Skip to content

albumentations-team/AlbumentationsX

BranchesTags

Repository files navigation

AlbumentationsX

PyPI version CI PyPI Downloads

📣 Stay updated! Subscribe to our newsletter for the latest releases, tutorials, and tips.

License: AGPL v3

Docs | Discord | Twitter | LinkedIn

AlbumentationsX is a Python library for image augmentation. It provides high-performance, robust implementations and cutting-edge features for computer vision tasks. Image augmentation is used in deep learning and computer vision to increase the quality of trained models. The purpose of image augmentation is to create new training samples from the existing data.

GitAds Sponsored

Sponsored by GitAds

📢 Important: AlbumentationsX Licensing

AlbumentationsX offers dual licensing:

  • AGPL-3.0 License: Free for open-source projects
  • Commercial License: For proprietary/commercial use (contact for pricing)

Quick Start

# Install AlbumentationsX
pip install albumentationsx
import albumentations as A

# Create your augmentation pipeline
transform = A.Compose([
    A.RandomCrop(width=256, height=256),
    A.HorizontalFlip(p=0.5),
    A.RandomBrightnessContrast(p=0.2),
])

For commercial licensing inquiries, please visit our pricing page.

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

Why AlbumentationsX

Table of contents

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

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

pip install -U albumentationsx

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 A
import cv2

# Declare an augmentation pipeline
transform = 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 colorspace
image = cv2.imread("image.jpg")
image = cv2.cvtColor(image, cv2.COLOR_BGR2RGB)

# Augment an image
transformed = transform(image=image)
transformed_image = transformed["image"]

AlbumentationsX collects anonymous usage statistics to improve the library. This can be disabled with ALBUMENTATIONS_OFFLINE=1 or ALBUMENTATIONS_NO_TELEMETRY=1.

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. For volumetric data (volumes and 3D masks), these transforms are applied independently to each slice along the Z-axis (depth dimension), maintaining consistency across the volume. The list of pixel-level transforms:

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. For volumetric data (volumes and 3D masks), these transforms are applied independently to each slice along the Z-axis (depth dimension), maintaining consistency across the volume. The following table shows which additional targets are supported by each transform:

  • Volume: 3D array of shape (D, H, W) or (D, H, W, C) where D is depth, H is height, W is width, and C is number of channels (optional)
  • Mask3D: Binary or multi-class 3D mask of shape (D, H, W) where each slice represents segmentation for the corresponding volume slice
Transform Image Mask BBoxes Keypoints Volume Mask3D
Affine ✓ ✓ ✓ ✓ ✓ ✓
AtLeastOneBBoxRandomCrop ✓ ✓ ✓ ✓ ✓ ✓
BBoxSafeRandomCrop ✓ ✓ ✓ ✓ ✓ ✓
CenterCrop ✓ ✓ ✓ ✓ ✓ ✓
CoarseDropout ✓ ✓ ✓ ✓ ✓ ✓
ConstrainedCoarseDropout ✓ ✓ ✓ ✓ ✓ ✓
Crop ✓ ✓ ✓ ✓ ✓ ✓
CropAndPad ✓ ✓ ✓ ✓ ✓ ✓
CropNonEmptyMaskIfExists ✓ ✓ ✓ ✓ ✓ ✓
D4 ✓ ✓ ✓ ✓ ✓ ✓
ElasticTransform ✓ ✓ ✓ ✓ ✓ ✓
Erasing ✓ ✓ ✓ ✓ ✓ ✓
FrequencyMasking ✓ ✓ ✓ ✓ ✓ ✓
GridDistortion ✓ ✓ ✓ ✓ ✓ ✓
GridDropout ✓ ✓ ✓ ✓ ✓ ✓
GridElasticDeform ✓ ✓ ✓ ✓ ✓ ✓
HorizontalFlip ✓ ✓ ✓ ✓ ✓ ✓
Lambda ✓ ✓ ✓ ✓ ✓ ✓
LongestMaxSize ✓ ✓ ✓ ✓ ✓ ✓
MaskDropout ✓ ✓ ✓ ✓ ✓ ✓
Morphological ✓ ✓ ✓ ✓ ✓ ✓
Mosaic ✓ ✓ ✓ ✓
NoOp ✓ ✓ ✓ ✓ ✓ ✓
OpticalDistortion ✓ ✓ ✓ ✓ ✓ ✓
OverlayElements ✓ ✓
Pad ✓ ✓ ✓ ✓ ✓ ✓
PadIfNeeded ✓ ✓ ✓ ✓ ✓ ✓
Perspective ✓ ✓ ✓ ✓ ✓ ✓
PiecewiseAffine ✓ ✓ ✓ ✓ ✓ ✓
PixelDropout ✓ ✓ ✓ ✓ ✓ ✓
RandomCrop ✓ ✓ ✓ ✓ ✓ ✓
RandomCropFromBorders ✓ ✓ ✓ ✓ ✓ ✓
RandomCropNearBBox ✓ ✓ ✓ ✓ ✓ ✓
RandomGridShuffle ✓ ✓ ✓ ✓ ✓ ✓
RandomResizedCrop ✓ ✓ ✓ ✓ ✓ ✓
RandomRotate90 ✓ ✓ ✓ ✓ ✓ ✓
RandomScale ✓ ✓ ✓ ✓ ✓ ✓
RandomSizedBBoxSafeCrop ✓ ✓ ✓ ✓ ✓ ✓
RandomSizedCrop ✓ ✓ ✓ ✓ ✓ ✓
Resize ✓ ✓ ✓ ✓ ✓ ✓
Rotate ✓ ✓ ✓ ✓ ✓ ✓
SafeRotate ✓ ✓ ✓ ✓ ✓ ✓
ShiftScaleRotate ✓ ✓ ✓ ✓ ✓ ✓
SmallestMaxSize ✓ ✓ ✓ ✓ ✓ ✓
SquareSymmetry ✓ ✓ ✓ ✓ ✓ ✓
ThinPlateSpline ✓ ✓ ✓ ✓ ✓ ✓
TimeMasking ✓ ✓ ✓ ✓ ✓ ✓
TimeReverse ✓ ✓ ✓ ✓ ✓ ✓
Transpose ✓ ✓ ✓ ✓ ✓ ✓
VerticalFlip ✓ ✓ ✓ ✓ ✓ ✓
XYMasking ✓ ✓ ✓ ✓ ✓ ✓

