layers.linear_projection_config
===============================

.. py:module:: layers.linear_projection_config


Classes
-------

.. autoapisummary::

   layers.linear_projection_config.LinearProjectionConfig


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

.. py:class:: LinearProjectionConfig(/, **data)

   Bases: :py:obj:`pydantic.BaseModel`


   Configuration for a LinearProjection layer.

   Create a new model by parsing and validating input data from keyword arguments.

   Raises [`ValidationError`][pydantic_core.ValidationError] if the input data cannot be
   validated to form a valid model.

   `self` is explicitly positional-only to allow `self` as a field name.


   .. py:attribute:: input_dim
      :type:  int
      :value: None


      Input dimension of the linear projection.


   .. py:attribute:: output_dim
      :type:  int
      :value: None


      Output dimension of the linear projection.


   .. py:attribute:: ndim
      :type:  None | int
      :value: None


      Number of dimensions of the input domain. Either None (Linear projection),  1D (sequence), 2D, or 3D. Defaults to None.


   .. py:attribute:: bias
      :type:  bool
      :value: None


      If true, use bias term in the linear projection. Defaults to True.


   .. py:attribute:: optional
      :type:  bool
      :value: None


      If true and input_dim==output_dim (i.e., there is no up/down projection), then the identity mapping is used. Defaults to False.


   .. py:attribute:: init_weights
      :type:  emmi.types.InitWeightsMode
      :value: None


      Initialization method of the weights of the MLP. Options are  "torch" (i.e., similar to the module) or "truncnormal002", or "zero".Defaults to "torch".


   .. py:method:: validate_ndim()

      Validate the ndim field to ensure it is either None, 1, 2, or 3.