix2d(params['translations'], params['center'],
params['scale'], params['angle'],
deg2rad(params['sx']),
deg2rad(params['sy'])).type_as(input)
return transform
def compute_affine_transformation(
input: torch.Tensor, params: Dict[str, torch.Tensor]) -> torch.Tensor:
r"""Compute the affine transformation matrix :math: `(*, 3, 3)`.
Args:
input (torch.Tensor): Tensor to be transformed with shape :math:`(*, C, H, W)`.
params (Dict[str, torch.Tensor]):
- params['angle']: Degrees of rotation.
- params['translations']: Horizontal and vertical translations.
- params['center']: Rotation center.
- params['scale']: Scaling params.
- params['sx']: Shear param toward x-axis.
- params['sy']: Shear param toward y-axis.
Returns:
torch.Tensor: The affine transformation matrix :math: `(*, 3, 3)`.
"""
transform = get_affine_matrix2d(
params['translations'],
params['center'],
params['scale'],
params['angle'],
deg2rad(params['sx']),
deg2rad(params['sy']),
).type_as(input)
return transform
def apply_affine(input: torch.Tensor,
params: Dict[str, torch.Tensor],
return_transform: bool = False) -> UnionType:
if not torch.is_tensor(input):
raise TypeError(f"Input type is not a torch.Tensor. Got {type(input)}")
r"""Random affine transformation of the image keeping center invariant
Args:
input (torch.Tensor): Tensor to be transformed with shape (H, W), (C, H, W), (*, C, H, W).
degrees (float or tuple): Range of degrees to select from.
If degrees is a number instead of sequence like (min, max), the range of degrees
will be (-degrees, +degrees). Set to 0 to deactivate rotations.
translate (tuple, optional): tuple of maximum absolute fraction for horizontal
and vertical translations. For example translate=(a, b), then horizontal shift
is randomly sampled in the range -img_width * a < dx < img_width * a and vertical shift is
randomly sampled in the range -img_height * b < dy < img_height * b. Will not translate by default.
scale (tuple, optional): scaling factor interval, e.g (a, b), then scale is
randomly sampled from the range a <= scale <= b. Will keep original scale by default.
shear (sequence or float, optional): Range of degrees to select from.
If shear is a number, a shear parallel to the x axis in the range (-shear, +shear)
will be applied. Else if shear is a tuple or list of 2 values a shear parallel to the x axis in the
range (shear[0], shear[1]) will be applied. Else if shear is a tuple or list of 4 values,
a x-axis shear in (shear[0], shear[1]) and y-axis shear in (shear[2], shear[3]) will be applied.
Will not apply shear by default
resample (int): Can be retrieved from Resample. 0 is NEAREST, 1 is BILINEAR.
return_transform (bool): if ``True`` return the matrix describing the transformation
applied to each. Default: False.
mode (str): interpolation mode to calculate output values
'bilinear' | 'nearest'. Default: 'bilinear'.
padding_mode (str): padding mode for outside grid values
'zeros' | 'border' | 'reflection'. Default: 'zeros'.
"""
input = _transform_input(input)
_validate_input_dtype(
input, accepted_dtypes=[torch.float16, torch.float32, torch.float64])
# arrange input data
x_data: torch.Tensor = input.view(-1, *input.shape[-3:])
height, width = x_data.shape[-2:]
# concatenate transforms
transform = get_affine_matrix2d(params['translations'], params['center'],
params['scale'], params['angle'],
deg2rad(params['sx']),
deg2rad(params['sy'])).type_as(input)
resample_name = Resample(params['resample'].item()).name.lower()
out_data: torch.Tensor = warp_affine(x_data, transform[:, :2, :],
(height, width), resample_name)
if return_transform:
return out_data.view_as(input), transform
return out_data.view_as(input)
def compute_affine_transformation(
input: torch.Tensor, params: Dict[str, torch.Tensor]) -> torch.Tensor:
input = _transform_input(input)
_validate_input_dtype(
input, accepted_dtypes=[torch.float16, torch.float32, torch.float64])
transform = get_affine_matrix2d(params['translations'], params['center'],
params['scale'], params['angle'],
deg2rad(params['sx']),
deg2rad(params['sy'])).type_as(input)
return transform
def compute_affine_transformation3d(
input: torch.Tensor, params: Dict[str, torch.Tensor]) -> torch.Tensor:
r"""Compute the applied transformation matrix :math: `(*, 4, 4)`.
