<br />

|---|
| [![](https://www.tensorflow.org/images/GitHub-Mark-32px.png) View source on GitHub](https://github.com/keras-team/keras/tree/v3.15.1/keras/src/random/random.py#L312-L345) |

Draw samples from a Beta distribution.

    tf.keras.random.beta(
        shape, alpha, beta, dtype=None, seed=None
    )

The values are drawn from a Beta distribution parametrized
by alpha and beta.

<br />

<br />

<br />

| ## Args ||
|---|---|
| `shape` | The shape of the random values to generate. |
| `alpha` | Float or an array of floats representing the first parameter alpha. Must be broadcastable with `beta` and `shape`. |
| `beta` | Float or an array of floats representing the second parameter beta. Must be broadcastable with `alpha` and `shape`. |
| `dtype` | Optional dtype of the tensor. Only floating point types are supported. If not specified, [`keras.config.floatx()`](https://www.tensorflow.org/api_docs/python/tf/keras/backend/floatx) is used, which defaults to `float32` unless you configured it otherwise (via [`keras.config.set_floatx(float_dtype)`](https://www.tensorflow.org/api_docs/python/tf/keras/backend/set_floatx)). |
| `seed` | Optional Python integer or instance of [`keras.random.SeedGenerator`](https://www.tensorflow.org/api_docs/python/tf/keras/random/SeedGenerator). By default, the `seed` argument is `None`, and an internal global [`keras.random.SeedGenerator`](https://www.tensorflow.org/api_docs/python/tf/keras/random/SeedGenerator) is used. The `seed` argument can be used to ensure deterministic (repeatable) random number generation. Note that passing an integer as the `seed` value will produce the same random values for each call. To generate different random values for repeated calls, an instance of [`keras.random.SeedGenerator`](https://www.tensorflow.org/api_docs/python/tf/keras/random/SeedGenerator) must be provided as the `seed` value. Remark concerning the JAX backend: When tracing functions with the JAX backend the global [`keras.random.SeedGenerator`](https://www.tensorflow.org/api_docs/python/tf/keras/random/SeedGenerator) is not supported. Therefore, during tracing the default value seed=None will produce an error, and a `seed` argument must be provided. |

<br />