diffusion_models.gaussian_diffusion.ddimm_diffuser
==================================================

.. py:module:: diffusion_models.gaussian_diffusion.ddimm_diffuser




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

.. py:class:: DenoisingMode



   Initialize self.  See help(type(self)) for accurate signature.


   .. py:attribute:: Linear
      :value: 'linear'



   .. py:attribute:: Quadratic
      :value: 'quadratic'



.. py:class:: DdimDiffuser(beta_scheduler, mode = DenoisingMode.Quadratic, number_of_steps = 20)



   Initializes the class instance.

   :param beta_scheduler: The beta scheduler instance to be used.
   :type beta_scheduler: BaseBetaScheduler


   .. py:attribute:: number_of_steps

      Number of steps to use in the denoising process.


   .. py:attribute:: mode

      Linear or Quadratic sampling.


   .. py:attribute:: device
      :type:  str
      :value: 'cpu'


      The device to use. Defaults to cpu.


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


      Returns the list of steps used in the denoising process.


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

      Get timestep information used for denoising.



   .. py:method:: from_checkpoint(checkpoint)
      :classmethod:


      Instantiate a DDIM Diffuser from a training checkpoint.

      :param checkpoint: The training checkpoint object containing
                         the trained model's parameters and configuration.

      :returns: An instance of the DdimDiffuser class initialized with the parameters
                loaded from the given checkpoint.



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

      Moves the data to the specified device.

      This performs a similar behaviour to the `to` method of PyTorch. moving the
      GaussianDiffuser and the BetaScheduler to the specified device.

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

      .. rubric:: Example

      >>> ddim_diffuser = DdimDiffuser()
      >>> ddim_diffuser = ddim_diffuser.to(device="cuda")



   .. py:method:: diffuse_batch(images)

      Diffuse a batch of images.

      Diffuse the given batch of images by adding noise based on the beta scheduler.

      :param images: Batch of images to diffuse.

                     Shape should be ``(B, C, H, W)``.

      :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)

      Denoise a batch of images.

      This denoises a batch images. This is the image generation process.

      :param images: A batch of noisy images.
      :param model: The model to be used for denoising.

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