mindspore.dataset.vision.Grayscale

class mindspore.dataset.vision.Grayscale(num_output_channels=1)[source]

Convert the input PIL Image to grayscale.

Parameters

num_output_channels (int) – The number of channels desired for the output image, must be 1 or 3. If 3 is provided, the returned image will have 3 identical RGB channels. Default: 1.

Raises

  • TypeError – If num_output_channels is not of type integer.

  • ValueError – If num_output_channels is not 1 or 3.

Supported Platforms:

CPU

Examples

>>> import os
>>> import numpy as np
>>> from PIL import Image, ImageDraw
>>> import mindspore.dataset as ds
>>> import mindspore.dataset.vision as vision
>>> from mindspore.dataset.transforms import Compose
>>>
>>> # Use the transform in dataset pipeline mode
>>> class MyDataset:
...     def __init__(self):
...         self.data = []
...         img = Image.new("RGB", (300, 300), (255, 255, 255))
...         draw = ImageDraw.Draw(img)
...         draw.ellipse(((0, 0), (100, 100)), fill=(255, 0, 0), outline=(255, 0, 0), width=5)
...         img.save("./1.jpg")
...         data = np.fromfile("./1.jpg", np.uint8)
...         self.data.append(data)
...
...     def __getitem__(self, index):
...         return self.data[0]
...
...     def __len__(self):
...         return 5
>>>
>>> my_dataset = MyDataset()
>>> generator_dataset = ds.GeneratorDataset(my_dataset, column_names="image")
>>> transforms_list = Compose([vision.Decode(to_pil=True),
...                            vision.Grayscale(3),
...                            vision.ToTensor()])
>>> # apply the transform to dataset through map function
>>> generator_dataset = generator_dataset.map(operations=transforms_list, input_columns="image")
>>> for item in generator_dataset.create_dict_iterator(num_epochs=1, output_numpy=True):
...     print(item["image"].shape, item["image"].dtype)
...     break
(3, 300, 300) float32
>>> os.remove("./1.jpg")
>>>
>>> # Use the transform in eager mode
>>> img = Image.new("RGB", (300, 300), (255, 255, 255))
>>> draw = ImageDraw.Draw(img)
>>> draw.polygon([(50, 50), (150, 50), (100, 150)], fill=(0, 255, 0), outline=(0, 255, 0))
>>> img.save("./2.jpg")
>>> data = Image.open("./2.jpg")
>>> output = vision.Grayscale(3)(data)
>>> print(np.array(output).shape, np.array(output).dtype)
(300, 300, 3) uint8
>>> os.remove("./2.jpg")
Tutorial Examples: