tf.keras.utils.array_to_img

Converts a 3D NumPy array to a PIL Image instance.

Main aliases

tf.keras.preprocessing.image.array_to_img

tf.keras.utils.array_to_img(
    x, data_format=None, scale=True, dtype=None
)

Used in the tutorials
Image segmentation Semantic Segmentation with Model Garden Adversarial regularization for image classification

from PIL import Image
img = np.random.random(size=(100, 100, 3))
pil_img = keras.utils.array_to_img(img)

Args
`x`	Input data, in any form that can be converted to a NumPy array.
`data_format`	Image data format, can be either `"channels_first"` or `"channels_last"`. Defaults to `None`, in which case the global setting `keras.backend.image_data_format()` is used (unless you changed it, it defaults to `"channels_last"`).
`scale`	Whether to rescale the image such that minimum and maximum values are 0 and 255 respectively. Defaults to `True`.
`dtype`	Dtype to use. `None` means the global setting `keras.backend.floatx()` is used (unless you changed it, it defaults to `"float32"`). Defaults to `None`.

Returns
A PIL Image instance.

Except as otherwise noted, the content of this page is licensed under the Creative Commons Attribution 4.0 License, and code samples are licensed under the Apache 2.0 License. For details, see the Google Developers Site Policies. Java is a registered trademark of Oracle and/or its affiliates. Some content is licensed under the numpy license.

Last updated 2024-06-07 UTC.

Args