Albumentations 1.4.9 Release Notes

• Support our work
• New transforms
• Integrations
• Speedups
• Deprecations
• Improvements and bug fixes

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.
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 for Albumentations

Transforms

PlanckianJitter

New transform, based on

• Paper: https://arxiv.org/abs/2202.07993
• Repo: https://github.com/TheZino/PlanckianJitter

Statements from the paper on why PlanckianJitter is superior to ColorJitter:

1. Realistic Color Variations: PlanckianJitter applies physically realistic illuminant variations based on Planck’s Law for black-body radiation. This leads to more natural and realistic variations in chromaticity compared to the arbitrary changes in hue, saturation, brightness, and contrast applied by ColorJitter​​.

2. Improved Representation for Color-Sensitive Tasks: The transformations in PlanckianJitter maintain the ability to discriminate image content based on color information, making it particularly beneficial for tasks where color is a crucial feature, such as classifying natural objects like birds or flowers. ColorJitter, on the other hand, can significantly alter colors, potentially degrading the quality of learned color features​​.

3. Robustness to Illumination Changes: PlanckianJitter produces models that are robust to illumination changes commonly observed in real-world images. This robustness is advantageous for applications where lighting conditions can vary widely​​.

4. Enhanced Color Sensitivity: Models trained with PlanckianJitter show a higher number of color-sensitive neurons, indicating that these models retain more color information compared to those trained with ColorJitter, which tends to induce color invariance​​.

by @zakajd

GaussNoise

Added option to approximate GaussNoise.

Generation of random Noise for large images is slow.

Added scaling factor for noise generation. Value should be in the range (0, 1]. When set to 1, noise is sampled for each pixel independently. If less, noise is sampled for a smaller size and resized to fit the shape of the image. Smaller values make the transform much faster. Default: 0.5

Integrations

Added integration wit HFHub. Now you can load and save augmentation pipeline to HuggingFace and reuse it in the future or share with others.

Notebook with documentation

import albumentations as A
import numpy as np

transform = A.Compose([
    A.RandomCrop(256, 256),
    A.HorizontalFlip(),
    A.RandomBrightnessContrast(),
    A.RGBShift(),
    A.Normalize(),
])

evaluation_transform = A.Compose([
    A.PadIfNeeded(256, 256),
    A.Normalize(),
])

transform.save_pretrained("qubvel-hf/albu", key="train")
# ^ this will save the transform to a directory "qubvel-hf/albu" with filename "albumentations_config_train.json"

transform.save_pretrained("qubvel-hf/albu", key="train", push_to_hub=True)
# ^ this will save the transform to a directory "qubvel-hf/albu" with filename "albumentations_config_train.json"
# + push the transform to the Hub to the repository "qubvel-hf/albu"

transform.push_to_hub("qubvel-hf/albu", key="train")
# ^ this will push the transform to the Hub to the repository "qubvel-hf/albu" (without saving it locally)

loaded_transform = A.Compose.from_pretrained("qubvel-hf/albu", key="train")
# ^ this will load the transform from local folder if exist or from the Hub repository "qubvel-hf/albu"

evaluation_transform.save_pretrained("qubvel-hf/albu", key="eval", push_to_hub=True)
# ^ this will save the transform to a directory "qubvel-hf/albu" with filename "albumentations_config_eval.json"

loaded_evaluation_transform = A.Compose.from_pretrained("qubvel-hf/albu", key="eval")
# ^ this will load the transform from the Hub repository "qubvel-hf/albu"

by @qubvel

Speedups

These transforms should be faster for all types of images. But measured only for three channel uint8

• RGBShift: 2X (+106%)
• GaussNoise: 3.3X (+ 236%)

Full updated benchmark

Deprecations

Deprecated always_apply

For years we had two parameters in constructors - probability and always_apply. The interplay between them is not always obvious and intuitively always_apply=True should be equivalent to p=1.

always_apply is deprecated now. always_apply=True still works, but it will be deprecated in the future. Use p=1 instead

by @ayasyrev

RandomFog

Updated interface for RandomFog

Old way:

RandomFog(fog_coef_lower=0.3, fog_coef_upper=1)

New way:

RandomFog(fog_coef_range=(0.3, 1))

by @ternaus

Improvements and bugfixes

Disable check for updates

When one imports Albumentations library, there is a check that it is the latest version installed.

