Albumentations 2.0.4 Release Notes

• Support Our Work
• Transforms
• Bug fixes and speedups

Support Our Work

1. Help Us Grow - If you find value in Albumentations, consider becoming a sponsor. Every contribution, no matter the size, helps us maintain and improve the library for everyone.
2. Show Your Support - If you enjoy using Albumentations, consider giving us a ⭐ on GitHub. It helps others discover the library and motivates our team.
3. Join Our Community - Have suggestions or ran into issues? We welcome your input! Share your experience in our GitHub issues or connect with us on Discord.

Transforms

Added HEStain transform

Applies H&E (Hematoxylin and Eosin) stain augmentation to histopathology images.

    This transform simulates different H&E staining conditions using either:
    1. Predefined stain matrices (8 standard references)
    2. Vahadane method for stain extraction
    3. Macenko method for stain extraction
    4. Custom stain matrices

Bug fixes and speedups

• Fix in docstring in Rotate by @MalteEbner
• Extended and clarified docstring in Compose on how to fix random seed also added this info to FAQ
• Bugfix in RandomRain
• 1.5 times speedup in GaussNoise by @vedantdalimkar

Albumentations 2.0.3 Release Notes

• Support Our Work
• Core
• Bug fixes and speedups

Support Our Work

1. Help Us Grow - If you find value in Albumentations, consider becoming a sponsor. Every contribution, no matter the size, helps us maintain and improve the library for everyone.
2. Show Your Support - If you enjoy using Albumentations, consider giving us a ⭐ on GitHub. It helps others discover the library and motivates our team.
3. Join Our Community - Have suggestions or ran into issues? We welcome your input! Share your experience in our GitHub issues or connect with us on Discord.

Core

Extended the functionality of the strict parameter in Compose.

Now, if strict=True and you pass incorrect arguments to transforms in Compose => will get error.

if strict=False you will get only a warning

There was a lot of deprecation in the last year. It may happen that your augmentation pipeline does not behave as expected, as parameters that use in transforms are ignored, and default values are used instead.

Bug fixes and speedups

• Bugfix in filtering of bounding boxes based on aspect ratio by @CristoJV
• Speedup In SaltAndPepper
• Speedup in AutoContrast
• Speedup in Illumination Illumination
• Speedup in ElasticTransform
• Speedup in RandomRain
• Bugfix in passing int np.arrayas labels in BboxParams

Albumentations 2.0.2 Release Notes

• Support Our Work
• Core
• Bug fixes and speedups

Support Our Work

1. Help Us Grow - If you find value in Albumentations, consider becoming a sponsor. Every contribution, no matter the size, helps us maintain and improve the library for everyone.
2. Show Your Support - If you enjoy using Albumentations, consider giving us a ⭐ on GitHub. It helps others discover the library and motivates our team.
3. Join Our Community - Have suggestions or ran into issues? We welcome your input! Share your experience in our GitHub issues or connect with us on Discord.

Core

Added parameter max_accept_ratio to BBoxParams

max_accept_ratio (float | None): Maximum allowed aspect ratio for bounding boxes. 
    The aspect ratio is calculated as max(width/height, height/width), so it's always >= 1. 
    Boxes with aspect ratio greater than this value will be filtered out. 
    For example, if `max_accept_ratio=3.0`, boxes with width:height or height:width ratios
    greater than 3:1 will be removed. Set to None to disable aspect ratio filtering. Default: None.

Bugfixes and Speedups

• Bugfix in clip=True in BboxParams, was clipping not only boxes, but class labels if passed as numpy array
• BugFix in keypoints in all distortions: Elastic, Optical, Grid, ThinPlateSpline,
• Speedup in PlasmaShadow, PlasmaBrightnessContrast, ChannelShuffle

Albumentations 2.0.1 Release Notes

• Support Our Work
• Core
• Bugfixes and speedups

Support Our Work

1. Help Us Grow - If you find value in Albumentations, consider becoming a sponsor. Every contribution, no matter the size, helps us maintain and improve the library for everyone.
2. Show Your Support - If you enjoy using Albumentations, consider giving us a ⭐ on GitHub. It helps others discover the library and motivates our team.
3. Join Our Community - Have suggestions or ran into issues? We welcome your input! Share your experience in our GitHub issues or connect with us on Discord.

