albumentations.augmentations.geometric.rotate

Randomly rotate the input by 90 degrees zero or more times. Even with p=1.0, the transform has a 1/4 probability of being identity: - With probability p * 1/4: no rotation (0 degrees) - With probability p * 1/4: rotate 90 degrees - With probability p * 1/4: rotate 180 degrees - With probability p * 1/4: rotate 270 degrees For example: - With p=1.0: Each rotation angle (including 0°) has 0.25 probability - With p=0.8: Each rotation angle has 0.2 probability, and no transform has 0.2 probability - With p=0.5: Each rotation angle has 0.125 probability, and no transform has 0.5 probability Common applications: - Aerial/satellite imagery: Objects can appear in any orientation - Medical imaging: Scans/slides may not have a consistent orientation - Document analysis: Pages or symbols might be rotated - Microscopy: Cell orientation is often arbitrary - Game development: Sprites/textures that should work in multiple orientations Not recommended for: - Natural scene images where gravity matters (e.g., landscape photography) - Face detection/recognition tasks - Text recognition (unless text can appear rotated) - Tasks where object orientation is important for classification Note: If your domain has both 90-degree rotation AND flip symmetries (e.g., satellite imagery, microscopy), consider using `D4` transform instead. `D4` is more efficient and mathematically correct as it: - Samples uniformly from all 8 possible combinations of rotations and flips - Properly represents the dihedral group D4 symmetries - Avoids potential correlation between separate rotation and flip augmentations `inverse()` requires `group_element` to be set explicitly; raises `ValueError` otherwise. When `group_element` is specified, the transform is deterministic—useful for TTA (Test Time Augmentation) where you need to apply each of the 4 rotations (0°, 90°, 180°, 270°) explicitly and invert predictions. Uses the same naming as D4: C4 is the rotation subgroup of D4. Call `inverse()` on a deterministic instance to get a new transform that undoes the rotation (r90 ↔ r270, r180 ↔ r180, e ↔ e).

Parameters

Examples

>>> import numpy as np
>>> import albumentations as A
>>> # Create example data
>>> image = np.random.randint(0, 256, (100, 100, 3), dtype=np.uint8)
>>> mask = np.random.randint(0, 2, (100, 100), dtype=np.uint8)
>>> bboxes = np.array([[10, 10, 50, 50], [40, 40, 80, 80]], dtype=np.float32)
>>> bbox_labels = [1, 2]  # Class labels for bounding boxes
>>> keypoints = np.array([[20, 30], [60, 70]], dtype=np.float32)
>>> keypoint_labels = [0, 1]  # Labels for keypoints
>>> # Define the transform
>>> transform = A.Compose([
...     A.RandomRotate90(p=1.0),
... ], bbox_params=A.BboxParams(coord_format='pascal_voc', label_fields=['bbox_labels']),
...    keypoint_params=A.KeypointParams(coord_format='xy', label_fields=['keypoint_labels']))
>>> # Apply the transform to all targets
>>> transformed = transform(
...     image=image,
...     mask=mask,
...     bboxes=bboxes,
...     bbox_labels=bbox_labels,
...     keypoints=keypoints,
...     keypoint_labels=keypoint_labels
... )
>>> rotated_image = transformed["image"]
>>> rotated_mask = transformed["mask"]
>>> rotated_bboxes = transformed["bboxes"]
>>> rotated_bbox_labels = transformed["bbox_labels"]
>>> rotated_keypoints = transformed["keypoints"]
>>> rotated_keypoint_labels = transformed["keypoint_labels"]

>>> # TTA: apply each of the 4 rotations, run inference, then undo on the predicted mask
>>> from albumentations.core.type_definitions import c4_group_elements
>>> predictions = []
>>> for element in c4_group_elements:
...     aug = A.RandomRotate90(p=1.0, group_element=element)
...     aug_image = aug(image=image)["image"]
...     pred_mask = np.zeros((100, 100, 1), dtype=np.uint8)  # placeholder for model output
...     restored = aug.inverse()(image=pred_mask)["image"]
...     predictions.append(restored)

Notes

If your domain has both 90-degree rotation AND flip symmetries (e.g., satellite imagery, microscopy), consider using `D4` transform instead. `D4` is more efficient and mathematically correct as it: - Samples uniformly from all 8 possible combinations of rotations and flips - Properly represents the dihedral group D4 symmetries - Avoids potential correlation between separate rotation and flip augmentations `inverse()` requires `group_element` to be set explicitly; raises `ValueError` otherwise. When `group_element` is specified, the transform is deterministic—useful for TTA (Test Time Augmentation) where you need to apply each of the 4 rotations (0°, 90°, 180°, 270°) explicitly and invert predictions. Uses the same naming as D4: C4 is the rotation subgroup of D4. Call `inverse()` on a deterministic instance to get a new transform that undoes the rotation (r90 ↔ r270, r180 ↔ r180, e ↔ e).

