:py:mod:`kosmos.ml.config.factories.model`
==========================================

.. py:module:: kosmos.ml.config.factories.model







Classes
-------

.. py:class:: ModelConfig

   Bases: :py:class:`abc.ABC`

   Model configuration.





   |

   .. rubric:: Methods

   .. py:method:: get_instance(input_dim: int, output_dim: int) -> kosmos.ml.models.model.Model

      Get the model instance.

      :param input_dim: Model input dimension.
      :type input_dim: int
      :param output_dim: Model output dimension.
      :type output_dim: int

      :returns: Model instance.
      :rtype: Model




----

.. py:class:: NeuralNetworkConfig(hidden_layers: list[int])

   Bases: :py:class:`ModelConfig`

   Neural network configuration.

   Initialize the neural network configuration.

   :param hidden_layers: Sizes of the hidden layers. The length of the list defines
                         the number of hidden layers, and each element specifies the
                         size of a layer.
   :type hidden_layers: list[int]





   |

   .. rubric:: Methods

   .. py:method:: get_instance(input_dim: int, output_dim: int) -> kosmos.ml.models.neural_network.NeuralNetwork

      Get the neural network instance.

      :param input_dim: Model input dimension.
      :type input_dim: int
      :param output_dim: Model output dimension.
      :type output_dim: int

      :returns: Neural network instance.
      :rtype: NeuralNetwork




----

.. py:class:: VQCConfig(num_layers: int, encoding_config: kosmos.ml.config.factories.encoding.EncodingConfig, weight_mapping_func: kosmos.ml.typing.TensorMapping | None = None, input_mapping_func: kosmos.ml.typing.TensorMapping | None = None, weight_init_range: tuple[float, float] = (-1.0, 1.0), bias_init_range: tuple[float, float] | None = (-0.001, 0.001), *, data_reuploading: bool = False, output_scaling: bool = False)

   Bases: :py:class:`ModelConfig`

   Variational quantum circuit configuration.

   Initialize the VQC configuration.

   :param num_layers: The number of variational layers.
   :type num_layers: int
   :param encoding_config: The encoding configuration.
   :type encoding_config: EncodingConfig
   :param weight_mapping_func: The mapping function for the weights.
                               Defaults to None.
   :type weight_mapping_func: TensorMapping | None
   :param input_mapping_func: The mapping function for the input.
                              Defaults to None.
   :type input_mapping_func: TensorMapping | None
   :param weight_init_range: Lower and upper bounds for initializing the
                             trainable weight parameters. Defaults to (-1.0, 1.0).
   :type weight_init_range: tuple[float, float]
   :param bias_init_range: Lower and upper bounds for initializing
                           the trainable bias parameters applied to each output unit. If None, no bias
                           parameters are used. Defaults to (-0.001, 0.001).
   :type bias_init_range: tuple[float, float] | None
   :param data_reuploading: Whether to use data re-uploading. Defaults to False.
   :type data_reuploading: bool
   :param output_scaling: Whether to use output scaling. Defaults to False.
   :type output_scaling: bool





   |

   .. rubric:: Methods

   .. py:method:: get_instance(input_dim: int, output_dim: int) -> kosmos.ml.models.vqc.vqc.VQC

      Get the VQC instance.

      :param input_dim: Model input dimension.
      :type input_dim: int
      :param output_dim: Model output dimension.
      :type output_dim: int

      :returns: VQC instance.
      :rtype: VQC