pyepo.func.abcmodule
====================

.. py:module:: pyepo.func.abcmodule

.. autoapi-nested-parse::

   Abstract autograd optimization module



Attributes
----------

.. autoapisummary::

   pyepo.func.abcmodule.logger


Classes
-------

.. autoapisummary::

   pyepo.func.abcmodule.optModule


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

.. py:data:: logger

.. py:class:: optModule(optmodel: pyepo.model.opt.optModel, processes: int = 1, solve_ratio: float = 1.0, reduction: pyepo.func.runtime.Reduction = 'mean', dataset: pyepo.data.dataset.optDataset | None = None, require_solpool: bool = False, seed: int | None = None)

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


   An abstract module for differentiable optimization losses in end-to-end
   predict-then-optimize. It provides common functionality (multiprocessing,
   solution pooling, loss reduction) for all loss modules.


   .. py:attribute:: optmodel
      :type:  pyepo.model.opt.optModel


   .. py:attribute:: processes
      :type:  int


   .. py:attribute:: pool
      :type:  pathos.multiprocessing.ProcessingPool | None


   .. py:attribute:: solve_ratio
      :type:  float


   .. py:attribute:: reduction
      :type:  pyepo.func.runtime.Reduction


   .. py:attribute:: solpool
      :value: None



   .. py:method:: forward(*args: torch.Tensor) -> torch.Tensor
      :abstractmethod:


      Forward pass