ksuit.models.single
===================

.. py:module:: ksuit.models.single


Classes
-------

.. autoapisummary::

   ksuit.models.single.Model


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

.. py:class:: Model(model_config, is_frozen = False, update_counter = None, path_provider = None, data_container = None, static_context = None)

   Bases: :py:obj:`ksuit.models.model_base.ModelBase`


   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 single models, i.e. one model with one optimizer as opposed to CompositeModel.

   :param model_config: Model configuration.
   :param is_frozen: If true, will set `requires_grad` of all parameters to false. Will also put the model into eval
                     mode (e.g., to put Dropout or BatchNorm into eval mode).
   :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 static_context: The static context used to pass information between submodules, e.g. patch_size, latent_dim.


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



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



   .. py:method:: get_named_models()

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



   .. py:method:: initialize_weights()

      Freezes the weights of the model by setting requires_grad to False if self.is_frozen is True.



   .. py:method:: apply_initializers()

      Apply the initializers to the model, calling initializer.init_weights and initializer.init_optim.



   .. py:method:: initialize_optimizer()

      Initialize the optimizer.



   .. py:method:: optimizer_step(grad_scaler)

      Perform an optimization step.



   .. py:method:: optimizer_schedule_step()

      Perform the optimizer learning rate scheduler step.



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

      Zero the gradients of the optimizer.



   .. py:method:: train(mode = True)

      Set the model to train or eval mode.

      Overwrites the nn.Module.train method to avoid setting the model to train mode if it is frozen.

      :param mode: If True, set the model to train mode. If False, set the model to eval mode.



   .. py:method:: to(device, *args, **kwargs)

      Performs Tensor dtype and/or device conversion, overwriting nn.Module.to method to set the _device attribute.

      :param device: The desired device of the tensor. Can be a string (e.g. "cuda:0") or "cpu".