Core

Added parameter filter_invalid_bboxes to BboxParams.

If True, filters out invalid bounding boxes (e.g., boxes with negative dimensions or boxes where x_max < x_min or y_max < y_min at the beginning of the pipeline. If clip=True, filtering is applied after clipping. Default: False.

Bugfixes and speedups:

• Speedup in CubicSymmetry by @ternaus
• Speedup in FromFloat, when applied to images, volume, volumes
• Bugfix in PixelDropout, was not supporting sequence as fill
• BugFix in GaussianBlur. Did not preserve brightness and did not scale properly at large sigma. Fixed. Also now matches behavior in PIL pretty close
• Bugfix in distortions: OpticalDistortion, GridDistortion, ElasticTransform, ThinPlateSpline. Only bounding boxes and keypoints were affected. by @RhysEvan

Albumentations 2.0.0 Release Notes

This is major release, meaning

• only one new transform

• a lot of changes.

  • all parameter renaming was moved through deprecations => you got deprecation warning for months
  • A few transform have change of default parameters. If you always specify parameters for each augmentations => it will not affect you.

If you have questions or proposals:

• GitHub issues
• Discord

If you have complaints:

• Will be happy to see you as one of our sponsors at https://github.com/sponsors/albumentations-team

New transform

ConstrainedCoarseDropout

by @vedantdalimkar

Core

• Deleted always_apply => use p=1 to always apply and p=0 for not applying.
• Deleted update_params, get_params_dependent_on_targets => use get_params_dependent_on_data

Transforms

GaussNoise

• Deleted: var_limit, mean
• Use: std_range, mean_range

It is not just a renaming, var_limit and std_range sample from different distributions. Sampling from std_range matches with other libraries like torchvision.

AdvancedBlur

• Deleted: sigmaX_limit, sigmaY_limit
• Use: sigma_x_limit, sigma_y_limit

RandomCrop

• Deleted pad_mode, pad_val_mask, pad_cvl
• Use: border_mode, fill_mask, fill

CenterCrop

• Deleted pad_mode, pad_val_mask, pad_cvl
• Use: border_mode, fill_mask, fill

Crop

• Deleted pad_mode, pad_val_mask, pad_cvl
• Use: border_mode, fill_mask, fill

RandomResizedCrop

• Deleted: height, width
• Use: size

RandomSizedCrop

• Deleted: height, width
• Use: size

RandomCropNearBBox

• Deleted: cropping_box_key
• Use: cropping_bbox_key

CropAndPad

• Deleted: pad_mode, pad_val_mask, pad_cvl
• Use: border_mode, fill_mask, fill

TemplateTransform

• Deleted: template_weight

ChannelDropout

• Deleted: fill_value
• Use: fill

CoarseDropout

• Deleted: min_holes, max_holes, min_height, max_height, min_width, max_width, mask_fill_value, fill_value
• Use: num_holes_range, hole_height_range, hole_width_range, fill, fill_mask

Also default parameters changed:
num_height_range = (8, 8) => num_height_range = (0.1, 0.2)
num_width_range = (8, 8) => num_width_range = (0.1, 0.2)

GridDropout

• Deleted: unit_size_min, unit_size_max, holes_number_x, holes_number_y, shift_x, shift_y, fill_value, mask_fill_value
• Use: unit_size_range, holes_number_xy, fill, fill_mask

MaskDropout

• Deleted: image_fill_value, mask_fill_value
• Use: fill, fill_mask

XYMasking

• Deleted: mask_fill_value, fill_value
• Use: fill, fill_mask

Rotate

• Deleted: value, mask_value
• Use: fill, fill_mask

Changed default value for border_mode from cv2.BORDER_REFLECT_101 to cv2.BORDER_CONSTANT

SafeRotate

• Deleted: value, mask_value
• Use: fill, fill_mask

Changed default value for border_mode from cv2.BORDER_REFLECT_101 to cv2.BORDER_CONSTANT

