Home>Programming related>Python
Download

Albumentations


Docs | Discord | Twitter | LinkedIn

Albumentations is a Python library for image augmentation. Image augmentation is used in deep learning and computer vision tasks to increase the quality of trained models. The purpose of image augmentation is to create new training samples from the existing data.

Here is an example of how you can apply some pixel-level augmentations from Albumentations to create new images from the original one:

Why Albumentations

  • Complete Computer Vision Support: Works with all major CV tasks including classification, segmentation (semantic & instance), object detection, and pose estimation.

  • Simple, Unified API: One consistent interface for all data types - RGB/grayscale/multispectral images, masks, bounding boxes, and keypoints.

  • Rich Augmentation Library: 70+ high-quality augmentations to enhance your training data.

  • Fast: Consistently benchmarked as the fastest augmentation library, with optimizations for production use.

  • Deep Learning Integration: Works with PyTorch, TensorFlow, and other frameworks. Part of the PyTorch ecosystem.

  • Created by Experts: Built by developers with deep experience in computer vision and machine learning competitions.

Community-Driven Project, Supported By

Albumentations thrives on developer contributions. We appreciate our sponsors who help sustain the project's infrastructure.

? Gold Sponsors
Your company could be here
? Silver Sponsors

? Bronze Sponsors

? Become a Sponsor

Your sponsorship is a way to say "thank you" to the maintainers and contributors who spend their free time building and maintaining Albumentations. Sponsors are featured on our website and README. View sponsorship tiers on GitHub Sponsors

Table of contents

  • Albumentations

    • System Information

    • Benchmark Parameters

    • Library Versions

    • Semantic segmentation on the Inria dataset

    • Medical imaging

    • Object detection and semantic segmentation on the Mapillary Vistas dataset

    • Keypoints augmentation

    • Pixel-level transforms

    • Spatial-level transforms

    • See also

    • I am new to image augmentation

    • I want to use Albumentations for the specific task such as classification or segmentation

    • I want to know how to use Albumentations with deep learning frameworks

    • I want to explore augmentations and see Albumentations in action

    • Current Maintainer

    • Emeritus Core Team Members

    • ? Become a Sponsor

    • Why Albumentations

    • Community-Driven Project, Supported By

    • Table of contents

    • Authors

    • Installation

    • Documentation

    • A simple example

    • Getting started

    • Who is using Albumentations

    • List of augmentations

    • A few more examples of augmentations

    • Benchmarking results

    • Performance Comparison

    • Contributing

    • Community

    • Citing

    Authors

    Current Maintainer

    Vladimir I. Iglovikov | Kaggle Grandmaster

    Emeritus Core Team Members

    Mikhail Druzhinin | Kaggle Expert

    Alex Parinov | Kaggle Master

    Alexander Buslaev | Kaggle Master

    Eugene Khvedchenya | Kaggle Grandmaster

    Installation

    Albumentations requires Python 3.9 or higher. To install the latest version from PyPI:

    pip install -U albumentations

    Other installation options are described in the documentation.

    Documentation

    The full documentation is available at https://albumentations.ai/docs/.

    A simple example

    import albumentations as Aimport cv2# Declare an augmentation pipelinetransform = A.Compose([A.RandomCrop(width=256, height=256),A.HorizontalFlip(p=0.5),A.RandomBrightnessContrast(p=0.2),
])# Read an image with OpenCV and convert it to the RGB colorspaceimage = cv2.imread("image.jpg")image = cv2.cvtColor(image, cv2.COLOR_BGR2RGB)# Augment an imagetransformed = transform(image=image)transformed_image = transformed["image"]

    Getting started

    I am new to image augmentation

    Please start with the introduction articles about why image augmentation is important and how it helps to build better models.

    I want to use Albumentations for the specific task such as classification or segmentation

    If you want to use Albumentations for a specific task such as classification, segmentation, or object detection, refer to the set of articles that has an in-depth description of this task. We also have a list of examples on applying Albumentations for different use cases.

    I want to know how to use Albumentations with deep learning frameworks

    We have examples of using Albumentations along with PyTorch and TensorFlow.

