An efficient library for image augmentation, providing extensive transformations to support machine learning and computer vision tasks.
Readme
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:
Vladimir I. Iglovikov | Kaggle Grandmaster
Mikhail Druzhinin | Kaggle Expert
Alexander Buslaev — Computer Vision Engineer at Mapbox | Kaggle Master
Evegene Khvedchenya — Computer Vision Research Engineer at Piñata Farms | Kaggle Grandmaster
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.
The full documentation is available at https://albumentations.ai/docs/.
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"]
Please start with the introduction articles about why image augmentation is important and how it helps to build better models.
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.
We have examples of using Albumentations along with PyTorch and TensorFlow.
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.
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 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 | ✓ | ✓ | ✓ | |
| Flip | ✓ | ✓ | ✓ | ✓ |
| GridDistortion | ✓ | ✓ | ✓ | |
| GridDropout | ✓ | ✓ | ||
| 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 | ✓ | ✓ | ✓ |
Transforms that mix several images into one
| Transform | Image | Mask | BBoxes | Keypoints | Global Label |
|---|---|---|---|---|---|
| MixUp | ✓ | ✓ | ✓ |
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 | 1.4.1 |
| imgaug | 0.4.0 |
| torchvision | 0.17.1+rocm5.7 |
| numpy | 1.26.4 |
| opencv-python-headless | 4.9.0.80 |
| scikit-image | 0.22.0 |
| scipy | 1.12.0 |
| pillow | 10.2.0 |
| kornia | 0.7.2 |
| augly | 1.0.0 |
| albumentations 1.4.0 | torchvision 0.17.1+rocm5.7 | kornia 0.7.2 | augly 1.0.0 | imgaug 0.4.0 | |
|---|---|---|---|---|---|
| HorizontalFlip | 9843 ± 2135 | 2436 ± 29 | 1014 ± 3 | 3663 ± 18 | 4884 ± 51 |
| VerticalFlip | 9898 ± 18 | 2570 ± 37 | 1024 ± 4 | 5325 ± 13 | 8683 ± 5 |
| Rotate | 610 ± 4 | 153 ± 2 | 204 ± 1 | 626 ± 3 | 499 ± 5 |
| Affine | 1705 ± 67 | 159 ± 1 | 200 ± 1 | - | 663 ± 24 |
| Equalize | 1061 ± 14 | 337 ± 1 | 77 ± 1 | - | 845 ± 33 |
| RandomCrop64 | 203197 ± 2105 | 15931 ± 27 | 837 ± 2 | 21858 ± 362 | 5681 ± 96 |
| RandomResizedCrop | 2998 ± 30 | 1160 ± 4 | 190 ± 1 | - | - |
| ShiftRGB | 1400 ± 3 | - | 435 ± 1 | - | 1528 ± 6 |
| Resize | 2581 ± 3 | 1239 ± 1 | 197 ± 1 | 431 ± 1 | 1728 ± 1 |
| RandomGamma | 4556 ± 3 | 230 ± 1 | 205 ± 1 | - | 2282 ± 110 |
| Grayscale | 7234 ± 4 | 1539 ± 7 | 444 ± 3 | 2606 ± 2 | 918 ± 42 |
| ColorJitter | 452 ± 43 | 51 ± 1 | 50 ± 1 | 221 ± 1 | - |
| RandomPerspective | 465 ± 1 | 121 ± 1 | 115 ± 1 | - | 433 ± 16 |
| GaussianBlur | 2315 ± 9 | 106 ± 2 | 72 ± 1 | 161 ± 1 | 1213 ± 3 |
| MedianBlur | 3711 ± 2 | - | 2 ± 1 | - | 566 ± 3 |
| MotionBlur | 2763 ± 25 | - | 101 ± 4 | - | 508 ± 2 |
| Posterize | 4238 ± 51 | 2581 ± 20 | 284 ± 4 | - | 1893 ± 9 |
| JpegCompression | 208 ± 1 | - | - | 692 ± 4 | 435 ± 1 |
| GaussianNoise | 64 ± 9 | - | - | 67 ± 1 | 212 ± 16 |
| Elastic | 129 ± 1 | 3 ± 1 | 1 ± 1 | - | 128 ± 1 |
To create a pull request to the repository, follow the documentation at CONTRIBUTING.md
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)
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}
}
FAQs
An efficient library for image augmentation, providing extensive transformations to support machine learning and computer vision tasks.
We found that albumentations demonstrated a healthy version release cadence and project activity because the last version was released less than a year ago. It has 2 open source maintainers collaborating on the project.
Did you know?
Socket for GitHub automatically highlights issues in each pull request and monitors the health of all your open source dependencies. Discover the contents of your packages and block harmful activity before you install or update your dependencies.
Security News
Tea.xyz, a crypto project aimed at rewarding open source contributions, is once again facing backlash due to an influx of spam packages flooding public package registries.
Security News
As cyber threats become more autonomous, AI-powered defenses are crucial for businesses to stay ahead of attackers who can exploit software vulnerabilities at scale.
Security News
UnitedHealth Group disclosed that the ransomware attack on Change Healthcare compromised protected health information for millions in the U.S., with estimated costs to the company expected to reach $1 billion.