Missed TensorFlow Dev Summit? Check out the video playlist. Watch recordings

tf.image.random_brightness

TensorFlow 1 version View source on GitHub

Adjust the brightness of images by a random factor.

tf.image.random_brightness(
    image, max_delta, seed=None
)

Used in the notebooks

Used in the tutorials

Equivalent to adjust_brightness() using a delta randomly picked in the interval [-max_delta, max_delta).

Args:

  • image: An image or images to adjust.
  • max_delta: float, must be non-negative.
  • seed: A Python integer. Used to create a random seed. See tf.compat.v1.set_random_seed for behavior.

Usage Example:

x = [[[1.0, 2.0, 3.0], 
      [4.0, 5.0, 6.0]], 
     [[7.0, 8.0, 9.0], 
      [10.0, 11.0, 12.0]]] 
tf.image.random_brightness(x, 0.2) 
<tf.Tensor: shape=(2, 2, 3), dtype=float32, numpy=...> 

Returns:

The brightness-adjusted image(s).

Raises:

  • ValueError: if max_delta is negative.