ElasticTransform

• Deleted: border_mode, value, mask_value

Perspective

• Deleted: pad_mode, pad_val, mask_pad_val

Affine

• Deleted: cval, cval_mask, mode
• Use: fill, fill_mask, border_mode

ShiftScaleRotate

• Deleted: value, mask_value
• Use: fill, fill_mask

Changed default border_mode from cv2.BORDER_REFLECT_101 to cv2.BORDER_CONSTANT

PiesewiseAffine

• Deleted: cval, cval_mask, mode, keypoints_threshold

OpticalDistortion

• Deleted: shift_limit, value, mask_value, border_mode

GridDistortion

• Deleted: value, mask_value, border_mode

RandomRotate90

Changed default probability from p=0.5 to p=1

PadIfNeeded

• Deleted: value, mask_value
• Use: fill, fill_mask

Changed default value for border_mode from cv2.BORDER_REFLECT_101 to cv2.BORDER_CONSTANT

ImageCompression

• Deleted: quality_lower, quality_upper
• Use: quality_range

RandomSnow

• Deleted: snow_point_lower, snow_point_upper
• Use: snow_point_range

RandomRain

• Deleted: slant_lower, slant_upper
• Use: slant_range

RandomFog

• Deleted: fog_coef_lower, fog_coef_upper
• Use: fog_coef_range

RandomSunFlare

• Deleted: angle_lower, angle_upper, num_flare_circles_lower, num_flare_circles_upper
• Use: num_flare_circles_range, angle_range

RandomShadow

• Deleted: num_shadows_lower, num_shadows_upper
• Use: num_shadows_limit

Solarize

• Deleted: threshold
• Use: threshold_range

Downscale

• Deleted interpolation, scale_min, scale_max
• Use: interpolation_pair, scale_range

by @ternaus

Small improvements

• Fixed links in readme by @guspan-tanadi
• Better bounding box processing in Dropouts

Albumentations 1.4.24 Release Notes

• Support Our Work
• Core
• Transforms
• Bugfixes

Support Our Work

1. Help Us Grow - If you find value in Albumentations, consider becoming a sponsor. Every contribution, no matter the size, helps us maintain and improve the library for everyone.
2. Show Your Support - If you enjoy using Albumentations, consider giving us a ⭐ on GitHub. It helps others discover the library and motivates our team.
3. Join Our Community - Have suggestions or ran into issues? We welcome your input! Share your experience in our GitHub issues or connect with us on Discord.

Core

• Added new keypoints format xyz for ImageOnly and Dual transforms (z coordinate stays unchanged)

Transforms

New transform AtLeastOneBBoxRandomCrop

Crop an area from image while ensuring at least one bounding box is present in the crop.

by @guillaume-rochette-oxb

Improvements

• SmallestMaxSize: Added option for separate max_size for height/width
• LongestMaxSize: Added option for separate max_size for height/width
• Added keypoints support to: CenterCrop3D, CoarseDropout3D, CubicSymmetry, Pad3D, PadIfNeeded3D, RandomCrop3D (by @ternaus)

Bugfixes

• Do not import eval-type-backport for python 3.10 and older. by @PerchunPak
• Bugfix in ToTensorV2 by @matejpekar

Albumentations 1.4.23 Release Notes

• Support Our Work
• Core
• Transforms
• Bugfixes

Support Our Work

1. Help Us Grow - If you find value in Albumentations, consider becoming a sponsor. Every contribution, no matter the size, helps us maintain and improve the library for everyone.
2. Show Your Support - If you enjoy using Albumentations, consider giving us a ⭐ on GitHub. It helps others discover the library and motivates our team.
3. Join Our Community - Have suggestions or ran into issues? We welcome your input! Share your experience in our GitHub issues or connect with us on Discord.

