data.vision¶
Vision utilities.
Datasets¶
datasets.MNIST([root, train, transform]) |
MNIST handwritten digits dataset from http://yann.lecun.com/exdb/mnist |
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 https://github.com/zalandoresearch/fashion-mnist |
datasets.CIFAR10([root, train, transform]) |
CIFAR10 image classification dataset from https://www.cs.toronto.edu/~kriz/cifar.html |
datasets.CIFAR100([root, fine_label, train, …]) |
CIFAR100 image classification dataset from https://www.cs.toronto.edu/~kriz/cifar.html |
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. |