<br />

|---|
| [![](https://www.tensorflow.org/images/GitHub-Mark-32px.png) View source on GitHub](https://github.com/tensorflow/probability/blob/v0.25.0/tensorflow_probability/python/sts/fitting.py#L36-L80) |

Initialize from a uniform \[-2, 2\] distribution in unconstrained space. (deprecated)

    tfp.sts.sample_uniform_initial_state(
        parameter, return_constrained=True, init_sample_shape=(), seed=None
    )

> [!WARNING]
> **Deprecated:** THIS FUNCTION IS DEPRECATED. It will be removed after 2022-03-01. Instructions for updating: Please use [`tf.random.stateless_uniform`](https://www.tensorflow.org/api_docs/python/tf/random/stateless_uniform) or similar.

<br />

<br />

<br />

| ## Args ||
|---|---|
| `parameter` | `sts.Parameter` named tuple instance. |
| `return_constrained` | if `True`, re-applies the constraining bijector to return initializations in the original domain. Otherwise, returns initializations in the unconstrained space. Default value: `True`. |
| `init_sample_shape` | `sample_shape` of the sampled initializations. Default value: `[]`. |
| `seed` | PRNG seed; see [`tfp.random.sanitize_seed`](https://www.tensorflow.org/probability/api_docs/python/tfp/random/sanitize_seed) for details. |

<br />

<br />

<br />

<br />

| ## Returns ||
|---|---|
| `uniform_initializer` | `Tensor` of shape `concat([init_sample_shape, parameter.prior.batch_shape, transformed_event_shape])`, where `transformed_event_shape` is `parameter.prior.event_shape`, if `return_constrained=True`, and otherwise it is `parameter.bijector.inverse_event_shape(parameteter.prior.event_shape)`. |

<br />