Core

Target images as numpy array

Now supports numpy arrays with shape (num_images, height, width, num_channels) or (num_images, height, width) as images in Compose

• Ideal for video processing applications
• Same transform applies to all images in the array

New 3D Data Support

• volume: (depth, height, width) or (depth, height, width, num_channels)
• mask3d: (depth, height, width) or (depth, height, width, num_channels)
• volumes: (num_volumes, depth, height, width) for batch processing
• masks3d: (num_volumes, depth, height, width) for batch processing

volume = np.random.rand(96, 256, 256) # Your 3D medical volume
mask = np.zeros((96, 256, 256)) # Your 3D segmentation mask
transformed = transform(volume=volume, mask3d=mask)
transformed_volume = transformed['volume']
transformed_mask = transformed['mask3d']

Transforms

Added 3D transforms by @ternaus

Padding & Cropping

• Pad3D: Pad 3D volumes with flexible padding options
• PadIfNeeded3D: Conditional padding to meet minimum dimensions or divisibility requirements
• CenterCrop3D: Center cropping for 3D volumes
• RandomCrop3D: Random cropping of 3D volumes

transform = A.Compose([
    # Crop volume to a fixed size for memory efficiency
    A.RandomCrop3D(size=(64, 128, 128), p=1.0),    
    # Randomly remove cubic regions to simulate occlusions
    A.CoarseDropout3D(
        num_holes_range=(2, 6),
        hole_depth_range=(0.1, 0.3),
        hole_height_range=(0.1, 0.3),
        hole_width_range=(0.1, 0.3),
        p=0.5
    ),    
])

volume = np.random.rand(96, 256, 256) # Your 3D medical volume
mask = np.zeros((96, 256, 256)) # Your 3D segmentation mask
transformed = transform(volume=volume, mask3d=mask)
transformed_volume = transformed['volume']
transformed_mask = transformed['mask3d']

Augmentation

• CoarseDropout3D: Random cuboid dropout regions for occlusion simulation
• CubicSymmetry: 48 possible cube symmetry transformations (24 rotations + 24 rotoreflections)

Fixes

• Added flexible brightness in RandomSunFlare by @momincks
• Bugfix in CenterCrop, RandomCrop by @iRyoka
• Fix in Normalize docstring by @mennohofste

Albumentations 1.4.22 Release Notes

• Support Our Work
• Transforms
• Core
• Bugfixes

Support Our Work

1. Help Us Grow - If you find value in Albumentations, consider becoming a sponsor. Every contribution, no matter the size, helps us maintain and improve the library for everyone.
2. Show Your Support - If you enjoy using Albumentations, consider giving us a ⭐ on GitHub. It helps others discover the library and motivates our team.
3. Join Our Community - Have suggestions or ran into issues? We welcome your input! Share your experience in our GitHub issues or connect with us on Discord.

Transforms

Elastic Transform

1. Added argument noise_distribution that allows sampling displacement fields from gaussian and from uniform distributions.
2. Deprecated parameters border_mode, value, mask_value - you can specify them, but will not have any effect.

New transform ShotNoise

Apply shot noise to the image by modeling photon counting as a Poisson process.

    Shot noise (also known as Poisson noise) occurs in imaging due to the quantum nature of light.
    When photons hit an imaging sensor, they arrive at random times following Poisson statistics.
    This transform simulates this physical process in linear light space by:
    1. Converting to linear space (removing gamma)
    2. Treating each pixel value as an expected photon count
    3. Sampling actual photon counts from a Poisson distribution
    4. Converting back to display space (reapplying gamma)

    The noise characteristics follow real camera behavior:
    - Noise variance equals signal mean in linear space (Poisson statistics)
    - Brighter regions have more absolute noise but less relative noise
    - Darker regions have less absolute noise but more relative noise
    - Noise is generated independently for each pixel and color channel

RandomGridShuffle

Addes support for bounding boxes

CorseDropout

Added an option to inpaint holes using inpaint_ns and inpaint_telea from OpenCV

GridDropout

Added an option to inpaint holes using inpaint_ns and inpaint_telea from OpenCV

MaskDropout

Added an option to inpaint holes using inpaint_ns and inpaint_telea from OpenCV

XYMasking

Added an option to inpaint holes using inpaint_ns and inpaint_telea from OpenCV

New transform TimeReverse

Added NewTransform TimeReverse

Reverse the time axis of a spectrogram image, also known as time inversion.

    Time inversion of a spectrogram is analogous to the random flip of an image,
    an augmentation technique widely used in the visual domain. This can be relevant
    in the context of audio classification tasks when working with spectrograms.
    The technique was successfully applied in the AudioCLIP paper, which extended
    CLIP to handle image, text, and audio inputs.

