Albumentations Files

• Support Our Work
• Transforms
• Speedups
• Bug fixes

Support Our Work

1. Help Us Grow - If you find value in Albumentations, consider becoming a sponsor. Every contribution, no matter the size, helps us maintain and improve the library for everyone.
2. Show Your Support - If you enjoy using Albumentations, consider giving us a ⭐ on GitHub. It helps others discover the library and motivates our team.
3. Join Our Community - Have suggestions or ran into issues? We welcome your input! Share your experience in our GitHub issues or connect with us on Discord.

Transforms

New transform Mosaic

Generalization of Mosaic from Ultralitics and YOLO4, and works per image an not on "batch" => can choose what additional images to pass, could be hard or rare classes.

by @Shysto and @ternaus

Core

SomeOf

Changed functionality to a more intuituve

Now it works as:

1. Select n transforms with equal probability
2. Apply each of them with the probability of each transform

Passing bounding bbox labels

Removed to pass labels when apply to bounding boxes.

:::python
In [9]: bboxes = np.array([[0.2, 0.2, 0.4, 0.4], [0.3, 0.4, 0.7, 0.9]])

In [10]: transform = A.Compose([A.HorizontalFlip(p=1)], bbox_params={"format": "albumentations"})

In [11]: image = np.random.rand(640, 640, 3)

In [12]: transformed = transform(image=image, bboxes=bboxes)

=> we can just pass coordinates, without bounding box labels

Speedups

When applied to uint images on 1 CPU core Albumentations outperforms Kornia and torchvision: Image benchmark

But when we compare: - Videos - Albumentations on 1 CPU core vs kornia and torchvision on GTX 4090

Albumentations has a lot to improve. Benchmark on videos

=> Speedups on videos in this release: - HorizontalFlip - VerticalFlip - RandomRotate90 - ChannelShuffle - Crop - RandomCrop - CenterCrop

Bugfixes

• Bugfix in RandomRain, drop_length was not used before
• BugFix in ElasticTransform Added back fill and fill_mask parameters as for extreme deformations they become useful. Also switched kernels for exact and approximate mode
• Fix in docsting by @nicolasj92
• Cleanup in composition module by @dmsy4