    I want to explore augmentations and see Albumentations in action

    Check the online demo of the library. With it, you can apply augmentations to different images and see the result. Also, we have a list of all available augmentations and their targets.

    Who is using Albumentations


    See also

    • A list of papers that cite Albumentations.

    • Open source projects that use Albumentations.

    List of augmentations

    Pixel-level transforms

    Pixel-level transforms will change just an input image and will leave any additional targets such as masks, bounding boxes, and keypoints unchanged. The list of pixel-level transforms:

    • AdditiveNoise

    • AdvancedBlur

    • AutoContrast

    • Blur

    • CLAHE

    • ChannelDropout

    • ChannelShuffle

    • ChromaticAberration

    • ColorJitter

    • Defocus

    • Downscale

    • Emboss

    • Equalize

    • FDA

    • FancyPCA

    • FromFloat

    • GaussNoise

    • GaussianBlur

    • GlassBlur

    • HistogramMatching

    • HueSaturationValue

    • ISONoise

    • Illumination

    • ImageCompression

    • InvertImg

    • MedianBlur

    • MotionBlur

    • MultiplicativeNoise

    • Normalize

    • PixelDistributionAdaptation

    • PlanckianJitter

    • PlasmaBrightnessContrast

    • PlasmaShadow

    • Posterize

    • RGBShift

    • RandomBrightnessContrast

    • RandomFog

    • RandomGamma

    • RandomGravel

    • RandomRain

    • RandomShadow

    • RandomSnow

    • RandomSunFlare

    • RandomToneCurve

    • RingingOvershoot

    • SaltAndPepper

    • Sharpen

    • ShotNoise

    • Solarize

    • Spatter

    • Superpixels

    • TemplateTransform

    • TextImage

    • ToFloat

    • ToGray

    • ToRGB

    • ToSepia

    • UnsharpMask

    • ZoomBlur

    Spatial-level transforms

    Spatial-level transforms will simultaneously change both an input image as well as additional targets such as masks, bounding boxes, and keypoints. The following table shows which additional targets are supported by each transform.

    TransformImageMaskBBoxesKeypoints
    Affine✓✓✓✓
    BBoxSafeRandomCrop✓✓✓✓
    CenterCrop✓✓✓✓
    CoarseDropout✓✓✓✓
    Crop✓✓✓✓
    CropAndPad✓✓✓✓
    CropNonEmptyMaskIfExists✓✓✓✓
    D4✓✓✓✓
    ElasticTransform✓✓✓✓
    Erasing✓✓✓✓
    FrequencyMasking✓✓✓✓
    GridDistortion✓✓✓✓
    GridDropout✓✓✓✓
    GridElasticDeform✓✓✓✓
    HorizontalFlip✓✓✓✓
    Lambda✓✓✓✓
    LongestMaxSize✓✓✓✓
    MaskDropout✓✓✓✓
    Morphological✓✓✓✓
    NoOp✓✓✓✓
    OpticalDistortion✓✓✓✓
    OverlayElements✓✓

    Pad✓✓✓✓
    PadIfNeeded✓✓✓✓
    Perspective✓✓✓✓
    PiecewiseAffine✓✓✓✓
    PixelDropout✓✓✓✓
    RandomCrop✓✓✓✓
    RandomCropFromBorders✓✓✓✓
    RandomCropNearBBox✓✓✓✓
    RandomGridShuffle✓✓✓✓
    RandomResizedCrop✓✓✓✓
    RandomRotate90✓✓✓✓
    RandomScale✓✓✓✓
    RandomSizedBBoxSafeCrop✓✓✓✓
    RandomSizedCrop✓✓✓✓
    Resize✓✓✓✓
    Rotate✓✓✓✓
    SafeRotate✓✓✓✓
    ShiftScaleRotate✓✓✓✓
    SmallestMaxSize✓✓✓✓
    ThinPlateSpline✓✓✓✓
    TimeMasking✓✓✓✓
    TimeReverse✓✓✓✓
    Transpose✓✓✓✓
    VerticalFlip✓✓✓✓
    XYMasking✓✓✓✓

