Uses of Interface
ai.beestream.jitnn.data.Transforms.Transform
Packages that use Transforms.Transform
Package
Description
Datasets: MNIST and CIFAR-10 readers, a byte-level text corpus, and synthetic data, held in memory as
a
Dataset.-
Uses of Transforms.Transform in ai.beestream.jitnn.data
Methods in ai.beestream.jitnn.data that return Transforms.TransformModifier and TypeMethodDescriptionstatic Transforms.TransformTransforms.normalize(float[] mean, float[] std) (x - mean[c]) / std[c] per channel (torchvision's Normalize).static Transforms.TransformTransforms.randomCrop(int pad) Pads the image withpadzeros on every side and crops the original size back at a random offset (torchvision's RandomCrop(size, padding)).static Transforms.TransformTransforms.randomHorizontalFlip()Mirrors the image left to right with probability 1/2 (torchvision's RandomHorizontalFlip).default Transforms.TransformTransforms.Transform.then(Transforms.Transform next) This transform, thennext.Methods in ai.beestream.jitnn.data with parameters of type Transforms.TransformModifier and TypeMethodDescriptiondefault Transforms.TransformTransforms.Transform.then(Transforms.Transform next) This transform, thennext.DataLoader.Builder.transform(Transforms.Transform t) Applied to every sample as its batch is assembled (augmentation, normalisation).