albumentations-team

Albumentations

Fast image augmentation library and an easy-to-use wrapper around other libraries. Documentation: https://albumentations.ai/docs/ Paper about the library: https://www.mdpi.com/2078-2489/11/2/125
Under MIT License
By albumentations-team

python deep-learning machine-learning object-detection detection image-segmentation image-processing segmentation image-classification image-augmentation augmentation fast-augmentations

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


Why Albumentations

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

```python
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


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 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.


| |albumentations1.0.0|imgaug0.4.0|torchvision (Pillow-SIMD backend)0.9.1|keras2.4.3|augmentor0.2.8|solt0.1.9|
|----------------------|:------------------------------------:|:----------------------------:|:-------------------------------------------------------:|:---------------------------:|:-------------------------------:|:--------------------------:|
|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


python
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:


bibtex
@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}
}