Image augmentations library Albumentations is heavily based on OpenCV, which allows it to beat torchvision, Kornia, PIL, and other similar libraries.
But there is still a huge room for improvement in terms of performance, as for some low level operations StringZilla or Numkong are faster, for some, especially for float32 images, numpy is the best.
The most annoying component is that OpenCV is limited to input shapes like (H, W, C), which limits its application to videos and volumes with shapes (X, H, W, C)
But there is still a huge room for improvement in terms of performance, as for some low level operations StringZilla or Numkong are faster, for some, especially for float32 images, numpy is the best.
The most annoying component is that OpenCV is limited to input shapes like (H, W, C), which limits its application to videos and volumes with shapes (X, H, W, C)