mindspore.dataset.vision.RandomLighting

class mindspore.dataset.vision.RandomLighting(alpha=0.05)

Add AlexNet-style PCA-based noise to an image. The eigenvalue and eigenvectors for Alexnet’s PCA noise is calculated from the imagenet dataset.

Parameters

alpha (float, optional) – Intensity of the image, which must be non-negative. Default: 0.05.

Raises

• TypeError – If alpha is not of type float.

• ValueError – If alpha is negative.

• RuntimeError – If given tensor shape is not <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.RandomLighting(0.1)]
>>> 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.RandomLighting(0.1)(data)
>>> print(output.shape, output.dtype)
(100, 100, 3) uint8

Tutorial Examples:

• Illustration of vision transforms