Oven logo

Oven

albumentations2.0.6

Published

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.

pip install albumentations

Package Downloads

Weekly DownloadsMonthly Downloads

Authors

Project URLs

Requires Python

>=3.9

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.

🏆 Gold Sponsors
Your company could be here
🥈 Silver Sponsors
Datature
🥉 Bronze Sponsors
Roboflow

💝 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

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
TransformImageMaskBBoxesKeypointsVolumeMask3D
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
TransformVolumeMask3DKeypoints
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

  • 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.

Transformalbumentations
2.0.4		augly
1.0.0		imgaug
0.4.0		kornia
0.8.0		torchvision
0.20.1		Speedup
(Alb/fastest other)
Affine1445 ± 9-1328 ± 16248 ± 6188 ± 21.09x
AutoContrast1657 ± 13--541 ± 8344 ± 13.06x
Blur7657 ± 114386 ± 45381 ± 125265 ± 11-1.42x
Brightness11985 ± 4552108 ± 321076 ± 321127 ± 27854 ± 135.68x
CLAHE647 ± 4-555 ± 14165 ± 3-1.17x
CenterCrop128119293 ± 2164----N/A
ChannelDropout11534 ± 306--2283 ± 24-5.05x
ChannelShuffle6772 ± 109-1252 ± 261328 ± 444417 ± 2341.53x
CoarseDropout18962 ± 1346-1190 ± 22--15.93x
ColorJitter1020 ± 91418 ± 5-104 ± 487 ± 12.44x
Contrast12394 ± 3631379 ± 25717 ± 51109 ± 41602 ± 138.99x
CornerIllumination484 ± 7--452 ± 3-1.07x
Elastic374 ± 2-395 ± 141 ± 03 ± 00.95x
Equalize1236 ± 21-814 ± 11306 ± 1795 ± 31.52x
Erasing27451 ± 2794--1210 ± 273577 ± 497.67x
GaussianBlur2350 ± 118387 ± 41460 ± 23254 ± 5127 ± 41.61x
GaussianIllumination720 ± 7--436 ± 13-1.65x
GaussianNoise315 ± 4-263 ± 9125 ± 1-1.20x
Grayscale32284 ± 11306088 ± 1073100 ± 241201 ± 522600 ± 235.30x
HSV1197 ± 23----N/A
HorizontalFlip14460 ± 3688808 ± 10129599 ± 4951297 ± 132486 ± 1071.51x
Hue1944 ± 64--150 ± 1-12.98x
Invert27665 ± 3803-3682 ± 792881 ± 434244 ± 306.52x
JpegCompression1321 ± 331202 ± 19687 ± 26120 ± 1889 ± 71.10x
LinearIllumination479 ± 5--708 ± 6-0.68x
MedianBlur1229 ± 9-1152 ± 146 ± 0-1.07x
MotionBlur3521 ± 25-928 ± 37159 ± 1-3.79x
Normalize1819 ± 49--1251 ± 141018 ± 71.45x
OpticalDistortion661 ± 7--174 ± 0-3.80x
Pad48589 ± 2059---4889 ± 1839.94x
Perspective1206 ± 3-908 ± 8154 ± 3147 ± 51.33x
PlankianJitter3221 ± 63--2150 ± 52-1.50x
PlasmaBrightness168 ± 2--85 ± 1-1.98x
PlasmaContrast145 ± 3--84 ± 0-1.71x
PlasmaShadow183 ± 5--216 ± 5-0.85x
Posterize12979 ± 1121-3111 ± 95836 ± 304247 ± 263.06x
RGBShift3391 ± 104--896 ± 9-3.79x
Rain2043 ± 115--1493 ± 9-1.37x
RandomCrop128111859 ± 137445395 ± 93421408 ± 6222946 ± 4231450 ± 2492.46x
RandomGamma12444 ± 753-3504 ± 72230 ± 3-3.55x
RandomResizedCrop4347 ± 37--661 ± 16837 ± 375.19x
Resize3532 ± 671083 ± 212995 ± 70645 ± 13260 ± 91.18x
Rotate2912 ± 681739 ± 1052574 ± 10256 ± 2258 ± 41.13x
SaltAndPepper629 ± 6--480 ± 12-1.31x
Saturation1596 ± 24-495 ± 3155 ± 2-3.22x
Sharpen2346 ± 10-1101 ± 30201 ± 2220 ± 32.13x
Shear1299 ± 11-1244 ± 14261 ± 1-1.04x
Snow611 ± 9--143 ± 1-4.28x
Solarize11756 ± 481-3843 ± 80263 ± 61032 ± 143.06x
ThinPlateSpline82 ± 1--58 ± 0-1.41x
VerticalFlip32386 ± 93616830 ± 165319935 ± 17082872 ± 374696 ± 1611.62x

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}
}