popgym.baselines.models.indrnn
==============================

.. py:module:: popgym.baselines.models.indrnn


Classes
-------

.. autoapisummary::

   popgym.baselines.models.indrnn.IndRNN


Module Contents
---------------

.. py:class:: IndRNN(input_size, hidden_size, activation='relu', clamp=True, max_len=1024)

   Bases: :py:obj:`torch.nn.Module`


   .. py:attribute:: clamp
      :value: True



   .. py:attribute:: clamp_val
      :value: 1.0006771306930664



   .. py:attribute:: input0


   .. py:attribute:: weight0


   .. py:attribute:: bias0


   .. py:attribute:: input1


   .. py:attribute:: weight1


   .. py:attribute:: bias1


   .. py:attribute:: output


   .. py:method:: clamp_weights() -> None


   .. py:method:: forward(x: torch.Tensor, state: Optional[torch.Tensor] = None) -> Tuple[torch.Tensor, torch.Tensor]

      input:
          x: [B, T, F]
          state: [B, 2, F]
      output:
          y: [B, T, D]
          state: [B, 2, D]