phitodeep.optimization.initialization
=====================================

.. py:module:: phitodeep.optimization.initialization


Classes
-------

.. autoapisummary::

   phitodeep.optimization.initialization.InitType
   phitodeep.optimization.initialization.Initializer
   phitodeep.optimization.initialization.Xavier
   phitodeep.optimization.initialization.He


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

.. py:class:: InitType(*args, **kwds)

   Bases: :py:obj:`enum.Enum`


   Create a collection of name/value pairs.

   Example enumeration:

   >>> class Color(Enum):
   ...     RED = 1
   ...     BLUE = 2
   ...     GREEN = 3

   Access them by:

   - attribute access:

     >>> Color.RED
     <Color.RED: 1>

   - value lookup:

     >>> Color(1)
     <Color.RED: 1>

   - name lookup:

     >>> Color['RED']
     <Color.RED: 1>

   Enumerations can be iterated over, and know how many members they have:

   >>> len(Color)
   3

   >>> list(Color)
   [<Color.RED: 1>, <Color.BLUE: 2>, <Color.GREEN: 3>]

   Methods can be added to enumerations, and members can have their own
   attributes -- see the documentation for details.


   .. py:attribute:: NORMAL
      :value: 1



   .. py:attribute:: UNIFORM
      :value: 2



.. py:class:: Initializer(name: str = 'Base', init_type: InitType = InitType.NORMAL)

   .. py:attribute:: name
      :value: 'Base'



   .. py:attribute:: init_type


   .. py:method:: get_scale(weights: numpy.ndarray) -> float
      :abstractmethod:



.. py:class:: Xavier(init_type: InitType = InitType.NORMAL)

   Bases: :py:obj:`Initializer`


   .. py:method:: get_scale(weights: numpy.ndarray) -> float


.. py:class:: He(init_type: InitType = InitType.NORMAL)

   Bases: :py:obj:`Initializer`


   .. py:method:: get_scale(weights: numpy.ndarray) -> float