emmi_inference.datasets.shapenet
================================

.. py:module:: emmi_inference.datasets.shapenet

.. autoapi-nested-parse::

   WARNING
   This file is a 1:1 duplicate from the ``tutorial`` folder, except ``getitem_grid_pos`` was removed to enable direct
   indexing over the dataset.

   It is here to avoid installation of a tutorial as a package and keep it isolated.



Classes
-------

.. autoapisummary::

   emmi_inference.datasets.shapenet.ShapeNetCarStats
   emmi_inference.datasets.shapenet.ShapeNetCarDataset


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

.. py:class:: ShapeNetCarStats

   Normalization statistics for the ShapeNet Car dataset.
   These statistics are used to normalize the data during training and evaluation.


   .. py:attribute:: raw_pos_min
      :type:  tuple[float]


   .. py:attribute:: raw_pos_max
      :type:  tuple[float]
      :value: (6.0,)



   .. py:attribute:: raw_pos_surface_min
      :type:  tuple[float]


   .. py:attribute:: raw_pos_surface_max
      :type:  tuple[float]
      :value: (3,)



   .. py:attribute:: volume_pos_mean
      :type:  tuple[float, float, float]


   .. py:attribute:: volume_pos_std
      :type:  tuple[float, float, float]
      :value: (1.03378, 0.682603, 2.27282)



   .. py:attribute:: surface_pos_mean
      :type:  tuple[float, float, float]
      :value: (9.00692e-05, 0.60236, 0.0252252)



   .. py:attribute:: surface_pos_std
      :type:  tuple[float, float, float]
      :value: (0.649866, 0.378063, 1.35368)



   .. py:attribute:: surface_pressure_mean
      :type:  tuple[float]


   .. py:attribute:: surface_pressure_std
      :type:  tuple[float]
      :value: (48.6757,)



   .. py:attribute:: volume_velocity_mean
      :type:  tuple[float, float, float]


   .. py:attribute:: volume_velocity_std
      :type:  tuple[float, float, float]
      :value: (1.361689, 1.267649, 5.850353)



   .. py:attribute:: volume_sdf_mean
      :type:  tuple[float]
      :value: (0.374222,)



   .. py:attribute:: volume_sdf_std
      :type:  tuple[float]
      :value: (0.178948,)



.. py:class:: ShapeNetCarDataset(root, split, position_scale = None, grid_resolution = None, num_repeats = 1, **kwargs)

   Bases: :py:obj:`ksuit.data.Dataset`


   Dataset implementeation for ShapeNet Car. Currently, supports the following properties:
   - position of car surface points
   - pressure at the surface points
   - normals at the surface points
   - positions of surrounding volume of the car
   - velocity at the volume points
   - normals at the volume points, pointing towards the car body
   - SDF at the volume points, w.r.t. the car body
   - grid positions for GINO encoder

   :param root: root path of the dataset. Expects a "processed" subfolder with "run_1" folders in it which contain the
                data files (e.g., "point_cloud.pt").
   :param split: Which split to use.

   :param root: root of the preprocessed dataset on disk. Expects a "preprocessed" subfolder with "param0", "param1", ..., "param8" folders in it which contain the
                data files (e.g., "surface_points.pt").
   :param split: Which split to use. Can be "train" or "test".
   :param position_scale: _description_. Defaults to None.
   :param grid_resolution: For GINO, a pre-defined grid is needed; grid_resolution specifies the resolution of the grid. Defaults to None.
   :param num_repeats: Number of times to repeat the same dataset within a single epoch. This is mainly used during validation, to loop of the same datapoints to reduce variances. Defaults to 1.

   :raises NotImplementedError: When an unknown split is provided.
   :raises AssertionError: If the root path does not exist or is not a preprocessed folder.
   :raises AssertionError: If the number of uris does not match the expected number for the split


   .. py:attribute:: split


   .. py:attribute:: position_scale
      :value: None



   .. py:attribute:: grid_resolution
      :value: None



   .. py:attribute:: source_root


   .. py:attribute:: num_repeats
      :value: 1



   .. py:attribute:: grid_positions
      :value: None



   .. py:method:: get_normalization_stats()
      :staticmethod:


      Returns the normalization stats for the dataset. This is used in the collator to normalize the data.



   .. py:method:: getitem_surface_position(idx)

      Retrieves surface position (num_surface_points, 3)



   .. py:method:: getitem_surface_pressure(idx)

      Retrieves surface pressure (num_surface_points, 1)



   .. py:method:: getitem_surface_normals(idx)

      Retrieves surface normals (num_surface_points, 3)



   .. py:method:: getitem_volume_velocity(idx)

      Retrieves volume velocity (num_volume_points, 3)



   .. py:method:: getitem_volume_position(idx)

      Retrieves volume points (num_volume_points, 3)



   .. py:method:: getitem_volume_sdf(idx)

      Retrieves volume sdf w.r.t. the car body (num_volume_points, 1)



   .. py:method:: getitem_volume_normals(idx)

      Retrieves volume normals (num_volume_points, 3)