model.shattered_gradients
=========================

.. py:module:: model.shattered_gradients


Attributes
----------

.. autoapisummary::

   model.shattered_gradients.weights


Classes
-------

.. autoapisummary::

   model.shattered_gradients.ShatteredGradientsNN


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

.. py:class:: ShatteredGradientsNN(weights: torch.Tensor, act_fun: str = 'Relu')

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


   Implements a neural network model using a linear layer followed by an activation function.

   This model is designed to exhibit shattered gradients. To generate a model that exhibits
   shattered gradients, use shattered_grad.py, located in datagenerator.

   Inherits from:
       torch.nn.Sequential: Parent class for implementing neural networks with modules defined in a
       sequential manner.

   Initializes a ShatteredGradientsNN object.

   :param weights: The weights to be applied to the linear layer.
   :type weights: torch.Tensor
   :param act_fun: The activation function to be used. Valid options are "Relu", "Gelu", or "Sigmoid".
                   Defaults to 'Relu'.
   :type act_fun: str


   .. py:method:: _default_activation_function(act_fun: str) -> torch.nn.Module

      Returns the default activation function based on the provided string.

      The `_default_activation_function` method maps the provided activation function name
      to the corresponding PyTorch activation function module. Supported activation functions
      include "Relu" (ReLU), "Gelu" (GELU), and "Sigmoid" (Sigmoid). If the provided name
      is not in the supported list, a KeyError is raised.

      :param act_fun: The activation function name or class.
      :type act_fun: str

      :returns: The corresponding PyTorch activation function module.
      :rtype: torch.nn.Module

      :raises KeyError: If the given activation function is not supported.



.. py:data:: weights