base_diffusion_model
====================

.. py:module:: base_diffusion_model




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

.. py:class:: BaseDiffusionModel(diffuser)



   Initializes the object with the specified diffuser.

   BaseDiffusionModel is an abstract base class for different diffusion models
   implementations. It defines the interface that all diffusion models should
   adhere to.

   :param diffuser: The diffuser to use for the diffusion model.

   .. warning::

      Do not instantiate this class directly. Instead, build your own diffusion
      model by inheriting from BaseDiffusionModel.
      (see :class:`~.SimpleUnet.SimpleUnet`)


   .. py:attribute:: diffuser
      :type:  diffusion_models.gaussian_diffusion.base_diffuser.BaseDiffuser

      A diffuser to be used by the diffusion model.


   .. py:method:: diffuse(images)

      Diffuse a batch of images.

      :param images: A tensor containing a batch of images.

      :returns:

                A tuple containing three tensors

                  - images: Diffused batch of images.
                  - noise: Noise added to the images.
                  - timesteps: Timesteps used for diffusion.



   .. py:method:: denoise(images)

      Denoise a batch of images.

      :param images: A tensor containing a batch of images to denoise.

      :returns: A list of tensors containing a batch of denoised images.



   .. py:method:: forward(x, timestep)
      :abstractmethod:


      Forward pass of the diffusion model.

      The forward pass of the diffusion model, predicting the noise at a single
      step.

      :param x: A batch of noisy images.
      :param timestep: The timesteps of each image in the batch.

      :returns: A tensor representing the noise predicted for each image.



   .. py:method:: to(device = 'cpu')

      Moves the model to the specified device.

      This performs a similar behaviour to the `to` method of PyTorch. moving the
      DiffusionModel and all related artifacts to the specified device.

      :param device: The device to which the method should move the object.
                     Default is "cpu".



   .. py:method:: compile(*args, **kwargs)

      Compiles the diffusion model.

      This performs a similar behaviour to the `compile` method of PyTorch.

      :returns: A compiled diffusion model.