Skip to main content

Fast, flexible, and advanced augmentation library for deep learning, computer vision, and medical imaging. Albumentations offers a wide range of transformations for both 2D (images, masks, bboxes, keypoints) and 3D (volumes, volumetric masks, keypoints) data, with optimized performance and seamless integration into ML workflows.

Project description

Albumentations

PyPI version CI PyPI Downloads Conda Downloads

๐Ÿ“ฃ Stay updated! Subscribe to our newsletter for the latest releases, tutorials, and tips directly from the Albumentations team.

License: MIT Gurubase

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: parrot

Why Albumentations

Community-Driven Project, Supported By

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

๐ŸŸ  Exclusive Partner
Your company could be here
๐ŸŸก Integration Partner
Your company could be here
๐ŸŸข Community Sponsor
Datature

๐Ÿ’ 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 our support page

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

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 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"]

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

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 โœ“ โœ“ โœ“ โœ“ โœ“ โœ“
AtLeastOneBBoxRandomCrop โœ“ โœ“ โœ“ โœ“ โœ“ โœ“
BBoxSafeRandomCrop โœ“ โœ“ โœ“ โœ“ โœ“ โœ“
CenterCrop โœ“ โœ“ โœ“ โœ“ โœ“ โœ“
CoarseDropout โœ“ โœ“ โœ“ โœ“ โœ“ โœ“
ConstrainedCoarseDropout โœ“ โœ“ โœ“ โœ“ โœ“ โœ“
Crop โœ“ โœ“ โœ“ โœ“ โœ“ โœ“
CropAndPad โœ“ โœ“ โœ“ โœ“ โœ“ โœ“
CropNonEmptyMaskIfExists โœ“ โœ“ โœ“ โœ“ โœ“ โœ“
D4 โœ“ โœ“ โœ“ โœ“ โœ“ โœ“
ElasticTransform โœ“ โœ“ โœ“ โœ“ โœ“ โœ“
Erasing โœ“ โœ“ โœ“ โœ“ โœ“ โœ“
FrequencyMasking โœ“ โœ“ โœ“ โœ“ โœ“ โœ“
GridDistortion โœ“ โœ“ โœ“ โœ“ โœ“ โœ“
GridDropout โœ“ โœ“ โœ“ โœ“ โœ“ โœ“
GridElasticDeform โœ“ โœ“ โœ“ โœ“ โœ“ โœ“
HorizontalFlip โœ“ โœ“ โœ“ โœ“ โœ“ โœ“
Lambda โœ“ โœ“ โœ“ โœ“ โœ“ โœ“
LongestMaxSize โœ“ โœ“ โœ“ โœ“ โœ“ โœ“
MaskDropout โœ“ โœ“ โœ“ โœ“ โœ“ โœ“
Morphological โœ“ โœ“ โœ“ โœ“ โœ“ โœ“
Mosaic โœ“ โœ“ โœ“ โœ“
NoOp โœ“ โœ“ โœ“ โœ“ โœ“ โœ“
OpticalDistortion โœ“ โœ“ โœ“ โœ“ โœ“ โœ“
OverlayElements โœ“ โœ“
Pad โœ“ โœ“ โœ“ โœ“ โœ“ โœ“
PadIfNeeded โœ“ โœ“ โœ“ โœ“ โœ“ โœ“
Perspective โœ“ โœ“ โœ“ โœ“ โœ“ โœ“
PiecewiseAffine โœ“ โœ“ โœ“ โœ“ โœ“ โœ“
PixelDropout โœ“ โœ“ โœ“ โœ“ โœ“ โœ“
RandomCrop โœ“ โœ“ โœ“ โœ“ โœ“ โœ“
RandomCropFromBorders โœ“ โœ“ โœ“ โœ“ โœ“ โœ“
RandomCropNearBBox โœ“ โœ“ โœ“ โœ“ โœ“ โœ“
RandomGridShuffle โœ“ โœ“ โœ“ โœ“ โœ“ โœ“
RandomResizedCrop โœ“ โœ“ โœ“ โœ“ โœ“ โœ“
RandomRotate90 โœ“ โœ“ โœ“ โœ“ โœ“ โœ“
RandomScale โœ“ โœ“ โœ“ โœ“ โœ“ โœ“
RandomSizedBBoxSafeCrop โœ“ โœ“ โœ“ โœ“ โœ“ โœ“
RandomSizedCrop โœ“ โœ“ โœ“ โœ“ โœ“ โœ“
Resize โœ“ โœ“ โœ“ โœ“ โœ“ โœ“
Rotate โœ“ โœ“ โœ“ โœ“ โœ“ โœ“
SafeRotate โœ“ โœ“ โœ“ โœ“ โœ“ โœ“
ShiftScaleRotate โœ“ โœ“ โœ“ โœ“ โœ“ โœ“
SmallestMaxSize โœ“ โœ“ โœ“ โœ“ โœ“ โœ“
SquareSymmetry โœ“ โœ“ โœ“ โœ“ โœ“ โœ“
ThinPlateSpline โœ“ โœ“ โœ“ โœ“ โœ“ โœ“
TimeMasking โœ“ โœ“ โœ“ โœ“ โœ“ โœ“
TimeReverse โœ“ โœ“ โœ“ โœ“ โœ“ โœ“
Transpose โœ“ โœ“ โœ“ โœ“ โœ“ โœ“
VerticalFlip โœ“ โœ“ โœ“ โœ“ โœ“ โœ“
XYMasking โœ“ โœ“ โœ“ โœ“ โœ“ โœ“

