dacapo.experiments.architectures.cnnectome_unet_config
======================================================

.. py:module:: dacapo.experiments.architectures.cnnectome_unet_config


Classes
-------

.. autoapisummary::

   dacapo.experiments.architectures.cnnectome_unet_config.CNNectomeUNetConfig


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

.. py:class:: CNNectomeUNetConfig



   This class configures the CNNectomeUNet based on
   https://github.com/saalfeldlab/CNNectome/blob/master/CNNectome/networks/unet_class.py

   Includes support for super resolution via the upsampling factors.

   .. attribute:: input_shape

      Coordinate
      The shape of the data passed into the network during training.

   .. attribute:: fmaps_out

      int
      The number of channels produced by your architecture.

   .. attribute:: fmaps_in

      int
      The number of channels expected from the raw data.

   .. attribute:: num_fmaps

      int
      The number of feature maps in the top level of the UNet.

   .. attribute:: fmap_inc_factor

      int
      The multiplication factor for the number of feature maps for each level of the UNet.

   .. attribute:: downsample_factors

      List[Coordinate]
      The factors to downsample the feature maps along each axis per layer.

   .. attribute:: kernel_size_down

      Optional[List[Coordinate]]
      The size of the convolutional kernels used before downsampling in each layer.

   .. attribute:: kernel_size_up

      Optional[List[Coordinate]]
      The size of the convolutional kernels used before upsampling in each layer.

   .. attribute:: _eval_shape_increase

      Optional[Coordinate]
      The amount by which to increase the input size when just prediction rather than training.
      It is generally possible to significantly increase the input size since we don't have the memory
      constraints of the gradients, the optimizer and the batch size.

   .. attribute:: upsample_factors

      Optional[List[Coordinate]]
      The amount by which to upsample the output of the UNet.

   .. attribute:: constant_upsample

      bool
      Whether to use a transpose convolution or simply copy voxels to upsample.

   .. attribute:: padding

      str
      The padding to use in convolution operations.

   .. attribute:: use_attention

      bool
      Whether to use attention blocks in the UNet. This is supported for 2D and  3D.

   .. method:: architecture_type()

      
      Returns the architecture type.

   .. note:: The architecture_type attribute is set to CNNectomeUNet.

   .. rubric:: References

   Saalfeld, S., Fetter, R., Cardona, A., & Tomancak, P. (2012).


   .. py:attribute:: architecture_type


   .. py:attribute:: input_shape
      :type:  funlib.geometry.Coordinate


   .. py:attribute:: fmaps_out
      :type:  int


   .. py:attribute:: fmaps_in
      :type:  int


   .. py:attribute:: num_fmaps
      :type:  int


   .. py:attribute:: fmap_inc_factor
      :type:  int


   .. py:attribute:: downsample_factors
      :type:  List[funlib.geometry.Coordinate]


   .. py:attribute:: kernel_size_down
      :type:  Optional[List[List[funlib.geometry.Coordinate]]]


   .. py:attribute:: kernel_size_up
      :type:  Optional[List[List[funlib.geometry.Coordinate]]]


   .. py:attribute:: upsample_factors
      :type:  Optional[List[funlib.geometry.Coordinate]]


   .. py:attribute:: constant_upsample
      :type:  bool


   .. py:attribute:: padding
      :type:  str


   .. py:attribute:: use_attention
      :type:  bool


   .. py:attribute:: batch_norm
      :type:  bool