mindspore.dataset.vision.RandomColor

class mindspore.dataset.vision.RandomColor(degrees=(0.1, 1.9))

Adjust the color of the input image by a fixed or random degree. This operation works only with 3-channel color images.

Parameters

degrees (Sequence[float], optional) – Range of random color adjustment degrees, which must be non-negative. It should be in (min, max) format. If min=max, then it is a single fixed magnitude operation. Default: (0.1, 1.9).

Raises

• TypeError – If degrees is not of type Sequence[float].

• ValueError – If degrees is negative.

• RuntimeError – If given tensor shape is not <H, W, C>.

Supported Platforms:

CPU

Examples

>>> import mindspore.dataset as ds
>>> import mindspore.dataset.vision as vision
>>>
>>> image_folder_dataset = ds.ImageFolderDataset("/path/to/image_folder_dataset_directory")
>>> transforms_list = [vision.Decode(), vision.RandomColor((0.5, 2.0))]
>>> image_folder_dataset = image_folder_dataset.map(operations=transforms_list,
...                                                 input_columns=["image"])

Tutorial Examples:

• Illustration of vision transforms