Skip to content

shift_scale_rotate

ShiftScaleRotate

Bases: MultiVariateAlbumentation

Randomly apply affine transforms: translate, scale and rotate the input.

Parameters:

Name Type Description Default
mode Union[None, str, Iterable[str]]

What mode(s) to execute this Op in. For example, "train", "eval", "test", or "infer". To execute regardless of mode, pass None. To execute in all modes except for a particular one, you can pass an argument like "!infer" or "!train".

None
ds_id Union[None, str, Iterable[str]]

What dataset id(s) to execute this Op in. To execute regardless of ds_id, pass None. To execute in all ds_ids except for a particular one, you can pass an argument like "!ds1".

None
image_in Optional[str]

The key of an image to be modified.

None
mask_in Optional[str]

The key of a mask to be modified (with the same random factors as the image).

None
masks_in Optional[str]

The key of masks to be modified (with the same random factors as the image).

None
bbox_in Optional[str]

The key of a bounding box(es) to be modified (with the same random factors as the image).

None
keypoints_in Optional[str]

The key of keypoints to be modified (with the same random factors as the image).

None
image_out Optional[str]

The key to write the modified image (defaults to image_in if None).

None
mask_out Optional[str]

The key to write the modified mask (defaults to mask_in if None).

None
masks_out Optional[str]

The key to write the modified masks (defaults to masks_in if None).

None
bbox_out Optional[str]

The key to write the modified bounding box(es) (defaults to bbox_in if None).

None
keypoints_out Optional[str]

The key to write the modified keypoints (defaults to keypoints_in if None).

None
bbox_params Union[BboxParams, str, None]

Parameters defining the type of bounding box ('coco', 'pascal_voc', 'albumentations' or 'yolo').

None
keypoint_params Union[KeypointParams, str, None]

Parameters defining the type of keypoints ('xy', 'yx', 'xya', 'xys', 'xyas', 'xysa').

None
shift_limit Union[float, Tuple[float, float]]

Shift factor range for both height and width. If shift_limit is a single float value, the range will be (-shift_limit, shift_limit). Absolute values for lower and upper bounds should lie in range [0, 1].

0.0625
scale_limit Union[float, Tuple[float, float]]

Scaling factor range. If scale_limit is a single float value, the range will be (-scale_limit, scale_limit).

0.1
rotate_limit Union[int, Tuple[int, int]]

Rotation range. If rotate_limit is a single int value, the range will be (-rotate_limit, rotate_limit).

45
interpolation int

Flag that is used to specify the interpolation algorithm. Should be one of: cv2.INTER_NEAREST, cv2.INTER_LINEAR, cv2.INTER_CUBIC, cv2.INTER_AREA, cv2.INTER_LANCZOS4.

INTER_LINEAR
border_mode int

Flag that is used to specify the pixel extrapolation method. Should be one of: cv2.BORDER_CONSTANT, cv2.BORDER_REPLICATE, cv2.BORDER_REFLECT, cv2.BORDER_WRAP, cv2.BORDER_REFLECT_101.

BORDER_REFLECT_101
value Union[None, int, float, List[int], List[float]]

Padding value if border_mode is cv2.BORDER_CONSTANT.

None
mask_value Union[None, int, float, List[int], List[float]]

Padding value if border_mode is cv2.BORDER_CONSTANT applied for masks.

None
Image types

uint8, float32

Source code in fastestimator/fastestimator/op/numpyop/multivariate/shift_scale_rotate.py
@traceable()
class ShiftScaleRotate(MultiVariateAlbumentation):
    """Randomly apply affine transforms: translate, scale and rotate the input.

