emmi_inference.models.pipelines.anchor_point_sampling_precollator
=================================================================

.. py:module:: emmi_inference.models.pipelines.anchor_point_sampling_precollator

.. autoapi-nested-parse::

   WARNING
   This file is a 1:1 duplicate from the ``tutorial`` folder.

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



Classes
-------

.. autoapisummary::

   emmi_inference.models.pipelines.anchor_point_sampling_precollator.AnchorPointSamplingPreCollator


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

.. py:class:: AnchorPointSamplingPreCollator(items, num_points, to_prefix_and_postfix, to_prefix_midfix_postfix, keep_queries = False, seed = None)

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


   Randomly subsamples points from a pointcloud.

   Initializes the point sampling precollator.

   :param items: Which pointcloud items should be subsampled (e.g., input_position, output_position, ...). If multiple
                 items are present, the subsampling will use identical indices for all items (e.g., to downsample
                 output_position and output_pressure with the same subsampling).
   :param num_points: Number of points to sample.
   :param seed: Random seed for deterministic sampling for evaluation. Default None (i.e., no seed). If not None,
                requires sample index to be present in batch.


   .. py:attribute:: items


   .. py:attribute:: num_points


   .. py:attribute:: keep_queries
      :value: False



   .. py:attribute:: to_prefix_and_postfix


   .. py:attribute:: to_prefix_midfix_postfix


   .. py:attribute:: seed
      :value: None