# tf.image.stateless_random_hue

<br />

|---|
| [![](https://www.tensorflow.org/images/GitHub-Mark-32px.png) View source on GitHub](https://github.com/tensorflow/tensorflow/blob/v2.13.1/tensorflow/python/ops/image_ops_impl.py#L2675-L2723) |

Adjust the hue of RGB images by a random factor deterministically.

    tf.image.stateless_random_hue(
        image, max_delta, seed
    )

Equivalent to `adjust_hue()` but uses a `delta` randomly picked in the
interval `[-max_delta, max_delta)`.

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`](https://www.tensorflow.org/versions/r2.13/api_docs/python/tf/random/set_seed)).

`max_delta` must be in the interval `[0, 0.5]`.

#### 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_hue(x, 0.2, seed)
    <tf.Tensor: shape=(2, 2, 3), dtype=float32, numpy=
    array([[[ 1.6514902,  1.       ,  3.       ],
            [ 4.65149  ,  4.       ,  6.       ]],
           [[ 7.65149  ,  7.       ,  9.       ],
            [10.65149  , 10.       , 12.       ]]], dtype=float32)>

<br />

<br />

<br />

| ## Args ||
|---|---|
| `image` | RGB image or images. The size of the last dimension must be 3. |
| `max_delta` | float. The maximum value for the random delta. |
| `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.) |

<br />

<br />

<br />

<br />

| ## Returns ||
|---|---|
| Adjusted image(s), same shape and DType as `image`. ||

<br />

<br />

<br />

<br />

| ## Raises ||
|---|---|
| `ValueError` | if `max_delta` is invalid. |

<br />