fastdev.nn.spconv_unet
======================

.. py:module:: fastdev.nn.spconv_unet

.. autoapi-nested-parse::

   SparseUNet Driven by SpConv.

   Adapted from: https://github.com/Pointcept/Pointcept

   This module requires the installation of the following packages:

   - spconv: https://github.com/traveller59/spconv?tab=readme-ov-file#spconv-spatially-sparse-convolution-library


   Original Author: Xiaoyang Wu (xiaoyang.wu.cs@gmail.com)
   Please cite their work if you use the following code in your research paper.





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

.. py:class:: SpUNetBase(in_channels: int, num_classes: int, base_channels=32, channels=(32, 64, 128, 256, 256, 128, 96, 96), layers=(2, 3, 4, 6, 2, 2, 2, 2), cls_mode=False)

   Bases: :py:obj:`torch.nn.Module`


   .. py:attribute:: in_channels


   .. py:attribute:: num_classes


   .. py:attribute:: base_channels
      :value: 32



   .. py:attribute:: channels
      :value: (32, 64, 128, 256, 256, 128, 96, 96)



   .. py:attribute:: layers
      :value: (2, 3, 4, 6, 2, 2, 2, 2)



   .. py:attribute:: num_stages


   .. py:attribute:: cls_mode
      :value: False



   .. py:attribute:: conv_input


   .. py:attribute:: down


   .. py:attribute:: up


   .. py:attribute:: enc


   .. py:attribute:: dec


   .. py:attribute:: final


   .. py:method:: forward(points: torch.Tensor)


.. py:class:: SpUNetCls(in_channels: int, num_classes: int, base_channels=32, channels=(32, 64, 128, 256, 256, 128, 96, 96), layers=(2, 3, 4, 6, 2, 2, 2, 2))

   Bases: :py:obj:`torch.nn.Module`


   .. py:attribute:: model


   .. py:method:: forward(points: torch.Tensor)


.. py:class:: SpUNetSeg(in_channels: int, num_classes: int, base_channels=32, channels=(32, 64, 128, 256, 256, 128, 96, 96), layers=(2, 3, 4, 6, 2, 2, 2, 2))

   Bases: :py:obj:`torch.nn.Module`


   .. py:attribute:: model


   .. py:method:: forward(points: torch.Tensor)