albumentations 1.3.1

Fast image augmentation library and easy to use wrapper around other libraries

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:

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
• Installation
• Documentation
• A simple example
• Getting started
  • I am new to image augmentation
  • I want to use Albumentations for the specific task such as classification or segmentation
  • I want to know how to use Albumentations with deep learning frameworks
  • I want to explore augmentations and see Albumentations in action
• Who is using Albumentations
• List of augmentations
  • Pixel-level transforms
  • Spatial-level transforms
• A few more examples of augmentations
• Benchmarking results
• Contributing
• Comments
• Citing

Authors

Alexander Buslaev — Computer Vision Engineer at Mapbox | Kaggle Master

Alex Parinov | 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 | Kaggle Expert

Installation

Albumentations requires Python 3.7 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:

• A list of papers that cite Albumentations.
• A list of teams that were using Albumentations and took high places in machine learning competitions.
• Open source projects that use 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. The list of pixel-level transforms:

• AdvancedBlur
• Blur
• CLAHE
• ChannelDropout
• ChannelShuffle
• ColorJitter
• Defocus
• Downscale
• Emboss
• Equalize
• FDA
• FancyPCA
• FromFloat
• GaussNoise
• GaussianBlur
• GlassBlur
• HistogramMatching
• HueSaturationValue
• ISONoise
• ImageCompression
• InvertImg
• MedianBlur
• MotionBlur
• MultiplicativeNoise
• Normalize
• PixelDistributionAdaptation
• Posterize
• RGBShift
• RandomBrightnessContrast
• RandomFog
• RandomGamma
• RandomGravel
• RandomRain
• RandomShadow
• RandomSnow
• RandomSunFlare
• RandomToneCurve
• RingingOvershoot
• Sharpen
• Solarize
• Spatter
• Superpixels
• TemplateTransform
• ToFloat
• ToGray
• ToRGB
• ToSepia
• UnsharpMask
• ZoomBlur

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	✓	✓	✓	✓
BBoxSafeRandomCrop	✓	✓	✓
CenterCrop	✓	✓	✓	✓
CoarseDropout	✓	✓		✓
Crop	✓	✓	✓	✓
CropAndPad	✓	✓	✓	✓
CropNonEmptyMaskIfExists	✓	✓	✓	✓
ElasticTransform	✓	✓	✓
Flip	✓	✓	✓	✓
GridDistortion	✓	✓	✓
GridDropout	✓	✓
HorizontalFlip	✓	✓	✓	✓
Lambda	✓	✓	✓	✓
LongestMaxSize	✓	✓	✓	✓
MaskDropout	✓	✓
NoOp	✓	✓	✓	✓
OpticalDistortion	✓	✓	✓
PadIfNeeded	✓	✓	✓	✓
Perspective	✓	✓	✓	✓
PiecewiseAffine	✓	✓	✓	✓
PixelDropout	✓	✓	✓	✓
RandomCrop	✓	✓	✓	✓
RandomCropFromBorders	✓	✓	✓	✓
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

Medical imaging

Object detection and semantic segmentation on the Mapillary Vistas dataset

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(R) Xeon(R) Gold 6140 CPU. 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 <small>1.1.0</small>	imgaug <small>0.4.0</small>	torchvision (Pillow-SIMD backend) <small>0.10.1</small>	keras <small>2.6.0</small>	augmentor <small>0.2.8</small>	solt <small>0.1.9</small>
HorizontalFlip	10220	2702	2517	876	2528	6798
VerticalFlip	4438	2141	2151	4381	2155	3659
Rotate	389	283	165	28	60	367
ShiftScaleRotate	669	425	146	29	-	-
Brightness	2765	1124	411	229	408	2335
Contrast	2767	1137	349	-	346	2341
BrightnessContrast	2746	629	190	-	189	1196
ShiftRGB	2758	1093	-	360	-	-
ShiftHSV	598	259	59	-	-	144
Gamma	2849	-	388	-	-	933
Grayscale	5219	393	723	-	1082	1309
RandomCrop64	163550	2562	50159	-	42842	22260
PadToSize512	3609	-	602	-	-	3097
Resize512	1049	611	1066	-	1041	1017
RandomSizedCrop_64_512	3224	858	1660	-	1598	2675
Posterize	2789	-	-	-	-	-
Solarize	2761	-	-	-	-	-
Equalize	647	385	-	-	765	-
Multiply	2659	1129	-	-	-	-
MultiplyElementwise	111	200	-	-	-	-
ColorJitter	351	78	57	-	-	-

Python and library versions: Python 3.9.5 (default, Jun 23 2021, 15:01:51) [GCC 8.3.0], numpy 1.19.5, pillow-simd 7.0.0.post3, opencv-python 4.5.3.56, scikit-image 0.18.3, scipy 1.7.1.

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}
}