ncalab.models.applications.growing
==================================

.. py:module:: ncalab.models.applications.growing


Submodules
----------

.. toctree::
   :maxdepth: 1

   /autoapi/ncalab/models/applications/growing/growingNCA/index


Classes
-------

.. autoapisummary::

   ncalab.models.applications.growing.GrowingNCAModel


Package Contents
----------------

.. py:class:: GrowingNCAModel(device: torch.device, num_image_channels: int = 4, num_hidden_channels: int = 16, fire_rate: float = 0.5, hidden_size: int = 128, use_alive_mask: bool = False, **kwargs)

   Bases: :py:obj:`ncalab.models.basicNCA.BasicNCAModel`


   NCA Model class for "growing" tasks, in which a structure is grown from a single seed pixel.

   This specialization of the BasicNCAModel has some interesting properties.
   For instance, it has no output channels, as the growing task directly
   manipulates the input image channels.

   :param device [torch.device]: Pytorch device descriptor.
   :param num_image_channels [int]: Number of channels reserved for input image. Defaults to 4.
   :param num_hidden_channels [int]: Number of hidden channels (communication channels). Defaults to 16.
   :param fire_rate [float]: Stochastic weight update. Defaults to 0.5.
   :param hidden_size [int]: Default number of nodes in hidden layer. Defaults to 128.
   :param use_alive_mask [bool]: Whether to use alive masking. Defaults to False.


   .. py:method:: loss(pred: ncalab.prediction.Prediction, label: torch.Tensor) -> Dict[str, torch.Tensor]

      Implements a simple MSE loss between target and prediction.

      :param pred: Prediction
      :param label: Target

      :returns [Tensor]: MSE Loss



   .. py:method:: validate(image: torch.Tensor, label: torch.Tensor, steps: Optional[int] = None) -> Optional[Tuple[Dict[str, float], ncalab.prediction.Prediction]]

      We typically don't validate during training of Growing NCA,
      because there is only a single sample in the training set.



   .. py:method:: make_seed(width: int, height: int) -> torch.Tensor


   .. py:method:: grow(seed: torch.Tensor, steps: int = 100) -> List[numpy.ndarray]

      Run the growth process and return the resulting output sequence.

      :param seed [torch.Tensor]: Seed image, can be generated through make_seed.
      :param steps [int]: Number of inference steps. Defaults to 100.

      :returns [List[np.ndarray]]: Sequence of output images.