tf.image.stateless_random_contrast

Adjust the contrast of images by a random factor deterministically.

tf.image.stateless_random_contrast(
    image, lower, upper, seed
)

Guarantees the same results given the same seed independent of how many times the function is called, and independent of global seed settings (e.g. tf.random.set_seed).

Args
`image`	An image tensor with 3 or more dimensions.
`lower`	float. Lower bound for the random contrast factor.
`upper`	float. Upper bound for the random contrast factor.
`seed`	A shape [2] Tensor, the seed to the random number generator. Must have dtype `int32` or `int64`. (When using XLA, only `int32` is allowed.)

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]]]
seed = (1, 2)
tf.image.stateless_random_contrast(x, 0.2, 0.5, seed)
<tf.Tensor: shape=(2, 2, 3), dtype=float32, numpy=
array([[[3.4605184, 4.4605184, 5.4605184],
        [4.820173 , 5.820173 , 6.820173 ]],
       [[6.179827 , 7.179827 , 8.179828 ],
        [7.5394816, 8.539482 , 9.539482 ]]], dtype=float32)>

Returns
The contrast-adjusted image(s).

Raises
`ValueError`	if `upper <= lower` or if `lower < 0`.

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 2021-08-16 UTC.

tf.image.stateless_random_contrast

Args

Usage Example:

Returns

Raises