Args:
input (torch.Tensor): Tensor to be transformed with shape (D, H, W), (C, D, H, W), (B, C, D, H, W).
params (Dict[str, torch.Tensor]):
- params['angles']: Degrees of rotation with the shape of :math: `(*, 3)` for yaw, pitch, roll.
- params['translations']: Horizontal, vertical and depthical translations (dx,dy,dz).
- params['center']: Rotation center (x,y,z).
- params['scale']: Isotropic scaling params.
- params['sxy']: Shear param toward x-y-axis.
- params['sxz']: Shear param toward x-z-axis.
- params['syx']: Shear param toward y-x-axis.
- params['syz']: Shear param toward y-z-axis.
- params['szx']: Shear param toward z-x-axis.
- params['szy']: Shear param toward z-y-axis.
Returns:
torch.Tensor: The applied transformation matrix :math: `(*, 4, 4)`
"""
input = _transform_input3d(input)
_validate_input_dtype(
input, accepted_dtypes=[torch.float16, torch.float32, torch.float64])
transform = get_affine_matrix3d(params['translations'], params['center'],
params['scale'], params['angles'],
deg2rad(params['sxy']),
deg2rad(params['sxz']),
deg2rad(params['syx']),
deg2rad(params['syz']),
deg2rad(params['szx']),
deg2rad(params['szy'])).type_as(input)
return transform
def compute_affine_transformation3d(input: torch.Tensor, params: Dict[str, torch.Tensor]) -> torch.Tensor:
r"""Compute the affine transformation matrix :math: `(*, 4, 4)`.
Args:
input (torch.Tensor): Tensor to be transformed with shape :math:`(*, C, D, H, W)`.
params (Dict[str, torch.Tensor]):
- params['angles']: Degrees of rotation with the shape of :math: `(*, 3)` for yaw, pitch, roll.
- params['translations']: Horizontal, vertical and depthical translations (dx,dy,dz).
- params['center']: Rotation center (x,y,z).
- params['scale']: Isotropic scaling params.
- params['sxy']: Shear param toward x-y-axis.
- params['sxz']: Shear param toward x-z-axis.
- params['syx']: Shear param toward y-x-axis.
- params['syz']: Shear param toward y-z-axis.
- params['szx']: Shear param toward z-x-axis.
- params['szy']: Shear param toward z-y-axis.
Returns:
torch.Tensor: The affine transformation matrix :math: `(*, 4, 4)`.
"""
transform = get_affine_matrix3d(
params['translations'], params['center'], params['scale'], params['angles'],
deg2rad(params['sxy']), deg2rad(params['sxz']), deg2rad(params['syx']),
deg2rad(params['syz']), deg2rad(params['szx']), deg2rad(params['szy'])
).to(input)
return transform
def compute_transformation(self, input: torch.Tensor, params: Dict[str, torch.Tensor]) -> torch.Tensor:
transform: torch.Tensor = get_affine_matrix3d(
params["translations"],
params["center"],
params["scale"],
params["angles"],
deg2rad(params["sxy"]),
deg2rad(params["sxz"]),
deg2rad(params["syx"]),
deg2rad(params["syz"]),
deg2rad(params["szx"]),
deg2rad(params["szy"]),
).to(input)
return transform
def compute_transformation(self, input: torch.Tensor, params: Dict[str, torch.Tensor]) -> torch.Tensor:
transform: torch.Tensor = get_affine_matrix3d(
params['translations'],
params['center'],
params['scale'],
params['angles'],
deg2rad(params['sxy']),
deg2rad(params['sxz']),
deg2rad(params['syx']),
deg2rad(params['syz']),
deg2rad(params['szx']),
deg2rad(params['szy']),
).to(input)
return transform
