albumentations 1.4.15

Description:

albumentations 1.4.15

Albumentations






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:

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.

Sponsors

Table of contents

Albumentations

Why Albumentations
Sponsors
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

See also


List of augmentations

Pixel-level transforms
Spatial-level transforms
Mixing-level transforms


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
Contributing
Community and Support
Comments
Citing



Authors
Vladimir I. Iglovikov | Kaggle Grandmaster
Mikhail Druzhinin | Kaggle Expert
Alex Parinov | Kaggle Master
Alexander Buslaev — Computer Vision Engineer at Mapbox | Kaggle Master
Evegene Khvedchenya — Computer Vision Research Engineer at Piñata Farms | Kaggle Grandmaster
Installation
Albumentations requires Python 3.8 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
ChromaticAberration
ColorJitter
Defocus
Downscale
Emboss
Equalize
FDA
FancyPCA
FromFloat
GaussNoise
GaussianBlur
GlassBlur
HistogramMatching
HueSaturationValue
ISONoise
ImageCompression
InvertImg
MedianBlur
MotionBlur
MultiplicativeNoise
Normalize
PixelDistributionAdaptation
PlanckianJitter
Posterize
RGBShift
RandomBrightnessContrast
RandomFog
RandomGamma
RandomGravel
RandomRain
RandomShadow
RandomSnow
RandomSunFlare
RandomToneCurve
RingingOvershoot
Sharpen
Solarize
Spatter
Superpixels
TemplateTransform
TextImage
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
Mask
BBoxes
Keypoints




Affine
✓
✓
✓
✓


BBoxSafeRandomCrop
✓
✓
✓
✓


CenterCrop
✓
✓
✓
✓


CoarseDropout
✓
✓

✓


Crop
✓
✓
✓
✓


CropAndPad
✓
✓
✓
✓


CropNonEmptyMaskIfExists
✓
✓
✓
✓


D4
✓
✓
✓
✓


ElasticTransform
✓
✓
✓



GridDistortion
✓
✓
✓



GridDropout
✓
✓




GridElasticDeform
✓
✓




HorizontalFlip
✓
✓
✓
✓


Lambda
✓
✓
✓
✓


LongestMaxSize
✓
✓
✓
✓


MaskDropout
✓
✓




Morphological
✓
✓




NoOp
✓
✓
✓
✓


OpticalDistortion
✓
✓
✓



PadIfNeeded
✓
✓
✓
✓


Perspective
✓
✓
✓
✓


PiecewiseAffine
✓
✓
✓
✓


PixelDropout
✓
✓




RandomCrop
✓
✓
✓
✓


RandomCropFromBorders
✓
✓
✓
✓


RandomGridShuffle
✓
✓

✓


RandomResizedCrop
✓
✓
✓
✓


RandomRotate90
✓
✓
✓
✓


RandomScale
✓
✓
✓
✓


RandomSizedBBoxSafeCrop
✓
✓
✓
✓


RandomSizedCrop
✓
✓
✓
✓


Resize
✓
✓
✓
✓


Rotate
✓
✓
✓
✓


SafeRotate
✓
✓
✓
✓


ShiftScaleRotate
✓
✓
✓
✓


SmallestMaxSize
✓
✓
✓
✓


Transpose
✓
✓
✓
✓


VerticalFlip
✓
✓
✓
✓


XYMasking
✓
✓

✓



Mixing-level transforms
Transforms that mix several images into one



Transform
Image
Mask
BBoxes
Keypoints
Global Label




MixUp
✓
✓


✓


OverlayElements
✓
✓






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 AMD Ryzen Threadripper 3970X CPU.
The table shows how many images per second can be processed on a single core; higher is better.



Library
Version




Python
3.10.13 (main, Sep 11 2023, 13:44:35) [GCC 11.2.0]


albumentations
1.4.11


imgaug
0.4.0


torchvision
0.18.1+rocm6.0


numpy
1.26.4


opencv-python-headless
4.10.0.84


scikit-image
0.24.0


scipy
1.14.0


pillow
10.4.0


kornia
0.7.3


augly
1.0.0







albumentations1.4.11
torchvision0.18.1+rocm6.0
kornia0.7.3
augly1.0.0
imgaug0.4.0




HorizontalFlip
8017 ± 12
2436 ± 2
935 ± 3
3575 ± 4
4806 ± 7


VerticalFlip
7366 ± 7
2563 ± 8
943 ± 1
4949 ± 5
8159 ± 21


Rotate
570 ± 12
152 ± 2
207 ± 1
633 ± 2
496 ± 2


Affine
1382 ± 31
162 ± 1
201 ± 1
-
682 ± 2


Equalize
1027 ± 2
336 ± 2
77 ± 1
-
1183 ± 1


RandomCrop64
19986 ± 57
15336 ± 16
811 ± 1
19882 ± 356
5410 ± 5


RandomResizedCrop
2308 ± 7
1046 ± 3
187 ± 1
-
-


ShiftRGB
1240 ± 3
-
425 ± 2
-
1554 ± 6


Resize
2314 ± 9
1272 ± 3
201 ± 3
431 ± 1
1715 ± 2


RandomGamma
2552 ± 2
232 ± 1
211 ± 1
-
1794 ± 1


Grayscale
7313 ± 4
1652 ± 2
443 ± 2
2639 ± 2
1171 ± 23


ColorJitter
396 ± 1
51 ± 1
50 ± 1
224 ± 1
-


PlankianJitter
449 ± 1
-
598 ± 1
-
-


RandomPerspective
471 ± 1
123 ± 1
114 ± 1
-
478 ± 2


GaussianBlur
2099 ± 2
113 ± 2
79 ± 2
165 ± 1
1244 ± 2


MedianBlur
538 ± 1
-
3 ± 1
-
565 ± 1


MotionBlur
2197 ± 9
-
102 ± 1
-
508 ± 1


Posterize
2449 ± 1
2587 ± 3
339 ± 6
-
1547 ± 1


JpegCompression
827 ± 1
-
50 ± 2
684 ± 1
428 ± 4


GaussianNoise
78 ± 1
-
-
67 ± 1
128 ± 1


Elastic
127 ± 1
3 ± 1
1 ± 1
-
130 ± 1


Normalize
971 ± 2
449 ± 1
415 ± 1
-
-



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

Community and Support

Twitter
Discord

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}
}