mindspore.dataset.vision.MixUp

class mindspore.dataset.vision.MixUp(batch_size, alpha, is_single=True)

Randomly mix up a batch of numpy.ndarray images together with its labels.

Each image will be multiplied by a random weight \(lambda\) generated from the Beta distribution and then added to another image multiplied by \(1 - lambda\). The same transformation will be applied to their labels with the same value of \(lambda\). Make sure that the labels are one-hot encoded in advance.

Parameters

• batch_size (int) – The number of images in a batch.

• alpha (float) – The alpha and beta parameter for the Beta distribution.

• is_single (bool, optional) – If True, it will randomly mix up [img0, …, img(n-1), img(n)] with [img1, …, img(n), img0] in each batch. Otherwise, it will randomly mix up images with the output of the previous batch. Default: True.

Raises

• TypeError – If batch_size is not of type integer.

• TypeError – If alpha is not of type float.

• TypeError – If is_single is not of type boolean.

• ValueError – If batch_size is not positive.

• ValueError – If alpha is not positive.

Supported Platforms:

CPU

Examples

>>> import mindspore.dataset as ds
>>> import mindspore.dataset.vision as vision
>>> import mindspore.dataset.transforms as transforms
>>>
>>> image_folder_dataset = ds.ImageFolderDataset("/path/to/image_folder_dataset_directory")
>>> # first decode the image
>>> image_folder_dataset = image_folder_dataset.map(operations=vision.Decode(),
...                                                 input_columns="image")
>>> # then ont hot decode the label
>>> image_folder_dataset = image_folder_dataset.map(operations=transforms.OneHot(10),
...                                                 input_columns="label")
>>> # batch the samples
>>> batch_size = 4
>>> image_folder_dataset = image_folder_dataset.batch(batch_size=batch_size)
>>> # finally mix up the images and labels
>>> image_folder_dataset = image_folder_dataset.map(
...     operations=vision.MixUp(batch_size=batch_size, alpha=0.2),
...     input_columns=["image", "label"])

Tutorial Examples:

• Illustration of vision transforms