Rotate the input by an angle selected randomly from the uniform distribution.

Parameters

Examples

>>> import numpy as np
>>> import albumentations as A
>>> # Create example data
>>> image = np.random.randint(0, 256, (100, 100, 3), dtype=np.uint8)
>>> mask = np.random.randint(0, 2, (100, 100), dtype=np.uint8)
>>> bboxes = np.array([[10, 10, 50, 50], [40, 40, 80, 80]], dtype=np.float32)
>>> bbox_labels = [1, 2]  # Class labels for bounding boxes
>>> keypoints = np.array([[20, 30], [60, 70]], dtype=np.float32)
>>> keypoint_labels = [0, 1]  # Labels for keypoints
>>> # Define the transform
>>> transform = A.Compose([
...     A.Rotate(limit=45, p=1.0),
... ], bbox_params=A.BboxParams(coord_format='pascal_voc', label_fields=['bbox_labels']),
...    keypoint_params=A.KeypointParams(coord_format='xy', label_fields=['keypoint_labels']))
>>> # Apply the transform to all targets
>>> transformed = transform(
...     image=image,
...     mask=mask,
...     bboxes=bboxes,
...     bbox_labels=bbox_labels,
...     keypoints=keypoints,
...     keypoint_labels=keypoint_labels
... )
>>> rotated_image = transformed["image"]
>>> rotated_mask = transformed["mask"]
>>> rotated_bboxes = transformed["bboxes"]
>>> rotated_bbox_labels = transformed["bbox_labels"]
>>> rotated_keypoints = transformed["keypoints"]
>>> rotated_keypoint_labels = transformed["keypoint_labels"]

Notes

- The rotation angle is randomly selected for each execution within the range specified by 'limit'. - When 'crop_border' is False, the output image will have the same size as the input, potentially introducing black triangles in the corners. - When 'crop_border' is True, the output image is cropped to remove black triangles, which may result in a smaller image. - Bounding boxes are rotated and may change size or shape. - Keypoints are rotated around the center of the image.

Rotate the input inside the input's frame by an angle selected randomly from the uniform distribution. This transformation ensures that the entire rotated image fits within the original frame by scaling it down if necessary. The resulting image maintains its original dimensions but may contain artifacts due to the rotation and scaling process.

Parameters

Examples

>>> import numpy as np
>>> import albumentations as A
>>> # Create example data
>>> image = np.random.randint(0, 256, (100, 100, 3), dtype=np.uint8)
>>> mask = np.random.randint(0, 2, (100, 100), dtype=np.uint8)
>>> bboxes = np.array([[10, 10, 50, 50], [40, 40, 80, 80]], dtype=np.float32)
>>> bbox_labels = [1, 2]  # Class labels for bounding boxes
>>> keypoints = np.array([[20, 30], [60, 70]], dtype=np.float32)
>>> keypoint_labels = [0, 1]  # Labels for keypoints
>>> # Define the transform
>>> transform = A.Compose([
...     A.SafeRotate(limit=45, p=1.0),
... ], bbox_params=A.BboxParams(coord_format='pascal_voc', label_fields=['bbox_labels']),
...    keypoint_params=A.KeypointParams(coord_format='xy', label_fields=['keypoint_labels']))
>>> # Apply the transform to all targets
>>> transformed = transform(
...     image=image,
...     mask=mask,
...     bboxes=bboxes,
...     bbox_labels=bbox_labels,
...     keypoints=keypoints,
...     keypoint_labels=keypoint_labels
... )
>>> rotated_image = transformed["image"]
>>> rotated_mask = transformed["mask"]
>>> rotated_bboxes = transformed["bboxes"]
>>> rotated_bbox_labels = transformed["bbox_labels"]
>>> rotated_keypoints = transformed["keypoints"]
>>> rotated_keypoint_labels = transformed["keypoint_labels"]

Notes

- The rotation is performed around the center of the image. - After rotation, the image is scaled to fit within the original frame, which may cause some distortion. - The output image will always have the same dimensions as the input image. - Bounding boxes and keypoints are transformed along with the image.