tf.image.random_saturation
Stay organized with collections
Save and categorize content based on your preferences.
Adjust the saturation of RGB images by a random factor.
tf.image.random_saturation(
image, lower, upper, seed=None
)
Equivalent to adjust_saturation()
but uses a saturation_factor
randomly
picked in the interval [lower, upper)
.
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_saturation(x, 5, 10)
<tf.Tensor: shape=(2, 2, 3), dtype=float32, numpy=
array([[[ 0. , 1.5, 3. ],
[ 0. , 3. , 6. ]],
[[ 0. , 4.5, 9. ],
[ 0. , 6. , 12. ]]], dtype=float32)>
For producing deterministic results given a seed
value, use
tf.image.stateless_random_saturation
. Unlike using the seed
param
with tf.image.random_*
ops, tf.image.stateless_random_*
ops guarantee 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
|
RGB image or images. The size of the last dimension must be 3.
|
lower
|
float. Lower bound for the random saturation factor.
|
upper
|
float. Upper bound for the random saturation factor.
|
seed
|
An operation-specific seed. It will be used in conjunction with the
graph-level seed to determine the real seeds that will be used in this
operation. Please see the documentation of set_random_seed for its
interaction with the graph-level random seed.
|
Returns |
Adjusted image(s), same shape and DType as image .
|
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 2024-01-23 UTC.
[null,null,["Last updated 2024-01-23 UTC."],[],[],null,["# tf.image.random_saturation\n\n\u003cbr /\u003e\n\n|------------------------------------------------------------------------------------------------------------------------------------------|\n| [View source on GitHub](https://github.com/tensorflow/tensorflow/blob/v2.15.0.post1/tensorflow/python/ops/image_ops_impl.py#L2998-L3047) |\n\nAdjust the saturation of RGB images by a random factor.\n\n#### View aliases\n\n\n**Compat aliases for migration**\n\nSee\n[Migration guide](https://www.tensorflow.org/guide/migrate) for\nmore details.\n\n[`tf.compat.v1.image.random_saturation`](https://www.tensorflow.org/api_docs/python/tf/image/random_saturation)\n\n\u003cbr /\u003e\n\n tf.image.random_saturation(\n image, lower, upper, seed=None\n )\n\nEquivalent to `adjust_saturation()` but uses a `saturation_factor` randomly\npicked in the interval `[lower, upper)`.\n\n#### Usage Example:\n\n x = [[[1.0, 2.0, 3.0],\n [4.0, 5.0, 6.0]],\n [[7.0, 8.0, 9.0],\n [10.0, 11.0, 12.0]]]\n tf.image.random_saturation(x, 5, 10)\n \u003ctf.Tensor: shape=(2, 2, 3), dtype=float32, numpy=\n array([[[ 0. , 1.5, 3. ],\n [ 0. , 3. , 6. ]],\n [[ 0. , 4.5, 9. ],\n [ 0. , 6. , 12. ]]], dtype=float32)\u003e\n\nFor producing deterministic results given a `seed` value, use\n[`tf.image.stateless_random_saturation`](../../tf/image/stateless_random_saturation). Unlike using the `seed` param\nwith `tf.image.random_*` ops, `tf.image.stateless_random_*` ops guarantee the\nsame results given the same seed independent of how many times the function is\ncalled, and independent of global seed settings (e.g. tf.random.set_seed).\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n| Args ---- ||\n|---------|-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|\n| `image` | RGB image or images. The size of the last dimension must be 3. |\n| `lower` | float. Lower bound for the random saturation factor. |\n| `upper` | float. Upper bound for the random saturation factor. |\n| `seed` | An operation-specific seed. It will be used in conjunction with the graph-level seed to determine the real seeds that will be used in this operation. Please see the documentation of set_random_seed for its interaction with the graph-level random seed. |\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n| Returns ------- ||\n|---|---|\n| Adjusted image(s), same shape and DType as `image`. ||\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n| Raises ------ ||\n|--------------|----------------------------------------|\n| `ValueError` | if `upper \u003c= lower` or if `lower \u003c 0`. |\n\n\u003cbr /\u003e"]]