albumentations.augmentations.geometric.resize

>>> import numpy as np
>>> import albumentations as A
>>> import cv2
>>> image = np.random.randint(0, 256, (480, 640, 3), dtype=np.uint8)
>>> mask = np.random.randint(0, 2, (480, 640), dtype=np.uint8)
>>> bboxes = np.array([[100, 80, 300, 200]], dtype=np.float32)
>>> bbox_labels = [1]
>>> keypoints = np.array([[200, 150]], dtype=np.float32)
>>> keypoint_labels = [0]
>>>
>>> transform = A.Compose([
...     A.LetterBox(size=(640, 640), fill=114, fill_mask=0, 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']))
>>>
>>> result = transform(
...     image=image,
...     mask=mask,
...     bboxes=bboxes,
...     bbox_labels=bbox_labels,
...     keypoints=keypoints,
...     keypoint_labels=keypoint_labels,
... )
>>> result['image'].shape
(640, 640, 3)

>>> import albumentations as A
>>> import cv2
>>> # Using max_size
>>> transform1 = A.LongestMaxSize(max_size=1024, area_for_downscale="image")
>>> # Input image (1500, 800) -> Output (1024, 546)
>>>
>>> # Using max_size_hw with both dimensions
>>> transform2 = A.LongestMaxSize(max_size_hw=(800, 1024), area_for_downscale="image_mask")
>>> # Input (1500, 800) -> Output (800, 427)
>>> # Input (800, 1500) -> Output (546, 1024)
>>>
>>> # Using max_size_hw with only height
>>> transform3 = A.LongestMaxSize(max_size_hw=(800, None))
>>> # Input (1500, 800) -> Output (800, 427)
>>>
>>> # Common use case with padding
>>> transform4 = A.Compose([
...     A.LongestMaxSize(max_size=1024, area_for_downscale="image"),
...     A.PadIfNeeded(min_height=1024, min_width=1024),
... ])

>>> import numpy as np
>>> import albumentations as A
>>> import cv2
>>>
>>> # Create sample data for demonstration
>>> image = np.zeros((100, 100, 3), dtype=np.uint8)
>>> # Add some shapes to visualize scaling effects
>>> cv2.rectangle(image, (25, 25), (75, 75), (255, 0, 0), -1)  # Red square
>>> cv2.circle(image, (50, 50), 10, (0, 255, 0), -1)  # Green circle
>>>
>>> # Create a mask for segmentation
>>> mask = np.zeros((100, 100), dtype=np.uint8)
>>> mask[25:75, 25:75] = 1  # Mask covering the red square
>>>
>>> # Create bounding boxes and keypoints
>>> bboxes = np.array([[25, 25, 75, 75]])  # Box around the red square
>>> bbox_labels = [1]
>>> keypoints = np.array([[50, 50]])  # Center of circle
>>> keypoint_labels = [0]
>>>
>>> # Apply RandomScale transform with comprehensive parameters
>>> transform = A.Compose([
...     A.RandomScale(
...         scale_limit=(-0.3, 0.5),     # Scale between 0.7x and 1.5x
...         interpolation=cv2.INTER_LINEAR,
...         mask_interpolation=cv2.INTER_NEAREST,
...         area_for_downscale="image",  # Use INTER_AREA for image downscaling
...         p=1.0                         # Always apply
...     )
... ], 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
>>> result = transform(
...     image=image,
...     mask=mask,
...     bboxes=bboxes,
...     bbox_labels=bbox_labels,
...     keypoints=keypoints,
...     keypoint_labels=keypoint_labels
... )
>>>
>>> # Get the transformed results
>>> scaled_image = result['image']        # Dimensions will be between 70-150 pixels
>>> scaled_mask = result['mask']          # Mask scaled proportionally to image
>>> scaled_bboxes = result['bboxes']      # Bounding boxes adjusted to new dimensions
>>> scaled_bbox_labels = result['bbox_labels']  # Labels remain unchanged
>>> scaled_keypoints = result['keypoints']      # Keypoints adjusted to new dimensions
>>> scaled_keypoint_labels = result['keypoint_labels']  # Labels remain unchanged
>>>
>>> # The image dimensions will vary based on the randomly sampled scale factor
>>> # With scale_limit=(-0.3, 0.5), dimensions could be anywhere from 70% to 150% of original

>>> import numpy as np
>>> import albumentations as A
>>> import cv2
>>>
>>> # Create sample data for demonstration
>>> image = np.zeros((100, 100, 3), dtype=np.uint8)
>>> # Add some shapes to visualize resize effects
>>> cv2.rectangle(image, (25, 25), (75, 75), (255, 0, 0), -1)  # Red square
>>> cv2.circle(image, (50, 50), 10, (0, 255, 0), -1)  # Green circle
>>>
>>> # Create a mask for segmentation
>>> mask = np.zeros((100, 100), dtype=np.uint8)
>>> mask[25:75, 25:75] = 1  # Mask covering the red square
>>>
>>> # Create bounding boxes and keypoints
>>> bboxes = np.array([[25, 25, 75, 75]])  # Box around the red square
>>> bbox_labels = [1]
>>> keypoints = np.array([[50, 50]])  # Center of circle
>>> keypoint_labels = [0]
>>>
>>> # Resize all data to 224x224 (common input size for many CNNs)
>>> transform = A.Compose([
...     A.Resize(
...         height=224,
...         width=224,
...         interpolation=cv2.INTER_LINEAR,
...         mask_interpolation=cv2.INTER_NEAREST,
...         area_for_downscale="image",  # Use INTER_AREA when downscaling images
...         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
>>> result = transform(
...     image=image,
...     mask=mask,
...     bboxes=bboxes,
...     bbox_labels=bbox_labels,
...     keypoints=keypoints,
...     keypoint_labels=keypoint_labels
... )
>>>
>>> # Get the transformed results
>>> resized_image = result['image']        # Shape will be (224, 224, 3)
>>> resized_mask = result['mask']          # Shape will be (224, 224)
>>> resized_bboxes = result['bboxes']      # Bounding boxes scaled to new dimensions
>>> resized_bbox_labels = result['bbox_labels']  # Labels remain unchanged
>>> resized_keypoints = result['keypoints']      # Keypoints scaled to new dimensions
>>> resized_keypoint_labels = result['keypoint_labels']  # Labels remain unchanged
>>>
>>> # Note: When resizing from 100x100 to 224x224:
>>> # - The red square will be scaled from (25-75) to approximately (56-168)
>>> # - The keypoint at (50, 50) will move to approximately (112, 112)
>>> # - All spatial relationships are preserved but coordinates are scaled

>>> import numpy as np
>>> import albumentations as A
>>> # Using max_size
>>> transform1 = A.SmallestMaxSize(max_size=120, area_for_downscale="image")
>>> # Input image (100, 150) -> Output (120, 180)
>>>
>>> # Using max_size_hw with both dimensions
>>> transform2 = A.SmallestMaxSize(max_size_hw=(100, 200), area_for_downscale="image_mask")
>>> # Input (80, 160) -> Output (100, 200)
>>> # Input (160, 80) -> Output (400, 200)
>>>
>>> # Using max_size_hw with only height
>>> transform3 = A.SmallestMaxSize(max_size_hw=(100, None))
>>> # Input (80, 160) -> Output (100, 200)