To disable this check you can set up environmental variable: NO_ALBUMENTATIONS_UPDATE to 1

by @lerignoux

Fix for deprecation warnings

For a set of transforms we were throwing deprecation warnings, even when modern version of the interface was used. Fixed. by @ternaus

Albucore

We moved low level operations like add, multiply, normalize, etc to a separate library: https://github.com/albumentations-team/albucore

There are numerous ways to perform such operations in opencv and numpy. And there is no clear winner. Results depend on image type.

Separate library gives us confidence that we picked the fastest version that works on any image type.

by @ternaus

Bugfixes

Various bugfixes by @ayasyrev @immortalCO

Albumentations 1.4.8 Release Notes

• Support our work
• Documentation
• Deprecations
• Improvements and bug fixes

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.
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 for Albumentations

Documentation

Added to the documentation links to the UI on HuggingFace to explore hyperparameters visually.

Deprecations

RandomSnow

Updated interface:

Old way:

transform = A.Compose([A.RandomSnow(
  snow_point_lower=0.1,
  snow_point_upper=0.3,
  p=0.5
)])

New way:

transform = A.Compose([A.RandomSnow(
  snow_point_range=(0.1, 0.3),
  p=0.5
)])

by @MarognaLorenzo

RandomRain

Old way

transform = A.Compose([A.RandomSnow(
  slant_lower=-10,
  slant_upper=10,
  p=0.5
)])

New way:

transform = A.Compose([A.RandomRain(
  slant_range=(-10, 10),
  p=0.5
)])

by @MarognaLorenzo

Improvements

Created library with core functions albucore. Moved a few helper functions there.
We need this library to be sure that transforms are:

1. At least as fast as numpy and opencv. For some functions it is possible to be faster than both of them.
2. Easier to debug.
3. Could be used in other projects, not related to Albumentations.

Bugfixes

• Bugfix in check_for_updates. Now the pipeline does not throw an error regardless of why we cannot check for update.
• Bugfix in RandomShadow. Does not create unexpected purple color on bright white regions with shadow overlay anymore.
• BugFix in Compose. Now Compose([]) does not throw an error, but just works as NoOp by @ayasyrev
• Bugfix in min_max normalization. Now return 0 and not NaN on constant images. by @ternaus
• Bugfix in CropAndPad. Now we can sample pad/crop values for all sides with interface like ((-0.1, -0.2), (-0.2, -0.3), (0.3, 0.4), (0.4, 0.5)) by @christian-steinmeyer
• Small refactoring to decrease tech debt by @ternaus and @ayasyrev

Albumentations 1.4.7 Release Notes

• Support our work
• Documentation
• Deprecations
• Improvements and bug fixes

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.
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 for Albumentations

Documentation

• Added to the website tutorial on how to use Albumentations with Hugginigface for object Detection. Based on the tutorial by @qubvel

Deprecations

ImageCompression

Old way:

transform = A.Compose([A.ImageCompression(
  quality_lower=75,
  quality_upper=100,
  p=0.5
)])

New way:

transform = A.Compose([A.ImageCompression(
  quality_range=(75, 100),  
  p=0.5
)])

by @MarognaLorenzo

Downscale

Old way:

transform = A.Compose([A.Downscale(
  scale_min=0.25,
  scale_max=1,
  interpolation= {"downscale": cv2.INTER_AREA, "upscale": cv2.INTER_CUBIC},
  p=0.5
)])

New way:

transform = A.Compose([A.Downscale(
  scale_range=(0.25, 1),
 interpolation_pair = {"downscale": cv2.INTER_AREA, "upscale": cv2.INTER_CUBIC},  
  p=0.5
)])

As of now both ways work and will provide the same result, but old functionality will be removed in later releases.

by @ternaus

Improvements

• Buggix in Blur.
• Bugfix in bbox clipping, it could be not intuitive, but boxes should be clipped by height, width and not height - 1, width -1 by @ternaus
• Allow to compose only keys, that are required there. Any extra unnecessary key will give an error by @ayasyrev
• In PadIfNeeded if value parameter is not None, but border mode is reflection, border mode is changed to cv2.BORDER_CONSTANT by @ternaus

Albumentations 1.4.6 Release Notes

This is out of schedule release with a bugfix that was introduced in version 1.4.5

In version 1.4.5 there was a bug that went unnoticed - if you used pipeline that consisted only of ImageOnly transforms but pass bounding boxes into it, you would get an error.

