duo_ai.utils.model
==================

.. py:module:: duo_ai.utils.model


Functions
---------

.. autoapisummary::

   duo_ai.utils.model.orthogonal_init
   duo_ai.utils.model.xavier_uniform_init


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

.. py:function:: orthogonal_init(module, gain=nn.init.calculate_gain('relu'))

   Apply orthogonal initialization to a module's weights and zero to biases.

   :param module: The module to initialize (e.g., nn.Linear, nn.Conv2d).
   :type module: nn.Module
   :param gain: Scaling factor for the orthogonal initialization. Default is relu gain.
   :type gain: float, optional

   :returns: The initialized module.
   :rtype: nn.Module

   .. rubric:: Examples

   >>> layer = nn.Linear(10, 5)
   >>> orthogonal_init(layer)


.. py:function:: xavier_uniform_init(module, gain=1.0)

   Apply Xavier uniform initialization to a module's weights and zero to biases.

   :param module: The module to initialize (e.g., nn.Linear, nn.Conv2d).
   :type module: nn.Module
   :param gain: Scaling factor for the Xavier initialization. Default is 1.0.
   :type gain: float, optional

   :returns: The initialized module.
   :rtype: nn.Module

   .. rubric:: Examples

   >>> layer = nn.Linear(10, 5)
   >>> xavier_uniform_init(layer)