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 โœ“ โœ“ โœ“
CoarseDropout3D โœ“ โœ“ โœ“
CubicSymmetry โœ“ โœ“ โœ“
Pad3D โœ“ โœ“ โœ“
PadIfNeeded3D โœ“ โœ“ โœ“
RandomCrop3D โœ“ โœ“ โœ“

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

  • albumentations: 2.0.4
  • 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 Albumentations is compared to the fastest other library for each transform.

Transform albumentations
2.0.4
augly
1.0.0
imgaug
0.4.0
kornia
0.8.0
torchvision
0.20.1
Speedup
(Alb/fastest other)
Affine 1445 ยฑ 9 - 1328 ยฑ 16 248 ยฑ 6 188 ยฑ 2 1.09x
AutoContrast 1657 ยฑ 13 - - 541 ยฑ 8 344 ยฑ 1 3.06x
Blur 7657 ยฑ 114 386 ยฑ 4 5381 ยฑ 125 265 ยฑ 11 - 1.42x
Brightness 11985 ยฑ 455 2108 ยฑ 32 1076 ยฑ 32 1127 ยฑ 27 854 ยฑ 13 5.68x
CLAHE 647 ยฑ 4 - 555 ยฑ 14 165 ยฑ 3 - 1.17x
CenterCrop128 119293 ยฑ 2164 - - - - N/A
ChannelDropout 11534 ยฑ 306 - - 2283 ยฑ 24 - 5.05x
ChannelShuffle 6772 ยฑ 109 - 1252 ยฑ 26 1328 ยฑ 44 4417 ยฑ 234 1.53x
CoarseDropout 18962 ยฑ 1346 - 1190 ยฑ 22 - - 15.93x
ColorJitter 1020 ยฑ 91 418 ยฑ 5 - 104 ยฑ 4 87 ยฑ 1 2.44x
Contrast 12394 ยฑ 363 1379 ยฑ 25 717 ยฑ 5 1109 ยฑ 41 602 ยฑ 13 8.99x
CornerIllumination 484 ยฑ 7 - - 452 ยฑ 3 - 1.07x
Elastic 374 ยฑ 2 - 395 ยฑ 14 1 ยฑ 0 3 ยฑ 0 0.95x
Equalize 1236 ยฑ 21 - 814 ยฑ 11 306 ยฑ 1 795 ยฑ 3 1.52x
Erasing 27451 ยฑ 2794 - - 1210 ยฑ 27 3577 ยฑ 49 7.67x
GaussianBlur 2350 ยฑ 118 387 ยฑ 4 1460 ยฑ 23 254 ยฑ 5 127 ยฑ 4 1.61x
GaussianIllumination 720 ยฑ 7 - - 436 ยฑ 13 - 1.65x
GaussianNoise 315 ยฑ 4 - 263 ยฑ 9 125 ยฑ 1 - 1.20x
Grayscale 32284 ยฑ 1130 6088 ยฑ 107 3100 ยฑ 24 1201 ยฑ 52 2600 ยฑ 23 5.30x
HSV 1197 ยฑ 23 - - - - N/A
HorizontalFlip 14460 ยฑ 368 8808 ยฑ 1012 9599 ยฑ 495 1297 ยฑ 13 2486 ยฑ 107 1.51x
Hue 1944 ยฑ 64 - - 150 ยฑ 1 - 12.98x
Invert 27665 ยฑ 3803 - 3682 ยฑ 79 2881 ยฑ 43 4244 ยฑ 30 6.52x
JpegCompression 1321 ยฑ 33 1202 ยฑ 19 687 ยฑ 26 120 ยฑ 1 889 ยฑ 7 1.10x
LinearIllumination 479 ยฑ 5 - - 708 ยฑ 6 - 0.68x
MedianBlur 1229 ยฑ 9 - 1152 ยฑ 14 6 ยฑ 0 - 1.07x
MotionBlur 3521 ยฑ 25 - 928 ยฑ 37 159 ยฑ 1 - 3.79x
Normalize 1819 ยฑ 49 - - 1251 ยฑ 14 1018 ยฑ 7 1.45x
OpticalDistortion 661 ยฑ 7 - - 174 ยฑ 0 - 3.80x
Pad 48589 ยฑ 2059 - - - 4889 ยฑ 183 9.94x
Perspective 1206 ยฑ 3 - 908 ยฑ 8 154 ยฑ 3 147 ยฑ 5 1.33x
PlankianJitter 3221 ยฑ 63 - - 2150 ยฑ 52 - 1.50x
PlasmaBrightness 168 ยฑ 2 - - 85 ยฑ 1 - 1.98x
PlasmaContrast 145 ยฑ 3 - - 84 ยฑ 0 - 1.71x
PlasmaShadow 183 ยฑ 5 - - 216 ยฑ 5 - 0.85x
Posterize 12979 ยฑ 1121 - 3111 ยฑ 95 836 ยฑ 30 4247 ยฑ 26 3.06x
RGBShift 3391 ยฑ 104 - - 896 ยฑ 9 - 3.79x
Rain 2043 ยฑ 115 - - 1493 ยฑ 9 - 1.37x
RandomCrop128 111859 ยฑ 1374 45395 ยฑ 934 21408 ยฑ 622 2946 ยฑ 42 31450 ยฑ 249 2.46x
RandomGamma 12444 ยฑ 753 - 3504 ยฑ 72 230 ยฑ 3 - 3.55x
RandomResizedCrop 4347 ยฑ 37 - - 661 ยฑ 16 837 ยฑ 37 5.19x
Resize 3532 ยฑ 67 1083 ยฑ 21 2995 ยฑ 70 645 ยฑ 13 260 ยฑ 9 1.18x
Rotate 2912 ยฑ 68 1739 ยฑ 105 2574 ยฑ 10 256 ยฑ 2 258 ยฑ 4 1.13x
SaltAndPepper 629 ยฑ 6 - - 480 ยฑ 12 - 1.31x
Saturation 1596 ยฑ 24 - 495 ยฑ 3 155 ยฑ 2 - 3.22x
Sharpen 2346 ยฑ 10 - 1101 ยฑ 30 201 ยฑ 2 220 ยฑ 3 2.13x
Shear 1299 ยฑ 11 - 1244 ยฑ 14 261 ยฑ 1 - 1.04x
Snow 611 ยฑ 9 - - 143 ยฑ 1 - 4.28x
Solarize 11756 ยฑ 481 - 3843 ยฑ 80 263 ยฑ 6 1032 ยฑ 14 3.06x
ThinPlateSpline 82 ยฑ 1 - - 58 ยฑ 0 - 1.41x
VerticalFlip 32386 ยฑ 936 16830 ยฑ 1653 19935 ยฑ 1708 2872 ยฑ 37 4696 ยฑ 161 1.62x