    This transform is implemented as a subclass of HorizontalFlip since reversing
    time in a spectrogram is equivalent to flipping the image horizontally.

New transform TimeMasking

Added NewTransform TimeMasking

Apply masking to a spectrogram in the time domain.

    This transform masks random segments along the time axis of a spectrogram,
    implementing the time masking technique proposed in the SpecAugment paper.
    Time masking helps in training models to be robust against temporal variations
    and missing information in audio signals.

    This is a specialized version of XYMasking configured for time masking only.
    For more advanced use cases (e.g., multiple masks, frequency masking, or custom
    fill values), consider using XYMasking directly.

New transform FrequencyMasking

Apply masking to a spectrogram in the frequency domain.

    This transform masks random segments along the frequency axis of a spectrogram,
    implementing the frequency masking technique proposed in the SpecAugment paper.
    Frequency masking helps in training models to be robust against frequency variations
    and missing spectral information in audio signals.

    This is a specialized version of XYMasking configured for frequency masking only.
    For more advanced use cases (e.g., multiple masks, time masking, or custom
    fill values), consider using XYMasking directly.

Added NewTransform FrequencyMasking

It is a specialized version of XYMasking that has the similar API as FrequencyMasking from torchaudio

New Transform Pad

Pad the sides of an image by specified number of pixels.

    Args:
        padding (int, tuple[int, int] or tuple[int, int, int, int]): Padding values. Can be:
            * int - pad all sides by this value
            * tuple[int, int] - (pad_x, pad_y) to pad left/right by pad_x and top/bottom by pad_y
            * tuple[int, int, int, int] - (left, top, right, bottom) specific padding per side

This is the generalization of the torchvision transform with the same name

New Transform Erasing

This is the generalization of the similar torchvision transform

Randomly erases rectangular regions in an image, following the Random Erasing Data Augmentation technique.

    This augmentation helps improve model robustness by randomly masking out rectangular regions in the image,
    simulating occlusions and encouraging the model to learn from partial information. It's particularly
    effective for image classification and person re-identification tasks.

New Transform AdditiveNoise

Apply random noise to image channels using various noise distributions.

    This transform generates noise using different probability distributions and applies it
    to image channels. The noise can be generated in three spatial modes and supports
    multiple noise distributions, each with configurable parameters.

    Args:
        noise_type: Type of noise distribution to use. Options:
            - "uniform": Uniform distribution, good for simple random perturbations
            - "gaussian": Normal distribution, models natural random processes
            - "laplace": Similar to Gaussian but with heavier tails, good for outliers
            - "beta": Flexible bounded distribution, can be symmetric or skewed

        spatial_mode: How to generate and apply the noise. Options:
            - "constant": One noise value per channel, fastest
            - "per_pixel": Independent noise value for each pixel and channel, slowest
            - "shared": One noise map shared across all channels, medium speed

Sharpen

Added 'gaussian' method for image sharpening.

New transform SaltAndPepper

Apply salt and pepper noise to the input image.

    Salt and pepper noise is a form of impulse noise that randomly sets pixels to either maximum value (salt)
    or minimum value (pepper). The amount and proportion of salt vs pepper noise can be controlled.

New transform PlasmaBrightNessContrast

Apply plasma fractal pattern to modify image brightness and contrast.

    This transform uses the Diamond-Square algorithm to generate organic-looking fractal patterns
    that are then used to create spatially-varying brightness and contrast adjustments.
    The result is a natural-looking, non-uniform modification of the image.

New Transform PlasmaShadow

<img width="118...

Albumentations 1.4.21 Release Notes

• Support Our Work
• Transforms
• Core
• Benchmark
• Speedups

Support Our Work

1. Love the library? You can contribute to its development by becoming a sponsor for the library. Your support is invaluable, and every contribution makes a difference.
2. Haven't starred our repo yet? Show your support with a ⭐! It's just only one mouse click away.
3. Got ideas or facing issues? We'd love to hear from you. Share your thoughts in our issues or join the conversation on our Discord server

Transforms

Auto padding in crops

Added option to pad the image if crop size is larger than the crop size

Old way

[
A.PadIfNeeded(min_height=1024, min_width=1024, p=1),
A.RandomCrop(height=1204, width=1024, p=1)
]

New way:

A.RandomCrop(height=1204, width=1024, p=1, pad_if_needed=True)

Works for:

• RandomCrop
• CenterCrop
• Crop

You may also use it to pad image to a desired size.

