Batch Transforms

In this section are defined the classes and functions to transform a batch of images or videos.

Note

Whilst these augmentations accept batched data, some of them offer a trade-off between randomness and computational cost such as BatchRandomColorJitter.

Note

Some transforms rely on Torchvision functional.

Wrappers

List of wrappers of the data augmentations.

BatchImageWrapper(transforms[, inplace])	Wrap transforms to handle image data.
BatchVideoWrapper(transforms[, inplace, ...])	Wrap transforms to handle batched video data.

Transforms

List of the batched data augmentations.

BatchMixUp(alpha[, inplace])	Mix input tensor with linear interpolation drawn according a Beta law.
BatchRandomApply(transforms[, p, inplace])	Apply randomly a list of transformations to a batch of images with a given probability.
BatchRandomColorJitter([brightness, ...])	Randomly change the brightness, contrast, saturation and hue to a batch of images.
BatchRandomGaussianBlur(kernel_size[, ...])	Blurs batch of images with randomly chosen Gaussian blur.
BatchRandomGrayScale([p, inplace])	Convert batch of images to grayscale.
BatchRandomHorizontalFlip([p, inplace])	Horizontally flip the given batch of images randomly with a given probability.
BatchRandomResizedCrop(size[, scale, ratio, ...])	Crop a random portion of a batch of images and resize it to a given size.
BatchRandomSolarize(threshold[, p, inplace, ...])	Solarize the batch of images randomly with a given probability by inverting all pixel values above a threshold.
BatchRandomTransform(p, inplace)	Abstract class to make a base class for all batch random transforms.
BatchVideoResize(size[, interpolation, ...])	Resize the input video to the given size.

Functional

List of the functions to make the batched data augmentations.

batch_adjust_brightness(imgs, brightness_factor)	Adjust brightness of a batch of images.
batch_adjust_contrast(imgs, contrast_factor)	Adjust contrast of a batch of images.
batch_adjust_hue(imgs, hue_factor[, value_check])	Adjust hue of a batch of images.
batch_adjust_saturation(imgs, saturation_factor)	Adjust color saturation of a batch of images.
batch_gaussian_blur(imgs, kernel_size[, ...])	Performs Gaussian blurring on the batch of images by given kernel.
batch_mixup(tensor_1, tensor_2, lam[, inplace])	Mix two tensors with linear interpolation.