fastdev.datasets.modelnet
=========================

.. py:module:: fastdev.datasets.modelnet




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

.. py:class:: ModelNetDatasetConfig

   Configuration for ModelNetDataset.


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


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



   .. py:attribute:: preprocess_data
      :type:  bool
      :value: True



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



   .. py:attribute:: num_categories
      :type:  Literal[10, 40]
      :value: 40



   .. py:attribute:: num_points
      :type:  int
      :value: 1024



   .. py:attribute:: resample
      :type:  bool
      :value: True



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



   .. py:method:: __post_init__()


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

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


   ModelNet dataset.

   - By setting `download_if_not_exist=True`, the dataset will be downloaded from Hugging Face Hub.
   - The modelnet40 dataset has already been FPS sampled, no need to run FPS sampling again.



   .. py:attribute:: config


   .. py:method:: __len__()


   .. py:method:: __getitem__(index)


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