Contributing

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

https://github.com/albuemntations-team/albumentation/graphs/contributors

Community

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}
}

๐Ÿ“ซ Stay Connected

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

Project details


Release history Release notifications | RSS feed

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

albumentations-2.0.8.tar.gz (354.5 kB view details)

Uploaded Source

Built Distribution

albumentations-2.0.8-py3-none-any.whl (369.4 kB view details)

Uploaded Python 3

File details

Details for the file albumentations-2.0.8.tar.gz.

File metadata

  • Download URL: albumentations-2.0.8.tar.gz
  • Upload date:
  • Size: 354.5 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.1.0 CPython/3.9.22

File hashes

Hashes for albumentations-2.0.8.tar.gz
Algorithm Hash digest
SHA256 4da95e658e490de3c34af8fcdffed09e36aa8a4edd06ca9f9e7e3ea0b0b16856
MD5 6d7f25f1868850fc401c746a222fece8
BLAKE2b-256 f4f485eb56c3217b53bcfc2d12e840a0b18ca60902086321cafa5a730f9c0470

See more details on using hashes here.

File details

Details for the file albumentations-2.0.8-py3-none-any.whl.

File metadata

  • Download URL: albumentations-2.0.8-py3-none-any.whl
  • Upload date:
  • Size: 369.4 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.1.0 CPython/3.9.22

File hashes

Hashes for albumentations-2.0.8-py3-none-any.whl
Algorithm Hash digest
SHA256 c4c4259aaf04a7386ad85c7fdcb73c6c7146ca3057446b745cc035805acb1017
MD5 950bd8cc13241b04c659a7e4602a1960
BLAKE2b-256 8e64013409c451a44b61310fb757af4527f3de57fc98a00f40448de28b864290

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page