If you had in such pipeline at least one non ImageOnly transform, say HorizontalFlip or Crop, everything would work as expected.

We fixed the issue and added tests to be sure that it will not happen in the future.

Albumentations 1.4.5 Release Notes

• Support our work
• Highlights
• Deprecations
• Improvements and bug fixes

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.
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 for Albumentations

Highlights

Bbox clipping

Before version 1.4.5 it was assumed that bounding boxes that are fed into the augmentation pipeline should not extend outside of the image.

Now we added an option to clip boxes to the image size before augmenting them. This makes pipeline more robust to inaccurate labeling

Example:

Will fail if boxes extend outside of the image:

transform = A.Compose([    
    A.HorizontalFlip(p=0.5)    
], bbox_params=A.BboxParams(format='coco'))

Clipping bounding boxes to the image size:

transform = A.Compose([    
    A.HorizontalFlip(p=0.5)    
], bbox_params=A.BboxParams(format='coco', clip=True))

by @ternaus

SelectiveChannelTransform

Added SelectiveChannelTransform that allows to apply transforms to a selected number of channels.

For example it could be helpful when working with multispectral images, when RGB is a subset of the overall multispectral stack which is common when working with satellite imagery.

Example:

aug = A.Compose(
        [A.HorizontalFlip(p=0.5),
        A.SelectiveChannelTransform(transforms=[A.ColorJItter(p=0.5),
        A.ChromaticAberration(p=0.5))], channels=[1, 2, 18], p=1)],
    )

Here HorizontalFlip applied to the whole multispectral image, but pipeline of ColorJitter and ChromaticAberration only to channels [1, 2, 18]

by @ternaus

Deprecations

CoarseDropout

Old way:

transform = A.Compose([A.CoarseDropout(
  min_holes = 5,
  max_holes = 8,
  min_width = 3,
  max_width = 12,
  min_height = 4,
  max_height = 5
)])

New way:

transform = A.Compose([A.CoarseDropout(
  num_holes_range=(5, 8),
  hole_width_range=(3, 12),
  hole_height_range=(4, 5)
)])

As of now both ways work and will provide the same result, but old functionality will be removed in later releases.

@ternaus

Improvements and bug fixes

• Number of fixes and speedups in the core of the library Compose and BasicTransform by @ayasyrev
• Extended Contributor's guide by @ternaus
• Can use random for fill_value in CoarseDropoutby @ternaus
• Fix in ToGray docstring by @wilderrodrigues
• BufFix in D4 - now works not only with square, but with rectangular images as well. By @ternaus
• BugFix in RandomCropFromBorders by @ternaus

Albumentations 1.4.4 Release Notes

Albumentations 1.4.4 Release Notes

• Support our work
• Highlights
• Transforms
• Improvements and bug fixes

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.
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 for Albumentations

Transforms

Added D4 transform

Applies one of the eight possible D4 dihedral group transformations to a square-shaped input, maintaining the square shape. These transformations correspond to the symmetries of a square, including rotations and reflections by @ternaus

The D4 group transformations include:
- e (identity): No transformation is applied.
- r90 (rotation by 90 degrees counterclockwise)
- r180 (rotation by 180 degrees)
- r270 (rotation by 270 degrees counterclockwise)
- v (reflection across the vertical midline)
- hvt (reflection across the anti-diagonal)
- h (reflection across the horizontal midline)
- t (reflection across the main diagonal)

Could be applied to:

• image
• mask
• bounding boxes
• key points

Does not generate interpolation artifacts as there is no interpolation.

