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: [].
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).
[null,null,["Last updated 2023-11-21 UTC."],[],[],null,["# tfp.sts.sample_uniform_initial_state\n\n\u003cbr /\u003e\n\n|--------------------------------------------------------------------------------------------------------------------------------------|\n| [View source on GitHub](https://github.com/tensorflow/probability/blob/v0.23.0/tensorflow_probability/python/sts/fitting.py#L36-L80) |\n\nInitialize from a uniform \\[-2, 2\\] distribution in unconstrained space. (deprecated) \n\n tfp.sts.sample_uniform_initial_state(\n parameter, return_constrained=True, init_sample_shape=(), seed=None\n )\n\n| **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.\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n| Args ---- ||\n|----------------------|-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|\n| `parameter` | `sts.Parameter` named tuple instance. |\n| `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`. |\n| `init_sample_shape` | `sample_shape` of the sampled initializations. Default value: `[]`. |\n| `seed` | PRNG seed; see [`tfp.random.sanitize_seed`](../../tfp/random/sanitize_seed) for details. |\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n| Returns ------- ||\n|-----------------------|-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|\n| `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)`. |\n\n\u003cbr /\u003e"]]
View source on GitHub