0.2.0 Release

Added support for the keypoint transformations to

• CenterCrop
• Flip
• HorizontalFlip
• IAAAffine
• IAACropAndPad
• IAAFliplr
• IAAFlipud
• IAAPerspective
• IAAPiecewiseAffine
• PadIfNeeded
• RandomCrop
• RandomRotate90
• RandomScale
• RandomSizedCrop
• Rotate
• ShiftScaleRotate
• VerticalFlip

Notebook with an example

Special thanks to the Evegene Khvedchenya (@BloodAxe) for the work.

Added an option to apply the same transformation to the more than one target of the same type.

The possible use case are image2image or stereo-image pipelines.

Notebook with an example

Special thanks to Alexander Buslaev (@albu) for the work.

Added new transformations

• RandomCropNearBBox
• RandomSizedBBoxSafeCrop
• SmallestMaxSize

Speed up in

• Normalize
• Flip
• HorizontalFlip
• VerticalFlip
• ElasticTransform

Bug fixes

• Fix for Compose with multiprocessing DataLoaders.
• Fix in SmallestMaxSize for multiclass masks.
• Fix in RandomBrightness
• Fix in RandomContrast

And many others.

Additional

• Performance benchmark was extended to the Augmentor and Solt libraries.
• Added table to Readme that shows all implemented transformations with the set of possible targets: images, bounding boxes, masks, key points. (Special thanks to Alex Parinov @creafz )
• The library can be installed in anaconda.

Contributors

@BloodAxe @albu @creafz @ternaus @erikgaas @marcocaccin @libfun @DBusAI @alexobednikov @StrikerRUS @IlyaOvodov @ZFTurbo @Vcv85 @georgymironov @LinaShiryaeva @vfdev-5 @daisukelab @cdicle

Extended bounding boxes support. New transformations. New notebooks with examples. A lot of bugfixes.

Bounding boxes support

Transformations that support bounding boxes

The main change in this release is the addition of the operations on bounding boxes to the

• Flip
• VerticalFlip
• HorizontalFlip
• Transpose
• RandomRotate90
• LongestMaxSize
• Resize
• RandomScale
• Crop
• RandomCrop
• CenterCrop
• RandomSizedCrop
• IAAAffine

Supported formats

Currently supported the following formats for the bounding boxes:

1. COCO: [x_min, y_min, width, height], ex [97, 12, 150, 200]
2. Pascal VOC: [x_min, y_min, x_max, y_max], ex [97, 12, 247, 212]

Bounding box filtering

It may happen that after the transformation a big part of the bounding box was cropped and it is needed to exclude such boxes.

We support such a bounding box filtering based on the:

• Bounding box area, measured in pixels.
• Visible box area, measured in percent.

Smaller changes

• Added support for 8-bit images.
• We changed all np.random occurrences to random due to the numpy behavior reported in pytorch/pytorch#5059
• Multiple bugfixes.

Added notebooks with examples

• How to migrate from torchvision to albumentations.
• How to apply the transformation to the classification problems.
• How to apply transformations to the detection problems.
• How to apply transformations to the segmentation problems.
• How to apply transformations to the non 8-bit images
• All in one showcase