mindspore.dataset.vision.RandomPosterize

View Source On Gitee
class mindspore.dataset.vision.RandomPosterize(bits=(8, 8))[source]

Reduce the bit depth of the color channels of image with a given probability to create a high contrast and vivid color image.

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

Parameters

bits (Union[int, Sequence[int]], optional) – Range of random posterize to compress image. Bits values must be in range of [1,8], and include at least one integer value in the given range. It must be in (min, max) or integer format. If min=max, then it is a single fixed magnitude operation. Default: (8, 8).

Raises
  • TypeError – If bits is not of type integer or sequence of integer.

  • ValueError – If bits is not in range [1, 8].

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

Supported Platforms:

CPU

Examples

>>> import numpy as np
>>> import mindspore.dataset as ds
>>> import mindspore.dataset.vision as vision
>>>
>>> # Use the transform in dataset pipeline mode
>>> data = np.random.randint(0, 255, size=(1, 100, 100, 3)).astype(np.uint8)
>>> numpy_slices_dataset = ds.NumpySlicesDataset(data, ["image"])
>>> transforms_list = [vision.RandomPosterize((6, 8))]
>>> numpy_slices_dataset = numpy_slices_dataset.map(operations=transforms_list, input_columns=["image"])
>>> for item in numpy_slices_dataset.create_dict_iterator(num_epochs=1, output_numpy=True):
...     print(item["image"].shape, item["image"].dtype)
...     break
(100, 100, 3) uint8
>>>
>>> # Use the transform in eager mode
>>> data = np.random.randint(0, 255, size=(100, 100, 3)).astype(np.uint8)
>>> output = vision.RandomPosterize(1)(data)
>>> print(output.shape, output.dtype)
(100, 100, 3) uint8
Tutorial Examples: