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