mindspore.dataset.vision

This module is to support vision augmentations. It includes two parts: c_transforms and py_transforms. C_transforms is a high performance image augmentation module which is developed with c++ opencv. Py_transforms provide more kinds of image augmentations which is developed with Python PIL.

Common imported modules in corresponding API examples are as follows:

import mindspore.dataset.vision.c_transforms as c_vision
import mindspore.dataset.vision.py_transforms as py_vision
from mindspore.dataset.transforms import c_transforms

mindspore.dataset.vision.c_transforms

mindspore.dataset.vision.c_transforms.AutoContrast

Apply automatic contrast on input image.

mindspore.dataset.vision.c_transforms.BoundingBoxAugment

Apply a given image transform on a random selection of bounding box regions of a given image.

mindspore.dataset.vision.c_transforms.CenterCrop

Crop the input image at the center to the given size.

mindspore.dataset.vision.c_transforms.Crop

Crop the input image at a specific location.

mindspore.dataset.vision.c_transforms.CutMixBatch

Apply CutMix transformation on input batch of images and labels.

mindspore.dataset.vision.c_transforms.CutOut

Randomly cut (mask) out a given number of square patches from the input image array.

mindspore.dataset.vision.c_transforms.Decode

Decode the input image in RGB mode(default) or BGR mode(deprecated).

mindspore.dataset.vision.c_transforms.Equalize

Apply histogram equalization on input image.

mindspore.dataset.vision.c_transforms.GaussianBlur

Blur input image with the specified Gaussian kernel.

mindspore.dataset.vision.c_transforms.HorizontalFlip

Flip the input image horizontally.

mindspore.dataset.vision.c_transforms.HWC2CHW

Transpose the input image from shape (H, W, C) to shape (C, H, W).

mindspore.dataset.vision.c_transforms.Invert

Apply invert on input image in RGB mode.

mindspore.dataset.vision.c_transforms.MixUpBatch

Apply MixUp transformation on input batch of images and labels.

mindspore.dataset.vision.c_transforms.Normalize

Normalize the input image with respect to mean and standard deviation.

mindspore.dataset.vision.c_transforms.NormalizePad

Normalize the input image with respect to mean and standard deviation then pad an extra channel with value zero.

mindspore.dataset.vision.c_transforms.Pad

Pad the image according to padding parameters.

mindspore.dataset.vision.c_transforms.RandomAffine

Apply Random affine transformation to the input image.

mindspore.dataset.vision.c_transforms.RandomColor

Adjust the color of the input image by a fixed or random degree.

mindspore.dataset.vision.c_transforms.RandomColorAdjust

Randomly adjust the brightness, contrast, saturation, and hue of the input image.

mindspore.dataset.vision.c_transforms.RandomCrop

Crop the input image at a random location.

mindspore.dataset.vision.c_transforms.RandomCropDecodeResize

A combination of Crop, Decode and Resize.

mindspore.dataset.vision.c_transforms.RandomCropWithBBox

Crop the input image at a random location and adjust bounding boxes accordingly.

mindspore.dataset.vision.c_transforms.RandomHorizontalFlip

Randomly flip the input image horizontally with a given probability.

mindspore.dataset.vision.c_transforms.RandomHorizontalFlipWithBBox

Flip the input image horizontally randomly with a given probability and adjust bounding boxes accordingly.

mindspore.dataset.vision.c_transforms.RandomPosterize

Reduce the number of bits for each color channel to posterize the input image randomly with a given probability.

mindspore.dataset.vision.c_transforms.RandomResize

Resize the input image using a randomly selected interpolation mode.

mindspore.dataset.vision.c_transforms.RandomResizedCrop

Crop the input image to a random size and aspect ratio.

mindspore.dataset.vision.c_transforms.RandomResizedCropWithBBox

Crop the input image to a random size and aspect ratio and adjust bounding boxes accordingly.

mindspore.dataset.vision.c_transforms.RandomResizeWithBBox

Tensor operation to resize the input image using a randomly selected interpolation mode and adjust bounding boxes accordingly.

mindspore.dataset.vision.c_transforms.RandomRotation

Rotate the input image randomly within a specified range of degrees.

mindspore.dataset.vision.c_transforms.RandomSelectSubpolicy

Choose a random sub-policy from a policy list to be applied on the input image.

mindspore.dataset.vision.c_transforms.RandomSharpness

Adjust the sharpness of the input image by a fixed or random degree.

mindspore.dataset.vision.c_transforms.RandomSolarize

Randomly selects a subrange within the specified threshold range and sets the pixel value within the subrange to (255 - pixel).

mindspore.dataset.vision.c_transforms.RandomVerticalFlip

Randomly flip the input image vertically with a given probability.

mindspore.dataset.vision.c_transforms.RandomVerticalFlipWithBBox

Flip the input image vertically, randomly with a given probability and adjust bounding boxes accordingly.

mindspore.dataset.vision.c_transforms.Rescale

Rescale the input image with the given rescale and shift.

mindspore.dataset.vision.c_transforms.Resize

Resize the input image to the given size with a given interpolation mode.

mindspore.dataset.vision.c_transforms.ResizeWithBBox

Resize the input image to the given size and adjust bounding boxes accordingly.