3D transforms

3D transforms operate on volumetric data and can modify both the input volume and associated 3D mask.

Where:

  • Volume: 3D array of shape (D, H, W) or (D, H, W, C) where D is depth, H is height, W is width, and C is number of channels (optional)
  • Mask3D: Binary or multi-class 3D mask of shape (D, H, W) where each slice represents segmentation for the corresponding volume slice
Transform Volume Mask3D Keypoints
CenterCrop3D ✓ ✓ ✓
CoarseDropout3D ✓ ✓ ✓
CubicSymmetry ✓ ✓ ✓
Pad3D ✓ ✓ ✓
PadIfNeeded3D ✓ ✓ ✓
RandomCrop3D ✓ ✓ ✓

A few more examples of augmentations

Semantic segmentation on the Inria dataset

inria

Medical imaging

medical

Object detection and semantic segmentation on the Mapillary Vistas dataset

vistas

Keypoints augmentation

Benchmark Results

Image Benchmark Results

System Information

  • Platform: macOS-15.1-arm64-arm-64bit
  • Processor: arm
  • CPU Count: 16
  • Python Version: 3.12.8

Benchmark Parameters

  • Number of images: 2000
  • Runs per transform: 5
  • Max warmup iterations: 1000

Library Versions

  • albumentationsx: 2.0.8
  • augly: 1.0.0
  • imgaug: 0.4.0
  • kornia: 0.8.0
  • torchvision: 0.20.1

Performance Comparison

Number shows how many uint8 images per second can be processed on one CPU thread. Larger is better. The Speedup column shows how many times faster AlbumentationsX is compared to the fastest other library for each transform.

