PadAndScaleAnnotatedImg

class hybrid_learning.datasets.custom.coco.keypoints_dataset.PadAndScaleAnnotatedImg(img_size)

Bases: TupleTransforms

Pickleable wrapper to pad and scale both an image and its COCO annotation to a target size. See pad_and_scale_annotation().

Public Data Attributes:

settings

Settings to reproduce the instance.

Inherited from : py: class:Transform

IDENTITY_CLASS	The identity class or classes for composition / addition.
settings	Settings to reproduce the instance.

Public Methods:

apply_to(img_t, anns)

Pad and rescale both image and annotations.

Inherited from : py: class:TupleTransforms

apply_to(img_t, anns)

Pad and rescale both image and annotations.

Inherited from : py: class:Transform

apply_to(img_t, anns)

Pad and rescale both image and annotations.

Special Methods:

__init__(img_size)

Init.

Inherited from : py: class:TupleTransforms

__init__(img_size)	Init.
__call__(*inputs)	Apply the transformation to the tuple (inp, target); the output again is a tuple.

Inherited from : py: class:Transform

__repr__()	Return repr(self).
__eq__(other)	Return self==value.
__copy__()	Return a shallow copy of self using settings.
__add__(other)	Return a flat composition of self with other.
__radd__(other)	Return a flat composition of other and self.
__call__(*inputs)	Apply the transformation to the tuple (inp, target); the output again is a tuple.

---

Parameters

img_size (Tuple[int, int]) –

__init__(img_size)

Init. Set the identity transformation for this class.

Parameters

img_size (Tuple[int, int]) –

apply_to(img_t, anns)

Pad and rescale both image and annotations.

Parameters

• img_t (Tensor) –

• anns (List[Dict[str, Any]]) –

img_size

The target size of the annotation.

property settings: Dict[str, Any]

Settings to reproduce the instance.