tf.keras.preprocessing.image.array_to_img

TensorFlow 1 version View source on GitHub

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

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

Used in the notebooks

Used in the tutorials

Usage:

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

Arguments:

  • x: Input Numpy array.
  • data_format: Image data format, can be either "channels_first" or "channels_last". Defaults to None, in which case the global setting tf.keras.backend.image_data_format() is used (unless you changed it, it defaults to "channels_last").
  • scale: Whether to rescale image values to be within [0, 255]. Defaults to True.
  • dtype: Dtype to use. Default to None, in which case the global setting tf.keras.backend.floatx() is used (unless you changed it, it defaults to "float32")

Returns:

A PIL Image instance.

Raises:

  • ImportError: if PIL is not available.
  • ValueError: if invalid x or data_format is passed.