mindspore.dataset.vision.py_transforms.RandomColor

class mindspore.dataset.vision.py_transforms.RandomColor(degrees=(0.1, 1.9))[source]

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

Parameters

degrees (Sequence[float, float]) – Range of color adjustment degree to select from, must be a Sequence of length 2, arranged in order of (min, max). A degree of 1.0 gives the original image, a degree of 0.0 gives a black and white image and higher degrees mean more brightness, contrast, etc. Default: (0.1, 1.9).

Raises

TypeError – If degrees is not of type Sequence[float, float].
ValueError – If degrees is negative.
RuntimeError – If shape of the input image is not <H, W, C>.

Supported Platforms:: CPU

Examples

>>> from mindspore.dataset.transforms.py_transforms import Compose
>>>
>>> transforms_list = Compose([py_vision.Decode(),
...                            py_vision.RandomColor((0.5, 2.0)),
...                            py_vision.ToTensor()])
>>> # apply the transform to dataset through map function
>>> image_folder_dataset = image_folder_dataset.map(operations=transforms_list,
...                                                 input_columns="image")