FlipDiagonal

class deeptrack.augmentations.FlipDiagonal(p: float | Callable[[...], float] = 0.5, augment: bool | Callable[[...], bool] | None = None, **kwargs)

Bases: Augmentation

Flips images along the main diagonal.

Updates all properties called “position” by swapping the first and second index.

Parameters

p: float

Probability of flipping the image, leaving as default (0.5) is sufficient most of the time.

augment: bool

Whether to perform the augmentation.

Methods

get(image: Image | np.ndarray, augment: PropertyLike[bool], **kwargs) -> Image

Abstract method which performs the FlipDiagonal augmentation.

update_properties(image: Image | np.ndarray, augment: PropertyLike[bool], **kwargs) -> None

Abstract method to update the properties of the image.

Methods Summary

get(image, augment, **kwargs)	Abstract method which performs the FlipDiagonal augmentation.
update_properties(image, augment, **kwargs)	Abstract method to update the properties of the image.

Methods Documentation

get(image: Image | np.ndarray, augment: PropertyLike[bool], **kwargs) → Image

Abstract method which performs the FlipDiagonal augmentation.

update_properties(image: Image | np.ndarray, augment: PropertyLike[bool], **kwargs) → None

Abstract method to update the properties of the image.