    A few more examples of augmentations

    Semantic segmentation on the Inria dataset

    Medical imaging

    Object detection and semantic segmentation on the Mapillary Vistas dataset

    Keypoints augmentation

    Benchmarking results

    System Information

    • Platform: macOS-15.0.1-arm64-arm-64bit

    • Processor: arm

    • CPU Count: 10

    • Python Version: 3.12.7

    Benchmark Parameters

    • Number of images: 1000

    • Runs per transform: 10

    • Max warmup iterations: 1000

    Library Versions

    • albumentations: 1.4.20

    • augly: 1.0.0

    • imgaug: 0.4.0

    • kornia: 0.7.3

    • torchvision: 0.20.0

    Performance Comparison

    Number - is the number of uint8 RGB images processed per second on a single CPU core. Higher is better.

    Transformalbumentations
    1.4.20    		augly
    1.0.0    		imgaug
    0.4.0    		kornia
    0.7.3    		torchvision
    0.20.0
    HorizontalFlip8618 ± 12334807 ± 8186042 ± 788390 ± 106914 ± 67
    VerticalFlip22847 ± 20319153 ± 129110931 ± 18441212 ± 4023198 ± 200
    Rotate1146 ± 791119 ± 411136 ± 218143 ± 11181 ± 11
    Affine682 ± 192-774 ± 97147 ± 9130 ± 12
    Equalize892 ± 61-581 ± 54152 ± 19479 ± 12
    RandomCrop8047341 ± 2052325272 ± 182211503 ± 4411510 ± 23032109 ± 1241
    ShiftRGB2349 ± 76-1582 ± 65--
    Resize2316 ± 166611 ± 781806 ± 63232 ± 24195 ± 4
    RandomGamma8675 ± 274-2318 ± 269108 ± 13-
    Grayscale3056 ± 472720 ± 9321681 ± 156289 ± 751838 ± 130
    RandomPerspective412 ± 38-554 ± 2286 ± 1196 ± 5
    GaussianBlur1728 ± 89242 ± 41090 ± 65176 ± 1879 ± 3
    MedianBlur868 ± 60-813 ± 305 ± 0-
    MotionBlur4047 ± 67-612 ± 1873 ± 2-
    Posterize9094 ± 301-2097 ± 68430 ± 493196 ± 185
    JpegCompression918 ± 23778 ± 5459 ± 3571 ± 3625 ± 17
    GaussianNoise166 ± 1267 ± 2206 ± 1175 ± 1-
    Elastic201 ± 5-235 ± 201 ± 02 ± 0
    Clahe454 ± 22-335 ± 4394 ± 9-
    CoarseDropout13368 ± 744-671 ± 38536 ± 87-
    Blur5267 ± 543246 ± 33807 ± 325--
    ColorJitter628 ± 55255 ± 13-55 ± 1846 ± 2
    Brightness8956 ± 3001163 ± 86-472 ± 101429 ± 20
    Contrast8879 ± 1426736 ± 79-425 ± 52335 ± 35
    RandomResizedCrop2828 ± 186--287 ± 58511 ± 10
    Normalize1196 ± 56--626 ± 40519 ± 12
    PlankianJitter2204 ± 385--813 ± 211-

    Contributing

    To create a pull request to the repository, follow the documentation at CONTRIBUTING.md

    Community

    • LinkedIn

    • Twitter

    • Discord

    Citing

    If you find this library useful for your research, please consider citing Albumentations: Fast and Flexible Image Augmentations:

    @Article{info11020125,AUTHOR = {Buslaev, Alexander and Iglovikov, Vladimir I. and Khvedchenya, Eugene and Parinov, Alex and Druzhinin, Mikhail and Kalinin, Alexandr A.},TITLE = {Albumentations: Fast and Flexible Image Augmentations},JOURNAL = {Information},VOLUME = {11},YEAR = {2020},NUMBER = {2},ARTICLE-NUMBER = {125},URL = {https://www.mdpi.com/2078-2489/11/2/125},ISSN = {2078-2489},DOI = {10.3390/info11020125}}
    Expand
    Additional Information
    Related Applications
    Recommended for You
    Related Information All