albumentations.augmentations.mixing.transforms

>>> import numpy as np
>>> import albumentations as A
>>>
>>> # Primary data (target image is 100x100)
>>> image = np.random.randint(0, 256, (100, 100, 3), dtype=np.uint8)
>>> instance_masks = np.zeros((1, 100, 100), dtype=np.uint8)
>>> instance_masks[0, 10:30, 10:30] = 1
>>> bboxes = np.array([[10, 10, 30, 30]], dtype=np.float32)
>>> class_labels = [1]
>>>
>>> # Donor 1: tight 40x40 mask-based donor (any donor dims work).
>>> donor1_image = np.full((40, 40, 3), 200, dtype=np.uint8)
>>> donor1_mask = np.ones((40, 40), dtype=np.uint8)
>>>
>>> # Donor 2: bbox-only donor on a 60x80 image (rectangle paste footprint).
>>> donor2_image = np.random.randint(0, 256, (60, 80, 3), dtype=np.uint8)
>>>
>>> transform = A.Compose([
...     A.CopyAndPaste(
...         min_visibility_after_paste=0.05,
...         scale_range=(0.5, 1.0),  # randomly shrink donors to 50%-100% of fit
...         p=1.0,
...     ),
... ], bbox_params=A.BboxParams(coord_format='pascal_voc', label_fields=['class_labels']))
>>>
>>> result = transform(
...     image=image,
...     masks=instance_masks,
...     bboxes=bboxes,
...     class_labels=class_labels,
...     copy_paste_metadata=[
...         {
...             'image': donor1_image,
...             'mask': donor1_mask,
...             'bbox_labels': {'class_labels': 2},
...         },
...         {
...             'image': donor2_image,
...             'bbox': [10, 5, 70, 55],  # pascal_voc on 60x80 donor dims
...             'bbox_labels': {'class_labels': 3},
...         },
...     ],
... )
>>> result_image = result['image']
>>> result_masks = result['masks']         # (N_surviving + K, H, W)
>>> result_bboxes = result['bboxes']       # Updated bboxes (in pascal_voc, target dims)
>>> result_labels = result['class_labels'] # Updated labels

>>> import numpy as np
>>> import albumentations as A
>>> import cv2
>>>
>>> # Prepare primary data
>>> primary_image = np.random.randint(0, 256, (100, 100, 3), dtype=np.uint8)
>>> primary_mask = np.random.randint(0, 2, (100, 100), dtype=np.uint8)
>>> primary_bboxes = np.array([[10, 10, 40, 40], [50, 50, 90, 90]], dtype=np.float32)
>>> primary_bbox_classes = [1, 2]
>>> primary_keypoints = np.array([[25, 25], [75, 75]], dtype=np.float32)
>>> primary_keypoint_classes = ['eye', 'nose']
>>>
>>> # Prepare additional images for mosaic.
>>> # bbox_labels and keypoint_labels are dicts mapping field name -> list of values.
>>> mosaic_metadata = [
...     {
...         '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([[20, 20, 60, 60]], dtype=np.float32),
...         'bbox_labels': {'bbox_classes': [3]},
...         'keypoints': np.array([[40, 40]], dtype=np.float32),
...         'keypoint_labels': {'keypoint_classes': ['mouth']},
...     },
...     {
...         '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([[30, 30, 70, 70]], dtype=np.float32),
...         'bbox_labels': {'bbox_classes': [4]},
...         'keypoints': np.array([[50, 50], [65, 65]], dtype=np.float32),
...         'keypoint_labels': {'keypoint_classes': ['eye', 'eye']},
...     },
... ]
>>>
>>> transform = A.Compose([
...     A.Mosaic(
...         grid_yx=(2, 2),
...         target_size=(200, 200),
...         cell_shape=(120, 120),
...         center_range=(0.4, 0.6),
...         fit_mode="cover",
...         p=1.0
...     ),
... ], bbox_params=A.BboxParams(coord_format='pascal_voc', label_fields=['bbox_classes']),
...    keypoint_params=A.KeypointParams(coord_format='xy', label_fields=['keypoint_classes']))
>>>
>>> transformed = transform(
...     image=primary_image,
...     mask=primary_mask,
...     bboxes=primary_bboxes,
...     bbox_classes=primary_bbox_classes,
...     keypoints=primary_keypoints,
...     keypoint_classes=primary_keypoint_classes,
...     mosaic_metadata=mosaic_metadata,
... )
>>>
>>> mosaic_image = transformed['image']
>>> mosaic_bboxes = transformed['bboxes']
>>> mosaic_bbox_classes = transformed['bbox_classes']
>>> mosaic_keypoint_classes = transformed['keypoint_classes']

>>> import numpy as np
>>> import albumentations as A
>>> import cv2
>>>
>>> # Prepare primary data (base image and mask)
>>> image = np.zeros((300, 300, 3), dtype=np.uint8)
>>> mask = np.zeros((300, 300), dtype=np.uint8)
>>>
>>> # 1. Create a simple overlay image (a red square)
>>> overlay_image1 = np.zeros((50, 50, 3), dtype=np.uint8)
>>> overlay_image1[:, :, 0] = 255  # Red color
>>>
>>> # 2. Create another overlay with a mask (a blue circle with transparency)
>>> overlay_image2 = np.zeros((80, 80, 3), dtype=np.uint8)
>>> overlay_image2[:, :, 2] = 255  # Blue color
>>> overlay_mask2 = np.zeros((80, 80), dtype=np.uint8)
>>> # Create a circular mask
>>> center = (40, 40)
>>> radius = 30
>>> for i in range(80):
...     for j in range(80):
...         if (i - center[0])**2 + (j - center[1])**2 < radius**2:
...             overlay_mask2[i, j] = 255
>>>
>>> # 3. Create an overlay with both bbox and mask_id
>>> overlay_image3 = np.zeros((60, 120, 3), dtype=np.uint8)
>>> overlay_image3[:, :, 1] = 255  # Green color
>>> # Create a rectangular mask with rounded corners
>>> overlay_mask3 = np.zeros((60, 120), dtype=np.uint8)
>>> cv2.rectangle(overlay_mask3, (10, 10), (110, 50), 255, -1)
>>>
>>> # Create the metadata list - each item is a dictionary with overlay information
>>> overlay_metadata = [
...     {
...         'image': overlay_image1,
...         # No bbox provided - will be placed randomly
...     },
...     {
...         'image': overlay_image2,
...         'bbox': [0.6, 0.1, 0.9, 0.4],  # Normalized coordinates [x_min, y_min, x_max, y_max]
...         'mask': overlay_mask2,
...         'mask_id': 1  # This overlay will update the mask with id 1
...     },
...     {
...         'image': overlay_image3,
...         'bbox': [0.1, 0.7, 0.5, 0.9],  # Bottom left placement
...         'mask': overlay_mask3,
...         'mask_id': 2  # This overlay will update the mask with id 2
...     }
... ]
>>>
>>> # Create the transform
>>> transform = A.Compose([
...     A.OverlayElements(p=1.0),
... ])
>>>
>>> # Apply the transform
>>> result = transform(
...     image=image,
...     mask=mask,
...     overlay_metadata=overlay_metadata  # Pass metadata using the default key
... )
>>>
>>> # Get results with overlays applied
>>> result_image = result['image']  # Image with the three overlays applied
>>> result_mask = result['mask']    # Mask with regions labeled using the mask_id values
>>>
>>> # Let's verify the mask contains the specified mask_id values
>>> has_mask_id_1 = np.any(result_mask == 1)  # Should be True
>>> has_mask_id_2 = np.any(result_mask == 2)  # Should be True