fastdev.datasets.s3dis
======================

.. py:module:: fastdev.datasets.s3dis








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

.. py:data:: logger

.. py:function:: collect_point_label(anno_path, out_filename, class_names_path, file_format='txt')

   Convert original dataset files to data_label file (each line is XYZRGBL).
       We aggregated all the points from each instance in the room.

   :param anno_path: path to annotations. e.g. Area_1/office_2/Annotations/
   :param out_filename: path to save collected points and labels (each line is XYZRGBL)
   :param file_format: txt or numpy, determines what file format to save.

   :returns: None

   .. note:: the points are shifted before save, the most negative point is now at origin.


.. py:function:: sample_points(points: numpy.ndarray, labels: numpy.ndarray, room_coord_max: numpy.ndarray, num_points: int = 4096, block_size: float = 1.0)

.. py:class:: S3DISDatasetConfig

   Configuration for S3DISDataset.


   .. py:attribute:: data_root
      :type:  str


   .. py:attribute:: download_if_not_exist
      :type:  bool
      :value: False



   .. py:attribute:: num_points
      :type:  int
      :value: 4096



   .. py:attribute:: test_area
      :type:  int
      :value: 5



   .. py:attribute:: block_size
      :type:  float
      :value: 1.0



   .. py:attribute:: sample_rate
      :type:  float
      :value: 1.0



.. py:class:: S3DISDataset(config: S3DISDatasetConfig, split: Literal['train', 'test'] = 'train')

   Bases: :py:obj:`torch.utils.data.Dataset`


   S3DIS dataset.


   .. py:attribute:: config


   .. py:attribute:: num_points


   .. py:attribute:: block_size


   .. py:attribute:: labelweights


   .. py:attribute:: room_idxs


   .. py:method:: __getitem__(idx)


   .. py:method:: __len__()


   .. py:method:: download_data(data_root: str)
      :staticmethod: