Efficient, composable data augmentation for machine and deep learning with support for n-dimensional images, keypoints and categorical masks.
using Pkg
Pkg.add("DataAugmentation")using DataAugmentation, TestImages
item = Image(testimage("lighthouse"))
tfm = Maybe(FlipX{2}()) |> RandomResizeCrop((128, 128))
timage = itemdata(apply(tfm, item))See the documentation for the available transformations and how to define your own.