TensorFlow 2.0 Beta is available Learn more

tfp.sts.sample_uniform_initial_state

Initialize from a uniform [-2, 2] distribution in unconstrained space.

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

Defined in python/sts/fitting.py.

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: Python integer to seed the random number generator.

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).