sign_language_translator.vision.sign.sign module

class sign_language_translator.vision.sign.sign.Sign(sign, *args, **kwargs)

Bases: ABC

abstract static concatenate(objects: Iterable[Sign]) → Sign

concatenate multiple signs in time dimension

abstract classmethod load(path: str, **kwargs) → Sign

read the sign from a path

abstract classmethod load_asset(label: str, archive_name: str | None = None, **kwargs) → Sign

load a sign asset from a dataset

abstract static name() → str

the string code of the sign format

abstract numpy(*args, **kwargs) → ndarray[Any, dtype[_ScalarType_co]]

return the sign as a numpy array

abstract save(path: str, **kwargs) → None

save the sign to a path

abstract show(**kwargs) → None

display the sign

abstract torch(dtype: dtype | None = None, device: device | str | None = None) → Tensor

return the sign as a torch tensor

abstract transform(transformation: Callable)

apply some transformation to the sign to change its appearance