emmi.modules.layers.linear_projection
=====================================

.. py:module:: emmi.modules.layers.linear_projection


Classes
-------

.. autoapisummary::

   emmi.modules.layers.linear_projection.LinearProjection


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

.. py:class:: LinearProjection(config)

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


   LinearProjection is a linear projection layer that can be used for 1D, 2D, and 3D data.

   Initialize the LinearProjection.

   :param input_dim: Input dimension of the linear projection.
   :param output_dim: Output dimension of the linear projection.
   :param ndim: Number of dimensions of the input domain. Either None (Linear projection),  1D (sequence), 2D, or 3D. Defaults to None.
   :param bias: If true, use bias term in the linear projection. Defaults to True.
   :param optional: If true and input_dim==output_dim (i.e., there is no up/down projection), then the identity mapping is used. Defaults to False.
   :param init_weights: Initialization method of the weights of the MLP. Options are  "torch" (i.e., similar to the
                        module) or "truncnormal002". Defaults to "truncnormal002". Defaults to "torch".

   :raises NotImplementedError: raises not implemented error if the number of dimensions of the input domain is bigger than 4.


   .. py:attribute:: project
      :type:  torch.nn.Module


   .. py:attribute:: init_weights


   .. py:method:: reset_parameters()

      Reset the parameters of the MLP with a specific initialization. Options are "torch" (i.e., default) or
          "truncnormal002".

      :raises NotImplementedError: raised if the specified initialization is not implemented.



   .. py:method:: forward(x)

      Forward function of the LinearProjection.

      :param x: Input tensor to the LinearProjection.

      :returns: Output tensor from the LinearProjection.