Awesome

Albumentations

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

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
<a href="https://datature.io" target="_blank"><img src="https://albumentations.ai/assets/sponsors/datature-full.png" width="100" alt="Datature"/></a>

🥉 Bronze Sponsors
<a href="https://roboflow.com" target="_blank"><img src="https://albumentations.ai/assets/sponsors/roboflow.png" width="100" alt="Roboflow"/></a>

💝 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

Albumentations

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

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	✓	✓	✓	✓	✓	✓
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	✓	✓	✓	✓	✓	✓

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
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

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.

Transform	albumentations<br>1.4.20	augly<br>1.0.0	imgaug<br>0.4.0	kornia<br>0.7.3	torchvision<br>0.20.0
HorizontalFlip	8618 ± 1233	4807 ± 818	6042 ± 788	390 ± 106	914 ± 67
VerticalFlip	22847 ± 2031	9153 ± 1291	10931 ± 1844	1212 ± 402	3198 ± 200
Rotate	1146 ± 79	1119 ± 41	1136 ± 218	143 ± 11	181 ± 11
Affine	682 ± 192	-	774 ± 97	147 ± 9	130 ± 12
Equalize	892 ± 61	-	581 ± 54	152 ± 19	479 ± 12
RandomCrop80	47341 ± 20523	25272 ± 1822	11503 ± 441	1510 ± 230	32109 ± 1241
ShiftRGB	2349 ± 76	-	1582 ± 65	-	-
Resize	2316 ± 166	611 ± 78	1806 ± 63	232 ± 24	195 ± 4
RandomGamma	8675 ± 274	-	2318 ± 269	108 ± 13	-
Grayscale	3056 ± 47	2720 ± 932	1681 ± 156	289 ± 75	1838 ± 130
RandomPerspective	412 ± 38	-	554 ± 22	86 ± 11	96 ± 5
GaussianBlur	1728 ± 89	242 ± 4	1090 ± 65	176 ± 18	79 ± 3
MedianBlur	868 ± 60	-	813 ± 30	5 ± 0	-
MotionBlur	4047 ± 67	-	612 ± 18	73 ± 2	-
Posterize	9094 ± 301	-	2097 ± 68	430 ± 49	3196 ± 185
JpegCompression	918 ± 23	778 ± 5	459 ± 35	71 ± 3	625 ± 17
GaussianNoise	166 ± 12	67 ± 2	206 ± 11	75 ± 1	-
Elastic	201 ± 5	-	235 ± 20	1 ± 0	2 ± 0
Clahe	454 ± 22	-	335 ± 43	94 ± 9	-
CoarseDropout	13368 ± 744	-	671 ± 38	536 ± 87	-
Blur	5267 ± 543	246 ± 3	3807 ± 325	-	-
ColorJitter	628 ± 55	255 ± 13	-	55 ± 18	46 ± 2
Brightness	8956 ± 300	1163 ± 86	-	472 ± 101	429 ± 20
Contrast	8879 ± 1426	736 ± 79	-	425 ± 52	335 ± 35
RandomResizedCrop	2828 ± 186	-	-	287 ± 58	511 ± 10
Normalize	1196 ± 56	-	-	626 ± 40	519 ± 12
PlankianJitter	2204 ± 385	-	-	813 ± 211	-

Contributing

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

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}
}