diffusion_models.gaussian_diffusion.base_diffuser
=================================================

.. py:module:: diffusion_models.gaussian_diffusion.base_diffuser




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

.. py:class:: BaseDiffuser(beta_scheduler)



   Initializes the object with the specified beta scheduler.

   BaseDiffuser is an abstract base class for different diffuser
   implementations. It defines the interface that all diffusers should adhere
   to.

   :param beta_scheduler: The beta scheduler used by the diffuser.

   .. warning::

      Do not instantiate this class directly. Instead, build your own Diffuser
      by inheriting from BaseDiffuser.
      (see :class:`~.gaussian_diffuser.GaussianDiffuser`)


   .. py:attribute:: beta_scheduler
      :type:  diffusion_models.gaussian_diffusion.beta_schedulers.BaseBetaScheduler

      The beta scheduler used by the diffuser.


   .. py:property:: steps
      :type: List[int]

      :abstractmethod:


      Returns the list of steps used in the denoising process.


   .. py:method:: get_timestep(number_of_images, idx)
      :abstractmethod:


      Get timestep information used for denoising.



   .. py:method:: diffuse_batch(images)
      :abstractmethod:


      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_batch(images, model)
      :abstractmethod:


      Denoise a batch of images.

      :param images: A tensor containing a batch of images to denoise.
      :param model: The model to be used for denoising.

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



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


      Moves the data to the specified device.

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

      :param device: The device to which the method should move the data.
                     It should be a string indicating the desired device.
                     Default is "cpu".