Skip to content

Latest commit

 

History

History
294 lines (235 loc) · 23.4 KB

README.md

File metadata and controls

294 lines (235 loc) · 23.4 KB
Raw

Albumentations

Build Status Documentation Status

  • The library is faster than other libraries on most of the transformations.
  • Based on numpy, OpenCV, imgaug picking the best from each of them.
  • Simple, flexible API that allows the library to be used in any computer vision pipeline.
  • Large, diverse set of transformations.
  • Easy to extend the library to wrap around other libraries.
  • Easy to extend to other tasks.
  • Supports transformations on images, masks, key points and bounding boxes.
  • Supports python 2.7-3.7
  • Easy integration with PyTorch.
  • Easy transfer from torchvision.
  • Was used to get top results in many DL competitions at Kaggle, topcoder, CVPR, MICCAI.
  • Written by Kaggle Masters.

Table of contents

How to use

All in one showcase notebook - showcase.ipynb

Classification - example.ipynb

Object detection - example_bboxes.ipynb

Non-8-bit images - example_16_bit_tiff.ipynb

Image segmentation example_kaggle_salt.ipynb

Keypoints example_keypoints.ipynb

Custom targets example_multi_target.ipynb

Weather transforms example_weather_transforms.ipynb

Serialization serialization.ipynb

Replay/Deterministic mode replay.ipynb

You can use this Google Colaboratory notebook to adjust image augmentation parameters and see the resulting images.

parrot

inria

medical

vistas

Authors

Alexander Buslaev

Alex Parinov

Vladimir I. Iglovikov

Evegene Khvedchenya

Mikhail Druzhinin

Installation

PyPI

You can use pip to install albumentations:

pip install albumentations

If you want to get the latest version of the code before it is released on PyPI you can install the library from GitHub:

pip install -U git+https://github.com/albu/albumentations

And it also works in Kaggle GPU kernels (proof)

!pip install albumentations > /dev/null

Conda

To install albumentations using conda we need first to install imgaug via conda-forge collection

conda install -c conda-forge imgaug
conda install albumentations -c albumentations

Documentation

The full documentation is available at albumentations.readthedocs.io.

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
CenterCrop ✓ ✓ ✓ ✓
Crop ✓ ✓ ✓ ✓
CropNonEmptyMaskIfExists ✓ ✓ ✓ ✓
ElasticTransform ✓ ✓
Flip ✓ ✓ ✓ ✓
GridDistortion ✓ ✓
HorizontalFlip ✓ ✓ ✓ ✓
IAAAffine ✓ ✓ ✓ ✓
IAACropAndPad ✓ ✓ ✓ ✓
IAAFliplr ✓ ✓ ✓ ✓
IAAFlipud ✓ ✓ ✓ ✓
IAAPerspective ✓ ✓ ✓ ✓
IAAPiecewiseAffine ✓ ✓ ✓ ✓
Lambda ✓ ✓ ✓ ✓
LongestMaxSize ✓ ✓ ✓ ✓
NoOp ✓ ✓ ✓ ✓
OpticalDistortion ✓ ✓
PadIfNeeded ✓ ✓ ✓ ✓
RandomCrop ✓ ✓ ✓ ✓
RandomCropNearBBox ✓ ✓ ✓ ✓
RandomGridShuffle ✓ ✓
RandomResizedCrop ✓ ✓ ✓ ✓
RandomRotate90 ✓ ✓ ✓ ✓
RandomScale ✓ ✓ ✓ ✓
RandomSizedBBoxSafeCrop ✓ ✓ ✓
RandomSizedCrop ✓ ✓ ✓ ✓
Resize ✓ ✓ ✓ ✓
Rotate ✓ ✓ ✓ ✓
ShiftScaleRotate ✓ ✓ ✓ ✓
SmallestMaxSize ✓ ✓ ✓ ✓
Transpose ✓ ✓ ✓ ✓
VerticalFlip ✓ ✓ ✓ ✓

Migrating from torchvision to albumentations

Migrating from torchvision to albumentations is simple - you just need to change a few lines of code. Albumentations has equivalents for common torchvision transforms as well as plenty of transforms that are not presented in torchvision. migrating_from_torchvision_to_albumentations.ipynb shows how one can migrate code from torchvision to albumentations.

Benchmarking results

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

Results for running the benchmark on first 2000 images from the ImageNet validation set using an Intel Xeon Gold 6140 CPU. For libraries that work with NumPy arrays, the uint8 data type is used to represent an image. The table shows how many images per second can be processed on a single core, higher is better.

albumentations
0.4.0		 imgaug
0.2.9		 torchvision (Pillow backend)
0.4.0		 torchvision (Pillow-SIMD backend)
0.4.0		 keras
2.3.1		 augmentor
0.2.6		 solt
0.1.8
HorizontalFlip 961 754 1246 1251 669 1154 619
VerticalFlip 3941 2069 1105 1150 3884 1054 3540
Rotate 375 300 83 120 18 36 91
ShiftScaleRotate 664 454 75 116 23 - -
Brightness 1806 1067 260 320 133 252 1694
Contrast 1701 1123 190 241 - 184 1699
BrightnessContrast 1749 577 114 143 - 112 880
ShiftRGB 1813 984 - - 509 - -
ShiftHSV 349 340 35 45 - - 106
Gamma 1926 - 549 580 - - 701
Grayscale 3688 307 487 574 - 872 2927
RandomCrop64 602010 2908 22398 33850 - 14267 38450
PadToSize512 2749 - 350 378 - - 2370
Resize512 576 427 211 648 - 213 568
RandomSizedCrop_64_512 2223 715 334 1023 - 339 1949
Equalize 466 460 - - - 256 -

Python and library versions: Python 3.7.3, numpy 1.17.2, pillow 6.2.0, pillow-simd 6.0.0.post0, opencv-python 4.1.1.26, scikit-image 0.15.0, scipy 1.3.0.

Contributing

To create a pull request to the repository follow the documentation at docs/contributing.rst

Adding new transforms

If you are contributing a new transformation, make sure to update "Pixel-level transforms" or/and "Spatial-level transforms" sections of this file (README.md). To do this, simply run (with python3 only):

python3 tools/make_transforms_docs.py make

and copy/paste the results into the corresponding sections. To validate your modifications, you can run:

python3 tools/make_transforms_docs.py check README.md

Building the documentation

  1. Go to docs/ directory 
    cd docs
  2. Install required libraries 
    pip install -r requirements.txt
  3. Build html files 
    make html
  4. Open _build/html/index.html in browser.

Alternatively, you can start a web server that rebuilds the documentation automatically when a change is detected by running make livehtml

Competitions won with the library

Albumentations are widely used in Computer Vision Competitions at Kaggle an other platforms.

You can find their names and links to the solutions here.

Used by

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 pytorch/pytorch#1355

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

Citing

If you find this library useful for your research, please consider citing:

@article{2018arXiv180906839B,
    author = {A. Buslaev, A. Parinov, E. Khvedchenya, V.~I. Iglovikov and A.~A. Kalinin},
     title = "{Albumentations: fast and flexible image augmentations}",
   journal = {ArXiv e-prints},
    eprint = {1809.06839},
      year = 2018
}

You can find the full list of papers that cite Albumentations here.