Table Of Contents
Table Of Contents

Vision utilities.


datasets.MNIST([root, train, transform]) MNIST handwritten digits dataset from
datasets.FashionMNIST([root, train, transform]) A dataset of Zalando’s article images consisting of fashion products, a drop-in replacement of the original MNIST dataset from
datasets.CIFAR10([root, train, transform]) CIFAR10 image classification dataset from
datasets.CIFAR100([root, fine_label, train, …]) CIFAR100 image classification dataset from
datasets.ImageRecordDataset(filename[, …]) A dataset wrapping over a RecordIO file containing images.
datasets.ImageFolderDataset(root[, flag, …]) A dataset for loading image files stored in a folder structure like.

Data transformations

transforms.Compose(transforms) Sequentially composes multiple transforms.
transforms.Cast([dtype]) Cast input to a specific data type
transforms.ToTensor() Converts an image NDArray to a tensor NDArray.
transforms.Normalize(mean, std) Normalize an tensor of shape (C x H x W) with mean and standard deviation.
transforms.RandomResizedCrop(size[, scale, …]) Crop the input image with random scale and aspect ratio.
transforms.CenterCrop(size[, interpolation]) Crops the image src to the given size by trimming on all four sides and preserving the center of the image.
transforms.Resize(size[, keep_ratio, …]) Resize an image to the given size.
transforms.RandomFlipLeftRight() Randomly flip the input image left to right with a probability of 0.5.
transforms.RandomFlipTopBottom() Randomly flip the input image top to bottom with a probability of 0.5.
transforms.RandomBrightness(brightness) Randomly jitters image brightness with a factor chosen from [max(0, 1 - brightness), 1 + brightness].
transforms.RandomContrast(contrast) Randomly jitters image contrast with a factor chosen from [max(0, 1 - contrast), 1 + contrast].
transforms.RandomSaturation(saturation) Randomly jitters image saturation with a factor chosen from [max(0, 1 - saturation), 1 + saturation].
transforms.RandomHue(hue) Randomly jitters image hue with a factor chosen from [max(0, 1 - hue), 1 + hue].
transforms.RandomColorJitter([brightness, …]) Randomly jitters the brightness, contrast, saturation, and hue of an image.
transforms.RandomLighting(alpha) Add AlexNet-style PCA-based noise to an image.