mindspore.dataset.vision.RandomAutoContrast
- class mindspore.dataset.vision.RandomAutoContrast(cutoff=0.0, ignore=None, prob=0.5)[源代码]
Automatically adjust the contrast of the image with a given probability.
- Parameters
cutoff (float, optional) – Percent of the lightest and darkest pixels to be cut off from the histogram of the input image. The value must be in range of [0.0, 50.0) (default=0.0).
ignore (Union[int, sequence], optional) – The background pixel values to be ignored, each of which must be in range of [0, 255] (default=None).
prob (float, optional) – Probability of the image being automatically contrasted, which must be in range of [0, 1] (default=0.5).
- Raises
TypeError – If cutoff is not of type float.
TypeError – If ignore is not of type integer or sequence of integer.
TypeError – If prob is not of type float.
ValueError – If cutoff is not in range [0.0, 50.0).
ValueError – If ignore is not in range [0, 255].
ValueError – If prob is not in range [0, 1].
RuntimeError – If given tensor shape is not <H, W> or <H, W, C>.
- Supported Platforms:
CPU
Examples
>>> transforms_list = [vision.Decode(), vision.RandomAutoContrast(cutoff=0.0, ignore=None, prob=0.5)] >>> image_folder_dataset = image_folder_dataset.map(operations=transforms_list, ... input_columns=["image"])