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.
mindspore.dataset.vision.c_transforms
Apply automatic contrast on input image. |
|
Apply a given image transform on a random selection of bounding box regions of a given image. |
|
Crops the input image at the center to the given size. |
|
Apply CutMix transformation on input batch of images and labels. |
|
Randomly cut (mask) out a given number of square patches from the input NumPy image array. |
|
Decode the input image in RGB mode. |
|
Apply histogram equalization on input image. |
|
Transpose the input image; shape (H, W, C) to shape (C, H, W). |
|
Apply invert on input image in RGB mode. |
|
Apply MixUp transformation on input batch of images and labels. |
|
Normalize the input image with respect to mean and standard deviation. |
|
Pads the image according to padding parameters. |
|
Apply Random affine transformation to the input image. |
|
Adjust the color of the input image by a fixed or random degree. |
|
Randomly adjust the brightness, contrast, saturation, and hue of the input image. |
|
Crop the input image at a random location. |
|
|
Equivalent to RandomResizedCrop, but crops before decodes. |
Crop the input image at a random location and adjust bounding boxes accordingly. |
|
Flip the input image horizontally, randomly with a given probability. |
|
|
Flip the input image horizontally, randomly with a given probability and adjust bounding boxes accordingly. |
Reduce the number of bits for each color channel. |
|
Tensor operation to resize the input image using a randomly selected interpolation mode. |
|
Crop the input image to a random size and aspect ratio. |
|
|
Crop the input image to a random size and aspect ratio and adjust bounding boxes accordingly. |
Tensor operation to resize the input image using a randomly selected interpolation mode and adjust bounding boxes accordingly. |
|
Rotate the input image by a random angle. |
|
Choose a random sub-policy from a list to be applied on the input image. |
|
Adjust the sharpness of the input image by a fixed or random degree. |
|
Invert all pixel values above a threshold. |
|
Flip the input image vertically, randomly with a given probability. |
|
|
Flip the input image vertically, randomly with a given probability and adjust bounding boxes accordingly. |
Tensor operation to rescale the input image. |
|
Resize the input image to the given size. |
|
Resize the input image to the given size and adjust bounding boxes accordingly. |
|
|
Tensor operation to decode, random crop and resize JPEG image using the simulation algorithm of Ascend series chip DVPP module. |
|
Tensor operation to decode and resize JPEG image using the simulation algorithm of Ascend series chip DVPP module. |
Tensor operation to perform randomly selected augmentation. |
mindspore.dataset.vision.py_transforms
Automatically maximize the contrast of the input PIL image. |
|
Crop the central reigion of the input PIL image to the given size. |
|
Randomly cut (mask) out a given number of square patches from the input NumPy image array. |
|
Decode the input image to PIL image format in RGB mode. |
|
Equalize the histogram of input PIL image. |
|
Generate 5 cropped images (one central image and four corners images). |
|
Convert the input PIL image to grayscale image. |
|
Convert a NumPy HSV image or one batch NumPy HSV images to RGB images. |
|
Transpose a NumPy image array; shape (H, W, C) to shape (C, H, W). |
|
Invert colors of input PIL image. |
|
Apply linear transformation to the input NumPy image array, given a square transformation matrix and a mean vector. |
|
Apply mix up transformation to the input image and label. |
|
Normalize the input NumPy image array of shape (C, H, W) with the given mean and standard deviation. |
|
Pad the input PIL image according to padding parameters. |
|
Apply Random affine transformation to the input PIL image. |
|
Adjust the color of the input PIL image by a random degree. |
|
Perform a random brightness, contrast, saturation, and hue adjustment on the input PIL image. |
|
Crop the input PIL image at a random location. |
|
Erase the pixels, within a selected rectangle region, to the given value. |
|
Randomly convert the input image into grayscale image with a given probability. |
|
Randomly flip the input image horizontally with a given probability. |
|
Randomly apply perspective transformation to the input PIL image with a given probability. |
|
Extract crop from the input image and resize it to a random size and aspect ratio. |
|
Rotate the input PIL image by a random angle. |
|
Adjust the sharpness of the input PIL image by a random degree. |
|
Randomly flip the input image vertically with a given probability. |
|
Resize the input PIL image to the given size. |
|
Convert a NumPy RGB image or a batch of NumPy RGB images to HSV images. |
|
Generate 10 cropped images (first 5 images from FiveCrop, second 5 images from their flipped version as per input flag to flip vertically or horizontally). |
|
Convert the input decoded NumPy image array of RGB mode to a PIL image of RGB mode. |
|
Convert the input NumPy image array or PIL image of shape (H, W, C) to a NumPy ndarray of shape (C, H, W). |
|
Convert the input NumPy image array to desired NumPy dtype. |
|
Uniformly select and apply a number of transforms sequentially from a list of transforms. |