def __init__(
self,
size: Union[int, Sequence[int]],
scale: Tuple[float, float] = (0.08, 1.0),
ratio: Tuple[float, float] = (3.0 / 4.0, 4.0 / 3.0),
interpolation: InterpolationMode = InterpolationMode.BILINEAR,
antialias: Optional[bool] = None,
) -> None:
super().__init__()
self.size = _setup_size(
size,
error_msg="Please provide only two dimensions (h, w) for size.")
if not isinstance(scale, Sequence):
raise TypeError("Scale should be a sequence")
scale = cast(Tuple[float, float], scale)
if not isinstance(ratio, Sequence):
raise TypeError("Ratio should be a sequence")
ratio = cast(Tuple[float, float], ratio)
if (scale[0] > scale[1]) or (ratio[0] > ratio[1]):
warnings.warn("Scale and ratio should be of kind (min, max)")
self.size = size
self.scale = scale
self.ratio = ratio
self.interpolation = interpolation
self.antialias = antialias
def __init__(
self,
size: Union[int, Sequence[int]],
scale: Tuple[float, float] = (0.08, 1.0),
ratio: Tuple[float, float] = (3.0 / 4.0, 4.0 / 3.0),
interpolation: InterpolationMode = InterpolationMode.BILINEAR,
) -> None:
super().__init__()
self.size = _setup_size(
size,
error_msg="Please provide only two dimensions (h, w) for size.")
if not isinstance(scale, Sequence):
raise TypeError("Scale should be a sequence")
scale = cast(Tuple[float, float], scale)
if not isinstance(ratio, Sequence):
raise TypeError("Ratio should be a sequence")
ratio = cast(Tuple[float, float], ratio)
if (scale[0] > scale[1]) or (ratio[0] > ratio[1]):
warnings.warn("Scale and ratio should be of kind (min, max)")
# Backward compatibility with integer value
if isinstance(interpolation, int):
warnings.warn(
"Argument interpolation should be of type InterpolationMode instead of int. "
"Please, use InterpolationMode enum.")
interpolation = _interpolation_modes_from_int(interpolation)
self.size = size
self.scale = scale
self.ratio = ratio
self.interpolation = interpolation
def __init__(self,
size: Union[int, Sequence[int]],
vertical_flip: bool = False) -> None:
super().__init__()
self.size = _setup_size(
size,
error_msg="Please provide only two dimensions (h, w) for size.")
self.vertical_flip = vertical_flip
def __init__(self,
size,
scale=(0.08, 1.0),
ratio=(3. / 4., 4. / 3.),
target_type=None):
super().__init__(target_type=target_type)
self.size = VT._setup_size(size, "Invalid value for size (h, w)")
self.scale = scale
self.ratio = ratio
def __init__(self, size, fill=0, padding_mode="constant"):
super().__init__()
size = tuple(
T._setup_size(
size,
error_msg="Please provide only two dimensions (h, w) for size."
))
self.crop_height = size[0]
self.crop_width = size[1]
self.fill = fill # TODO: Fill is currently respected only on PIL. Apply tensor patch.
self.padding_mode = padding_mode
def __init__(self,
size,
padding=None,
pad_if_needed=False,
fill=0,
padding_mode="constant",
mask_fill=255,
target_type: Optional[TargetType] = None):
super().__init__(target_type)
self.size = VT._setup_size(size, "Invalid value for size (h, w)")
self.padding = padding
self.pad_if_needed = pad_if_needed
self.padding_mode = padding_mode
self.fill = fill
self.mask_fill = mask_fill
if self.padding is not None and self.target_type is not None:
# when reflection padding is applied, what are the expected mask or bbox?
raise RuntimeError(
"padding is unexpected for non-classification tasks")
if self.target_type == "detection":
warnings.warn(
f"{self.__class__.__name__} expects coordinate origin is at left top. "
f"Inconsistency with this may cause unexpected results.",
HomuraTransformWarning)
def __init__(self, size: Union[int, Sequence[int]]) -> None:
super().__init__()
self.size = _setup_size(
size,
error_msg="Please provide only two dimensions (h, w) for size.")
def __init__(self, size, target_type=None):
super().__init__(target_type)
self.size = VT._setup_size(size, "Invalid size for (h, w) for size")
def __init__(self, size):
self.size = tuple(
_setup_size(
size,
error_msg="Please provide only two dimensions (h, w) for size."
))
def active_size(self, size):
self._active_size = _setup_size(
int(size / self.ratio),
error_msg="Please provide only two dimensions (h, w) for size.")