Transform albumentationsx
2.0.8		 augly
1.0.0		 imgaug
0.4.0		 kornia
0.8.0		 torchvision
0.20.1		 Speedup
(AlbX/fastest other)
Affine 1445 ± 9 - 1328 ± 16 248 ± 6 188 ± 2 1.09x
AutoContrast 1657 ± 13 - - 541 ± 8 344 ± 1 3.06x
Blur 7657 ± 114 386 ± 4 5381 ± 125 265 ± 11 - 1.42x
Brightness 11985 ± 455 2108 ± 32 1076 ± 32 1127 ± 27 854 ± 13 5.68x
CLAHE 647 ± 4 - 555 ± 14 165 ± 3 - 1.17x
CenterCrop128 119293 ± 2164 - - - - N/A
ChannelDropout 11534 ± 306 - - 2283 ± 24 - 5.05x
ChannelShuffle 6772 ± 109 - 1252 ± 26 1328 ± 44 4417 ± 234 1.53x
CoarseDropout 18962 ± 1346 - 1190 ± 22 - - 15.93x
ColorJitter 1020 ± 91 418 ± 5 - 104 ± 4 87 ± 1 2.44x
Contrast 12394 ± 363 1379 ± 25 717 ± 5 1109 ± 41 602 ± 13 8.99x
CornerIllumination 484 ± 7 - - 452 ± 3 - 1.07x
Elastic 374 ± 2 - 395 ± 14 1 ± 0 3 ± 0 0.95x
Equalize 1236 ± 21 - 814 ± 11 306 ± 1 795 ± 3 1.52x
Erasing 27451 ± 2794 - - 1210 ± 27 3577 ± 49 7.67x
GaussianBlur 2350 ± 118 387 ± 4 1460 ± 23 254 ± 5 127 ± 4 1.61x
GaussianIllumination 720 ± 7 - - 436 ± 13 - 1.65x
GaussianNoise 315 ± 4 - 263 ± 9 125 ± 1 - 1.20x
Grayscale 32284 ± 1130 6088 ± 107 3100 ± 24 1201 ± 52 2600 ± 23 5.30x
HSV 1197 ± 23 - - - - N/A
HorizontalFlip 14460 ± 368 8808 ± 1012 9599 ± 495 1297 ± 13 2486 ± 107 1.51x
Hue 1944 ± 64 - - 150 ± 1 - 12.98x
Invert 27665 ± 3803 - 3682 ± 79 2881 ± 43 4244 ± 30 6.52x
JpegCompression 1321 ± 33 1202 ± 19 687 ± 26 120 ± 1 889 ± 7 1.10x
LinearIllumination 479 ± 5 - - 708 ± 6 - 0.68x
MedianBlur 1229 ± 9 - 1152 ± 14 6 ± 0 - 1.07x
MotionBlur 3521 ± 25 - 928 ± 37 159 ± 1 - 3.79x
Normalize 1819 ± 49 - - 1251 ± 14 1018 ± 7 1.45x
OpticalDistortion 661 ± 7 - - 174 ± 0 - 3.80x
Pad 48589 ± 2059 - - - 4889 ± 183 9.94x
Perspective 1206 ± 3 - 908 ± 8 154 ± 3 147 ± 5 1.33x
PlankianJitter 3221 ± 63 - - 2150 ± 52 - 1.50x
PlasmaBrightness 168 ± 2 - - 85 ± 1 - 1.98x
PlasmaContrast 145 ± 3 - - 84 ± 0 - 1.71x
PlasmaShadow 183 ± 5 - - 216 ± 5 - 0.85x
Posterize 12979 ± 1121 - 3111 ± 95 836 ± 30 4247 ± 26 3.06x
RGBShift 3391 ± 104 - - 896 ± 9 - 3.79x
Rain 2043 ± 115 - - 1493 ± 9 - 1.37x
RandomCrop128 111859 ± 1374 45395 ± 934 21408 ± 622 2946 ± 42 31450 ± 249 2.46x
RandomGamma 12444 ± 753 - 3504 ± 72 230 ± 3 - 3.55x
RandomResizedCrop 4347 ± 37 - - 661 ± 16 837 ± 37 5.19x
Resize 3532 ± 67 1083 ± 21 2995 ± 70 645 ± 13 260 ± 9 1.18x
Rotate 2912 ± 68 1739 ± 105 2574 ± 10 256 ± 2 258 ± 4 1.13x
SaltAndPepper 629 ± 6 - - 480 ± 12 - 1.31x
Saturation 1596 ± 24 - 495 ± 3 155 ± 2 - 3.22x
Sharpen 2346 ± 10 - 1101 ± 30 201 ± 2 220 ± 3 2.13x
Shear 1299 ± 11 - 1244 ± 14 261 ± 1 - 1.04x
Snow 611 ± 9 - - 143 ± 1 - 4.28x
Solarize 11756 ± 481 - 3843 ± 80 263 ± 6 1032 ± 14 3.06x
ThinPlateSpline 82 ± 1 - - 58 ± 0 - 1.41x
VerticalFlip 32386 ± 936 16830 ± 1653 19935 ± 1708 2872 ± 37 4696 ± 161 1.62x

🤝 Contribute

We thrive on community collaboration! AlbumentationsX wouldn't be the powerful augmentation library it is without contributions from developers like you. Please see our Contributing Guide to get started. A huge Thank You 🙏 to everyone who contributes!

AlbumentationsX open-source contributors

We look forward to your contributions to help make the AlbumentationsX ecosystem even better!

📜 License

AlbumentationsX offers two licensing options to suit different needs:

  • AGPL-3.0 License: This OSI-approved open-source license is perfect for students, researchers, and enthusiasts. It encourages open collaboration and knowledge sharing. See the LICENSE file for full details.
  • AlbumentationsX Commercial License: Designed for commercial use, this license allows for the seamless integration of AlbumentationsX into commercial products and services, bypassing the open-source requirements of AGPL-3.0. If your use case involves commercial deployment, please visit our pricing page.

📞 Contact

For bug reports and feature requests related to AlbumentationsX, please visit GitHub Issues. For questions, discussions, and community support, join our active communities on Discord, Twitter, and LinkedIn. We're here to help with all things AlbumentationsX!

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}
}

📫 Stay Connected

Never miss updates, tutorials, and tips from the AlbumentationsX team! Subscribe to our newsletter.

About

Next-generation Albumentations: dual-licensed for open-source and commercial use

albumentations.ai/

Topics

python deep-learning image-processing image-classification deeplearning object-detection data-augmentation image-augmentation maching-learning instance-segmentation image-segmentations

Resources

Readme

License

View license

Code of conduct

Code of conduct

Contributing

Contributing
Activity
Custom properties

Stars

92 stars

Watchers

1 watching

Forks

11 forks
Report repository

Releases 2

🛠 Albumentations 2.0.10 Release Notes Latest
Aug 22, 2025
+ 1 release

Sponsor this project

  •  
Learn more about GitHub Sponsors

Contributors 3

Languages