albumentations

Fast image augmentation library and an easy-to-use wrapper around other libraries. Documentation: https://albumentations.ai/docs/ Paper about the library: https://www.mdpi.com/2078-2489/11/2/125

9872
1270
Python

Albumentations

PyPI version
CI
PyPI Downloads
Conda Downloads
Stack Overflow
License: MIT
Gurubase
PyPI - Types

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.

πŸ† Gold Sponsors
Your company could be here
πŸ₯ˆ Silver Sponsors
Datature
πŸ₯‰ Bronze Sponsors
Roboflow

πŸ’ Become a Sponsor

Your sponsorship is a way to say β€œthank 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

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

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 βœ“ βœ“ βœ“
CoarseDropout3D βœ“ βœ“ βœ“
CubicSymmetry βœ“ βœ“ βœ“
Pad3D βœ“ βœ“ βœ“
PadIfNeeded3D βœ“ βœ“ βœ“
RandomCrop3D βœ“ βœ“ βœ“

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