`trw.transforms.cutout_function`¶

Module Contents¶

Classes¶

CutOutType

Base class for protocol classes. Protocol classes are defined as:

Functions¶

`cutout_value_fn_constant`(image: trw.basic_typing.Tensor, value: trw.basic_typing.Numeric) → None	Replace all image as a constant value
`cutout_random_ui8_torch`(image: torch.Tensor, min_value: int = 0, max_value: int = 255) → None	Replace the image content as a constant value
`cutout_random_size`(min_size: Sequence[int], max_size: Sequence[int]) → List[int]	Return a random size within the specified bounds.
`cutout`(image: trw.basic_typing.TensorNCX, cutout_size: Union[trw.basic_typing.ShapeCX, Callable[[], trw.basic_typing.ShapeCX]], cutout_value_fn: CutOutType) → None	Remove a part of the image randomly

trw.transforms.cutout_function.cutout_value_fn_constant(image: trw.basic_typing.Tensor, value: trw.basic_typing.Numeric) → None¶: Replace all image as a constant value

trw.transforms.cutout_function.cutout_random_ui8_torch(image: torch.Tensor, min_value: int = 0, max_value: int = 255) → None¶: Replace the image content as a constant value

trw.transforms.cutout_function.cutout_random_size(min_size: Sequence[int], max_size: Sequence[int]) → List[int]¶

Return a random size within the specified bounds.

Parameters

min_size – a sequence representing the min size to be generated
max_size – a sequence representing the max size (inclusive) to be generated

Returns

a tuple representing the size

class trw.transforms.cutout_function.CutOutType¶

Bases: typing_extensions.Protocol

Base class for protocol classes. Protocol classes are defined as:

class Proto(Protocol):
    def meth(self) -> int:
        ...

Such classes are primarily used with static type checkers that recognize structural subtyping (static duck-typing), for example:

class C:
    def meth(self) -> int:
        return 0

def func(x: Proto) -> int:
    return x.meth()

func(C())  # Passes static type check

See PEP 544 for details. Protocol classes decorated with @typing_extensions.runtime act as simple-minded runtime protocol that checks only the presence of given attributes, ignoring their type signatures.

Protocol classes can be generic, they are defined as:

class GenProto(Protocol[T]):
    def meth(self) -> T:
        ...

__call__(self, image: trw.basic_typing.TensorNCX) → None¶

trw.transforms.cutout_function.cutout(image: trw.basic_typing.TensorNCX, cutout_size: Union[trw.basic_typing.ShapeCX, Callable[[], trw.basic_typing.ShapeCX]], cutout_value_fn: CutOutType) → None¶

Remove a part of the image randomly