dacapo.experiments.starts.cosem_start
=====================================

.. py:module:: dacapo.experiments.starts.cosem_start


Attributes
----------

.. autoapisummary::

   dacapo.experiments.starts.cosem_start.logger


Classes
-------

.. autoapisummary::

   dacapo.experiments.starts.cosem_start.CosemStart


Functions
---------

.. autoapisummary::

   dacapo.experiments.starts.cosem_start.get_model_setup


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

.. py:data:: logger

.. py:function:: get_model_setup(run)

   Loads the model setup from the dacapo store for the specified run. The
   model setup includes the classes_channels, voxel_size_input and
   voxel_size_output.

   :param run: str
               The run for which the model setup is to be loaded.

   :returns:

             list
                 The classes_channels of the model.
             voxel_size_input : list
                 The voxel_size_input of the model.
             voxel_size_output : list
                 The voxel_size_output of the model.
   :rtype: classes_channels

   :raises Exception: If the model setup cannot be loaded, an Exception is thrown which
       is logged and handled by training the model without head matching.

   .. rubric:: Examples

   >>> classes_channels, voxel_size_input, voxel_size_output = get_model_setup(run)

   .. rubric:: Notes

   This function is called by the CosemStart class to load the model setup
   from the dacapo store for the specified run.


.. py:class:: CosemStart(start_config)



   A class to represent the starting point for tasks. This class inherits
   from the Start class and is used to load the weights of the starter model
   used for finetuning. The weights are loaded from the dacapo store for the
   specified run and criterion.

   .. attribute:: run

      str
      The run to be used as a starting point for tasks.

   .. attribute:: criterion

      str
      The criterion to be used for choosing weights from run.

   .. attribute:: name

      str
      The name of the run and criterion.

   .. attribute:: channels

      list
      The classes_channels of the model.

   .. method:: __init__(start_config)

      
      Initializes the CosemStart class with specified config to run the
      initialization of weights for a model associated with a specific
      criterion.

   .. method:: check()

      
      Checks if the checkpoint for the specified run and criterion exists.

   .. method:: initialize_weights(model, new_head=None)

      
      Retrieves the weights from the dacapo store and load them into
      the model.

   .. rubric:: Notes

   This class is used to represent the starting point for tasks. The weights
   of the starter model used for finetuning are loaded from the dacapo store.


   .. py:attribute:: run


   .. py:attribute:: criterion


   .. py:attribute:: name


   .. py:attribute:: channels


   .. py:method:: check()

      Checks if the checkpoint for the specified run and criterion exists.

      :raises Exception: If the checkpoint does not exist, an Exception is thrown which
          is logged and handled by training the model without head matching.

      .. rubric:: Examples

      >>> check()

      .. rubric:: Notes

      This function is called by the CosemStart class to check if the
      checkpoint for the specified run and criterion exists.



   .. py:method:: initialize_weights(model, new_head=None)

      Retrieves the weights from the dacapo store and load them into
      the model.

      :param model: obj
                    The model to which the weights are to be loaded.
      :param new_head: list
                       The labels of the new head.

      :returns:

                obj
                    The model with the weights loaded from the dacapo store.
      :rtype: model

      :raises RuntimeError: If weights of a non-existing or mismatched layer are being
          loaded, a RuntimeError exception is thrown which is logged
          and handled by loading only the common layers from weights.

      .. rubric:: Examples

      >>> model = initialize_weights(model, new_head)

      .. rubric:: Notes

      This function is called by the CosemStart class to retrieve the weights
      from the dacapo store and load them into the model.