Provides the most value in tasks where data is invariant to rotations and reflections like:

• Top view drone and satellite imagery
• Medical images

Example:

Added new normalizations to Normalize transform

• standard - subtract fixed mean, divide by fixed std
• image - the same as standard, but mean and std computed for each image independently.
• image_per_channel - the same as before, but per channel
• min_max - subtract min(image)and divide by max(image) - min(image)
• min_max_per_channel - the same, but per channel
  by @ternaus

Changes in the interface of RandomShadow

New, preferred wat is to use num_shadows_limit instead of num_shadows_lower / num_shadows_upper by @ayasyrev

Improvements and bug fixes

Added check for input parameters to transforms with Pydantic

Now all input parameters are validated and prepared with Pydantic. This will prevent bugs, when transforms are initialized without errors with parameters that are outside of allowed ranges.
by @ternaus

Updates in RandomGridShuffle

1. Bugfix by @ayasyrev
2. Transform updated to work even if side is not divisible by the number of tiles. by @ternaus

Example:

New way to add additional targets

Standard way uses additional_targets

transform = A.Compose(
    transforms=[A.Rotate(limit=(90.0, 90.0), p=1.0)],
    keypoint_params=A.KeypointParams(
        angle_in_degrees=True,
        check_each_transform=True,
        format="xyas",
        label_fields=None,
        remove_invisible=False,
    ),
    additional_targets={"keypoints2": "keypoints"},
)

Now you can also add them using add_targets:

transform = A.Compose(
    transforms=[A.Rotate(limit=(90.0, 90.0), p=1.0)],
    keypoint_params=A.KeypointParams(
        angle_in_degrees=True,
        check_each_transform=True,
        format="xyas",
        label_fields=None,
        remove_invisible=False,
    ),
)
transform.add_targets({"keypoints2": "keypoints"})

by @ayasyrev

Small fixes

• Small speedup in the code for transforms that use add_weighted function by @gogetron
• Fix in error message in Affine transform by @matsumotosan
• Bugfix in Sequential by @ayasyrev

Documentation

• Updated Contributor's guide. by @ternaus
• Added example notebook on how to apply D4 to images, masks, bounding boxes and key points. by @ternaus
• Added example notebook on how to apply RandomGridShuffle to images, masks and keypoints. by @ternaus

Albumentations 1.4.3 Release Notes

Albumentations 1.4.3 Release Notes

• Request
• Highlights
• New transform
• Minor improvements and bug fixes

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.
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 for Albumentations

New transform

• Added Morphological transform that modifies the structure of the image. Dilation expands the white (foreground) regions in a binary or grayscale image, while erosion shrinks them.

Minor improvements and bug fixes

• Updated benchmark for uint8 images, processed on CPU. Added Kornia and Augly. LINK by @ternaus
• Bugfix in FDA transform by @ternaus
• Now RandomSizedCrop supports the same signature as analogous transform in torchvision by @zetyquickly

1.4.2

Albumentations 1.4.2 Release Notes

• Request
• Highlights
• New transform
• New functionality
• Improvements and bug fixes

Request

1. If you enjoy using the library as an individual developer or as a representative of the company please consider becoming a sponsor for the library. Every dollar helps.
2. If you did not give our repo a ⭐, it is only one mouse click
3. If you have feature requests or proposals or encounter issues - submit your request to issues or ask in Discord server for Albumentations

New transform

Left: Original, Middle: Chromatic aberration (default args, mode="green_purple"), Right: Chromatic aberration (default args, mode="red_blue")
(Image is from our internal mobile mapping dataset)

• Added ChromaticAbberation transform that adds chromatic distortion to the image. Wiki by @mrsmrynk

New functionality

• Return mixing parameter for MixUp transform by @Dipet. For more details Tutorial on MixUp

Improvements and Bugfixes

• Do not throw deprecation warning when people do not use deprecated parameters in AdvancedBlur by @Aloqeely
• Updated CONTRIBUTORS.md for Windows users by @Aloqeely
• Fixed Docstring for DownScale transform by @ryoryon66
• Bugfix in PadIfNeeded serialization @ternaus