    Args:
        mode: What mode(s) to execute this Op in. For example, "train", "eval", "test", or "infer". To execute
            regardless of mode, pass None. To execute in all modes except for a particular one, you can pass an argument
            like "!infer" or "!train".
        ds_id: What dataset id(s) to execute this Op in. To execute regardless of ds_id, pass None. To execute in all
            ds_ids except for a particular one, you can pass an argument like "!ds1".
        image_in: The key of an image to be modified.
        mask_in: The key of a mask to be modified (with the same random factors as the image).
        masks_in: The key of masks to be modified (with the same random factors as the image).
        bbox_in: The key of a bounding box(es) to be modified (with the same random factors as the image).
        keypoints_in: The key of keypoints to be modified (with the same random factors as the image).
        image_out: The key to write the modified image (defaults to `image_in` if None).
        mask_out: The key to write the modified mask (defaults to `mask_in` if None).
        masks_out: The key to write the modified masks (defaults to `masks_in` if None).
        bbox_out: The key to write the modified bounding box(es) (defaults to `bbox_in` if None).
        keypoints_out: The key to write the modified keypoints (defaults to `keypoints_in` if None).
        bbox_params: Parameters defining the type of bounding box ('coco', 'pascal_voc', 'albumentations' or 'yolo').
        keypoint_params: Parameters defining the type of keypoints ('xy', 'yx', 'xya', 'xys', 'xyas', 'xysa').
        shift_limit: Shift factor range for both height and width. If shift_limit is a single float value, the range
            will be (-shift_limit, shift_limit). Absolute values for lower and upper bounds should lie in range [0, 1].
        scale_limit: Scaling factor range. If scale_limit is a single float value, the range will be
            (-scale_limit, scale_limit).
        rotate_limit: Rotation range. If rotate_limit is a single int value, the range will be
            (-rotate_limit, rotate_limit).
        interpolation: Flag that is used to specify the interpolation algorithm. Should be one of:
            cv2.INTER_NEAREST, cv2.INTER_LINEAR, cv2.INTER_CUBIC, cv2.INTER_AREA, cv2.INTER_LANCZOS4.
        border_mode: Flag that is used to specify the pixel extrapolation method. Should be one of:
            cv2.BORDER_CONSTANT, cv2.BORDER_REPLICATE, cv2.BORDER_REFLECT, cv2.BORDER_WRAP, cv2.BORDER_REFLECT_101.
        value: Padding value if border_mode is cv2.BORDER_CONSTANT.
        mask_value: Padding value if border_mode is cv2.BORDER_CONSTANT applied for masks.

    Image types:
        uint8, float32
    """
    def __init__(self,
                 shift_limit: Union[float, Tuple[float, float]] = 0.0625,
                 scale_limit: Union[float, Tuple[float, float]] = 0.1,
                 rotate_limit: Union[int, Tuple[int, int]] = 45,
                 interpolation: int = cv2.INTER_LINEAR,
                 border_mode: int = cv2.BORDER_REFLECT_101,
                 value: Union[None, int, float, List[int], List[float]] = None,
                 mask_value: Union[None, int, float, List[int], List[float]] = None,
                 mode: Union[None, str, Iterable[str]] = None,
                 ds_id: Union[None, str, Iterable[str]] = None,
                 image_in: Optional[str] = None,
                 mask_in: Optional[str] = None,
                 masks_in: Optional[str] = None,
                 bbox_in: Optional[str] = None,
                 keypoints_in: Optional[str] = None,
                 image_out: Optional[str] = None,
                 mask_out: Optional[str] = None,
                 masks_out: Optional[str] = None,
                 bbox_out: Optional[str] = None,
                 keypoints_out: Optional[str] = None,
                 bbox_params: Union[BboxParams, str, None] = None,
                 keypoint_params: Union[KeypointParams, str, None] = None):
        super().__init__(
            ShiftScaleRotateAlb(shift_limit=shift_limit,
                                scale_limit=scale_limit,
                                rotate_limit=rotate_limit,
                                interpolation=interpolation,
                                border_mode=border_mode,
                                value=value,
                                mask_value=mask_value,
                                always_apply=True),
            image_in=image_in,
            mask_in=mask_in,
            masks_in=masks_in,
            bbox_in=bbox_in,
            keypoints_in=keypoints_in,
            image_out=image_out,
            mask_out=mask_out,
            masks_out=masks_out,
            bbox_out=bbox_out,
            keypoints_out=keypoints_out,
            bbox_params=bbox_params,
            keypoint_params=keypoint_params,
            mode=mode,
            ds_id=ds_id)