Skip to content
master
Switch branches/tags
Code

Albumentations

PyPI version CI

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 augmentations from Albumentations to create new images from the original one: parrot

Why Albumentations

  • Albumentations supports all common computer vision tasks such as classification, semantic segmentation, instance segmentation, object detection, and pose estimation.
  • The library provides a simple unified API to work with all data types: images (RBG-images, grayscale images, multispectral images), segmentation masks, bounding boxes, and keypoints.
  • The library contains more than 70 different augmentations to generate new training samples from the existing data.
  • Albumentations is fast. We benchmark each new release to ensure that augmentations provide maximum speed.
  • It works with popular deep learning frameworks such as PyTorch and TensorFlow. By the way, Albumentations is a part of the PyTorch ecosystem.
  • Written by experts. The authors have experience both working on production computer vision systems and participating in competitive machine learning. Many core team members are Kaggle Masters and Grandmasters.
  • The library is widely used in industry, deep learning research, machine learning competitions, and open source projects.

Table of contents

Authors

Alexander Buslaev — Computer Vision Engineer at Mapbox | Kaggle Master

Alex Parinov — Tech Lead at SberDevices | Kaggle Master

Vladimir I. Iglovikov — Staff Engineer at Lyft Level5 | Kaggle Grandmaster

Evegene Khvedchenya — Computer Vision Research Engineer at Piñata Farms | Kaggle Grandmaster

Mikhail Druzhinin — Computer Vision Engineer at ID R&D | Kaggle Expert

Installation

Albumentations requires Python 3.6 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. 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. The following table shows which additional targets are supported by each transform.

Transform Image Masks BBoxes Keypoints
Affine
CenterCrop
CoarseDropout
Crop
CropAndPad
CropNonEmptyMaskIfExists
ElasticTransform
Flip
GridDistortion
GridDropout
HorizontalFlip
Lambda
LongestMaxSize
MaskDropout
NoOp
OpticalDistortion
PadIfNeeded
Perspective
PiecewiseAffine
RandomCrop
RandomCropNearBBox
RandomGridShuffle
RandomResizedCrop
RandomRotate90
RandomScale
RandomSizedBBoxSafeCrop
RandomSizedCrop
Resize
Rotate
SafeRotate
ShiftScaleRotate
SmallestMaxSize
Transpose
VerticalFlip

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

To run the benchmark yourself, follow the instructions in benchmark/README.md

Results for running the benchmark on the first 2000 images from the ImageNet validation set using an Intel Xeon E5-2650 v4. All outputs are converted to a contiguous NumPy array with the np.uint8 data type. The table shows how many images per second can be processed on a single core; higher is better.

albumentations
1.0.0
imgaug
0.4.0
torchvision (Pillow-SIMD backend)
0.9.1
keras
2.4.3
augmentor
0.2.8
solt
0.1.9
HorizontalFlip 6244 2281 2208 774 2201 4334
VerticalFlip 5443 2265 1910 5297 1945 3857
Rotate 340 261 146 24 55 311
ShiftScaleRotate 566 372 129 24 - -
Brightness 2333 1065 370 197 366 1929
Contrast 2352 1098 307 - 306 1950
BrightnessContrast 2331 613 170 - 169 998
ShiftRGB 2320 1059 - 320 - -
ShiftHSV 474 254 55 - - 122
Gamma 2347 - 331 - - 815
Grayscale 3757 368 608 - 901 974
RandomCrop64 149449 2750 32824 - 27683 14356
PadToSize512 3460 - 528 - - 2796
Resize512 910 568 889 - 872 906
RandomSizedCrop_64_512 2276 781 1345 - 1303 1935
Posterize 2353 - - - - -
Solarize 2366 - - - - -
Equalize 558 386 - - 671 -
Multiply 2237 1149 - - - -
MultiplyElementwise 97 177 - - - -
ColorJitter 290 69 52 - - -

Python and library versions: Python 3.9.5 (default, May 12 2021, 15:26:36) [GCC 8.3.0], numpy 1.19.5, pillow-simd 7.0.0.post3, opencv-python 4.5.2.52, scikit-image 0.18.1, scipy 1.6.3.

Contributing

To create a pull request to the repository, follow the documentation at https://albumentations.ai/docs/contributing/

Comments

In some systems, in the multiple GPU regime, PyTorch may deadlock the DataLoader if OpenCV was compiled with OpenCL optimizations. Adding the following two lines before the library import may help. For more details https://github.com/pytorch/pytorch/issues/1355

cv2.setNumThreads(0)
cv2.ocl.setUseOpenCL(False)

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}
}