1.4.1

Albumentations 1.4.1 Release Notes

• Request
• Highlights
• New transform
• Improvements
• Bug fixes

Request

1. If you enjoy using the library as an individual developer or during the day job as a part of the company, please consider becoming a sponsor for the library. Every dollar helps.
2. If you did not give our repo a ⭐, it is only one mouse click
3. If you have feature requests or proposals or encounter issues - submit your request to issues or our new initiative, - Discord server for albumentations

New transform

• Added MixUp transform: which linearly combines an input (image, mask, and class label) with another set from a predefined reference dataset. The mixing degree is controlled by a parameter λ (lambda), sampled from a Beta distribution. This method is known for improving model generalization by promoting linear behavior between classes and smoothing decision boundaries.

Minor changes and Bug Fixes

• Moved from isort, flake8, black to ruff
• Added extra checks for docstrings to match Google Style.
• Updated Who's using
• Removed quidda dependency, which addresses opencv library inconsistencies issues
• New, updated version of benchmark.

1.4.0

Albumentations 1.4.0 Release Notes

• Request
• Highlights
• New transform
• Backwards Incompatible Changes
• Improvements
• Bug fixes

Request

1. If you enjoy using the library as an individual developer or during the day job as a part of the company, please consider becoming a sponsor for the library. Every dollar helps.
2. If you did not give our repo a ⭐, it is [only one mouse click].(https://github.com/albumentations-team/albumentations)
3. If you have feature requests, proposals, or encounter issues - submit your request to issues or, our new initiative, - Discord server for albumentations

Highlights

In this release, we mainly focused on the technical debt as its decrease allows faster iterations and bug fixes in the codebase. We added only one new transform, did not work on speeding up transforms, and other changes are minor.

1. We are removing the dependency on the imgaug library. The library was one of our inspirations when we created Albumentations, but maintainers of imgaug ceased its support which caused inconsistencies in library versions. It was done in 2021, say commit ba44eff by @Dipet .

But, somehow, we are cutting this dependency only in 2024.

2. Added typing in all of the codebase. When we started the library, Python 2 was still widely used; hence, none of the original codebases had types specified for function arguments and return types. Since the end of the support for Python 2, we added types to the new or updated code, but only now have we covered all the codebase.

New transform

• Added XYMasking transform: applies masking strips to an image, either horizontally (X axis) or vertically (Y axis), simulating occlusions. This transform is helpful for training models to recognize images with varied visibility conditions. It's particularly effective for spectrogram images, allowing spectral and frequency masking to improve model robustness.
  As other dropout transforms CoarseDropout, MaskDropout, GridDropout it supports images, masks and keypoints as targets. (004fabb by @ternaus )

Backward Incompatible Changes

The deprecated code, including 15 transforms, was removed.
Dependency on the imgaug library was removed.

(be6a217 by @ternaus )

Deleted Transforms

1. JpegCompression. Use ImageCompression instead.
2. RandomBrightness. Use RandomBrigtnessContrast instead.
3. RandomContrast. Use RandomBrigtnessContrast instead.
4. Cutout. Use CoarseDropout instead.
5. ToTensor. Use ToTensorV2 instead.
6. IAAAdditiveGaussianNoise. Use GaussNoise instead.
7. IAAAffine. Use Affine instead.
8. IAACropAndPad. Use CropAndPad instead.
9. IAAEmboss. Use Emboss instead.
10. IAAFliplr. Use HorizontalFlip instead.
11. IAAFlipud. Use VerticalFlip instead.
12. IAAPerspective. Use Perspective instead.
13. IAAPiecewiseAffine. Use PiecewiseAffine instead.
14. IAASharpen. Use Sharpen instead.
15. IAASuperpixels. Use Superpixels instead.

Other deprecated functionality

• Removed eps parameter in RandomGamma
• Removed lambda_transformsin serialization.from_dict function.

Minor changes and Bug Fixes

• Added details Contributor's guide
• Added support for matrix=None case for Piecewise affine transform (c70e664 @Dipet )
• Bugfix - Eliminated the possibility of the Perspective transform collapsing (a919a77 @alicangok )
• Fixes in docstrings (@domef, @aaronzs, @Dipet, @ternaus )
• Added checks for python 3.12