mindspore.dataset.vision.c_transforms.Rotate

Rotate the input image by specified degrees.

mindspore.dataset.vision.c_transforms.SoftDvppDecodeRandomCropResizeJpeg

A combination of Crop, Decode and Resize using the simulation algorithm of Ascend series chip DVPP module.

mindspore.dataset.vision.c_transforms.SoftDvppDecodeResizeJpeg

Decode and resize JPEG image using the simulation algorithm of Ascend series chip DVPP module.

mindspore.dataset.vision.c_transforms.UniformAugment

Perform randomly selected augmentation on input image.

mindspore.dataset.vision.c_transforms.VerticalFlip

Flip the input image vertically.

mindspore.dataset.vision.py_transforms

mindspore.dataset.vision.py_transforms.AutoContrast

Automatically maximize the contrast of the input PIL Image.

mindspore.dataset.vision.py_transforms.CenterCrop

Crop the central region of the input PIL Image with the given size.

mindspore.dataset.vision.py_transforms.Cutout

Randomly apply a given number of square patches of zeros to a location within the input numpy.ndarray image of shape (C, H, W).

mindspore.dataset.vision.py_transforms.Decode

Decode the input raw image to PIL Image format in RGB mode.

mindspore.dataset.vision.py_transforms.Equalize

Apply histogram equalization on the input PIL Image.

mindspore.dataset.vision.py_transforms.FiveCrop

Crop the given image into one central crop and four corners.

mindspore.dataset.vision.py_transforms.Grayscale

Convert the input PIL Image to grayscale.

mindspore.dataset.vision.py_transforms.HsvToRgb

Convert one or more numpy.ndarray images from HSV to RGB.

mindspore.dataset.vision.py_transforms.HWC2CHW

Transpose the input numpy.ndarray image of shape (H, W, C) to (C, H, W).

mindspore.dataset.vision.py_transforms.Invert

Invert the colors of the input PIL Image.

mindspore.dataset.vision.py_transforms.LinearTransformation

Transform the input numpy.ndarray image with a given square transformation matrix and a mean vector.

mindspore.dataset.vision.py_transforms.MixUp

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

mindspore.dataset.vision.py_transforms.Normalize

Normalize the input numpy.ndarray image of shape (C, H, W) with the specified mean and standard deviation.

mindspore.dataset.vision.py_transforms.NormalizePad

Normalize the input numpy.ndarray image of shape (C, H, W) with the specified mean and standard deviation, then pad an extra channel filled with zeros.

mindspore.dataset.vision.py_transforms.Pad

Pad the input image on all sides with the given padding parameters.

mindspore.dataset.vision.py_transforms.RandomAffine

Apply random affine transformation to the input PIL Image.

mindspore.dataset.vision.py_transforms.RandomColor

Adjust the color balance of the input PIL Image by a random degree.

mindspore.dataset.vision.py_transforms.RandomColorAdjust

Randomly adjust the brightness, contrast, saturation, and hue of the input PIL Image.

mindspore.dataset.vision.py_transforms.RandomCrop

Crop the input PIL Image at a random location with the specified size.

mindspore.dataset.vision.py_transforms.RandomErasing

Randomly erase the pixels within a random selected rectangle region with a given probability.

mindspore.dataset.vision.py_transforms.RandomGrayscale

Randomly convert the input image into grayscale with a given probability.

mindspore.dataset.vision.py_transforms.RandomHorizontalFlip

Randomly flip the input image horizontally with a given probability.

mindspore.dataset.vision.py_transforms.RandomPerspective

Randomly apply perspective transformation to the input PIL Image with a given probability.

mindspore.dataset.vision.py_transforms.RandomResizedCrop

Randomly crop the image and resize it to a given size.

mindspore.dataset.vision.py_transforms.RandomRotation

Rotate the input PIL Image by a random angle.

mindspore.dataset.vision.py_transforms.RandomSharpness

Adjust the sharpness of the input PIL Image by a random degree.

mindspore.dataset.vision.py_transforms.RandomVerticalFlip

Randomly flip the input image vertically with a given probability.

mindspore.dataset.vision.py_transforms.Resize

Resize the input PIL Image to the given size.

mindspore.dataset.vision.py_transforms.RgbToHsv

Convert one or more numpy.ndarray images from RGB to HSV.

mindspore.dataset.vision.py_transforms.TenCrop

Crop the given image into one central crop and four corners plus the flipped version of these.

mindspore.dataset.vision.py_transforms.ToPIL

Convert the input decoded numpy.ndarray image to PIL Image.

mindspore.dataset.vision.py_transforms.ToTensor

Convert the input PIL Image or numpy.ndarray of shape (H, W, C) in the range [0, 255] to numpy.ndarray of shape (C, H, W) in the range [0.0, 1.0] with the desired dtype.

mindspore.dataset.vision.py_transforms.ToType

Convert the input numpy.ndarray image to the desired dtype.

mindspore.dataset.vision.py_transforms.UniformAugment

Uniformly select a number of transformations from a sequence and apply them sequentially and randomly, which means that there is a chance that a chosen transformation will not be applied.