ivy.rnn(step_function, inputs, initial_states, /, *, go_backwards=False, mask=None, constants=None, unroll=False, input_length=None, time_major=False, zero_output_for_mask=False, return_all_outputs=True)[source]#

Iterate over the time dimension of a tensor.

  • step_function (Callable) – RNN step function.

  • inputs (Array) – Array of temporal data of shape (samples, time, …).

  • initial_states (List[Array]) – Array with shape (samples, state_size).

  • go_backwards (bool, default: False) – If True, do the iteration over the time dimension in reverse order and return the reversed sequence.

  • mask (Optional[Array], default: None) – Binary array with shape (samples, time, 1), with a zero for every element that is masked.

  • constants (Optional[Array], default: None) – List of constant values passed at each step.

  • unroll (bool, default: False) – Whether to use a pythonic while loop or ivy.while_loop

  • input_length (Optional[int], default: None) – An integer or 1-D array, depending on whether the time dimension is fixed-length. In case of variable length input, it is used for masking in case there is no mask specified.

  • time_major (bool, default: False) – If True, the inputs and outputs will be in shape (timesteps, batch, …) whereas in the False case, it will be (batch, timesteps, …).

  • zero_output_for_mask (bool, default: False) – If True, the otput for masked timestep will be zeros, whereas in the False case, output from previous timestep is returned

  • return_all_outputs (bool, default: True) – If True, return the recurrent outputs for all timesteps in the sequence. If False, only return the output for the last timestep.


  • ret – A tuple of - the latest output of the rnn of shape (samples, …) - the output of the rnn of shape (samples, time, …) if

    return_all_outputs=True else (samples, 1, …)

    • list of tensors, latest states returned by the step funciton, of shape (samples, …)

  • Both the description and the type hints above assumes an array input for simplicity,

  • but this function is nestable, and therefore also accepts ivy.Container

  • instances in place of any of the arguments.