Core

Random state

Now random state for the pipeline does not depend on the global random state

Before

random.seed(seed)
np.random.seed(seed)

transform = A.Compose(...) 

Now

transform = A.Compose(seed=seed, ...)

or

transform = A.Compose(...)
transform.set_random_seed(seed)

Saving used parameters

Now you can get exact parameters that were used in the pipeline on a given sample with

transform = A.Compose(save_applied_params=True, ...)

result = transform(image=image, bboxes=bboxes, mask=mask, keypoints=keypoints)

print(result["applied_transforms"])

Benchmark

Moved benchmark to a separate repo

https://github.com/albumentations-team/benchmark/

Current result for uint8 images:

Transform	albumentations 1.4.20	augly 1.0.0	imgaug 0.4.0	kornia 0.7.3	torchvision 0.20.0
HorizontalFlip	8325 ± 955	4807 ± 818	6042 ± 788	390 ± 106	914 ± 67
VerticalFlip	20493 ± 1134	9153 ± 1291	10931 ± 1844	1212 ± 402	3198 ± 200
Rotate	1272 ± 12	1119 ± 41	1136 ± 218	143 ± 11	181 ± 11
Affine	967 ± 3	-	774 ± 97	147 ± 9	130 ± 12
Equalize	961 ± 4	-	581 ± 54	152 ± 19	479 ± 12
RandomCrop80	118946 ± 741	25272 ± 1822	11503 ± 441	1510 ± 230	32109 ± 1241
ShiftRGB	1873 ± 252	-	1582 ± 65	-	-
Resize	2365 ± 153	611 ± 78	1806 ± 63	232 ± 24	195 ± 4
RandomGamma	8608 ± 220	-	2318 ± 269	108 ± 13	-
Grayscale	3050 ± 597	2720 ± 932	1681 ± 156	289 ± 75	1838 ± 130
RandomPerspective	410 ± 20	-	554 ± 22	86 ± 11	96 ± 5
GaussianBlur	1734 ± 204	242 ± 4	1090 ± 65	176 ± 18	79 ± 3
MedianBlur	862 ± 30	-	813 ± 30	5 ± 0	-
MotionBlur	2975 ± 52	-	612 ± 18	73 ± 2	-
Posterize	5214 ± 101	-	2097 ± 68	430 ± 49	3196 ± 185
JpegCompression	845 ± 61	778 ± 5	459 ± 35	71 ± 3	625 ± 17
GaussianNoise	147 ± 10	67 ± 2	206 ± 11	75 ± 1	-
Elastic	171 ± 15	-	235 ± 20	1 ± 0	2 ± 0
Clahe	423 ± 10	-	335 ± 43	94 ± 9	-
CoarseDropout	11288 ± 609	-	671 ± 38	536 ± 87	-
Blur	4816 ± 59	246 ± 3	3807 ± 325	-	-
ColorJitter	536 ± 41	255 ± 13	-	55 ± 18	46 ± 2
Brightness	4443 ± 84	1163 ± 86	-	472 ± 101	429 ± 20
Contrast	4398 ± 143	736 ± 79	-	425 ± 52	335 ± 35
RandomResizedCrop	2952 ± 24	-	-	287 ± 58	511 ± 10
Normalize	1016 ± 84	-	-	626 ± 40	519 ± 12
PlankianJitter	1844 ± 208	-	-	813 ± 211	-

Speedups

• Speedup in PlankianJitter in uint8 mode
• Replaced cv2.addWeighted with wsum from simsimd package

Albumentations 1.4.20 Release Notes

Hotfix version.

• Fix in check_version
• Fix in PieceWiseAffine
• Fix in RandomSizedCrop and RandomResizedCrop
• Fix in RandomOrder