ksuit.models.model_base
=======================

.. py:module:: ksuit.models.model_base


Classes
-------

.. autoapisummary::

   ksuit.models.model_base.ModelBase


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

.. py:class:: ModelBase(model_config, update_counter = None, path_provider = None, data_container = None, initializer_config = None, static_context = None)

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


   Base class for all neural network modules.

   Your models should also subclass this class.

   Modules can also contain other Modules, allowing to nest them in
   a tree structure. You can assign the submodules as regular attributes::

       import torch.nn as nn
       import torch.nn.functional as F

       class Model(nn.Module):
           def __init__(self):
               super().__init__()
               self.conv1 = nn.Conv2d(1, 20, 5)
               self.conv2 = nn.Conv2d(20, 20, 5)

           def forward(self, x):
               x = F.relu(self.conv1(x))
               return F.relu(self.conv2(x))

   Submodules assigned in this way will be registered, and will have their
   parameters converted too when you call :meth:`to`, etc.

   .. note::
       As per the example above, an ``__init__()`` call to the parent class
       must be made before assignment on the child.

   :ivar training: Boolean represents whether this module is in training or
                   evaluation mode.
   :vartype training: bool

   Base class for ksuit models that is used to define the interface for all models trainable by ksuit trainers.

   Provides methods to initialize the model weights and setup (model-specific) optimizers.

   :param model_config: Model configuration.
   :param update_counter: The update counter provided to the optimizer.
   :param path_provider: A path provider used by the initializer to store or retrieve checkpoints.
   :param data_container: The data container which includes the data and dataloader.
                          This is currently unused but helpful for quick prototyping only, evaluating forward in debug mode, etc.
   :param initializer_config: The initializer config used to initialize the model e.g. from a checkpoint.
   :param static_context: The static context used to pass information between submodules, e.g. patch_size, latent_dim.


   .. py:attribute:: logger


   .. py:attribute:: name


   .. py:attribute:: update_counter
      :value: None



   .. py:attribute:: path_provider
      :value: None



   .. py:attribute:: data_container
      :value: None



   .. py:attribute:: initializers
      :type:  list[ksuit.initializers.InitializerBase]
      :value: []



   .. py:attribute:: static_context


   .. py:attribute:: model_config


   .. py:attribute:: is_initialized
      :value: False



   .. py:property:: optimizer
      :type: ksuit.optimizer.OptimizerWrapper | None



   .. py:property:: device
      :type: torch.device

      :abstractmethod:



   .. py:property:: is_frozen
      :type: bool

      :abstractmethod:



   .. py:property:: param_count
      :type: int



   .. py:property:: trainable_param_count
      :type: int



   .. py:property:: frozen_param_count
      :type: int



   .. py:property:: nograd_paramnames
      :type: list[str]



   .. py:method:: initialize()

      Initializes weights and optimizer parameters of the model.



   .. py:method:: get_named_models()
      :abstractmethod:


      Returns a dict of {model_name: model}, e.g., to log all learning rates of all models/submodels.



   .. py:method:: initialize_weights()
      :abstractmethod:


      Initialize the weights of the model.



   .. py:method:: apply_initializers()
      :abstractmethod:


      Apply the initializers to the model.



   .. py:method:: initialize_optimizer()
      :abstractmethod:


      Initialize the optimizer of the model.



   .. py:method:: optimizer_step(grad_scaler)
      :abstractmethod:


      Perform an optimization step.



   .. py:method:: optimizer_schedule_step()
      :abstractmethod:


      Perform the optimizer learning rate scheduler step.



   .. py:method:: optimizer_zero_grad(set_to_none = True)
      :abstractmethod:


      Zero the gradients of the optimizer.