.. _Kaolin Library: https://github.com/NVIDIAGameWorks/kaolin
.. _timelapse: https://kaolin.readthedocs.io/en/latest/modules/kaolin.visualize.html#kaolin.visualize.Timelapse

.. _kaolin_training-visualizer:

==================================
Training Visualizer
==================================

.. raw:: html

    <div style="width: 100%;display: inline-block;position: relative;">
        <div id="dummy" style="margin-top: 56%;">
        </div>
        <div align="center">
        <div id="kaltura_player_1" style="position:absolute;top:0;left:0;left: 0;right: 0;bottom:0;border:solid thin black;"></div>
        <script type="text/javascript" src="https://cdnapisec.kaltura.com/p/2935771/embedPlaykitJs/uiconf_id/46302491"></script>
        <script type="text/javascript">
            try {
            var kalturaPlayer = KalturaPlayer.setup({
            targetId: "kaltura_player_1",
            provider:
            { partnerId: 2935771, uiConfId: 46302491 }
            });
            kalturaPlayer.loadMedia(
            {entryId: '1_3mbng44u'}
            );
            } catch (e)
            { console.error(e.message) }
        </script>
        </div>
    </div>

The Omniverse Kaolin Training Visualizer extension allows interactive visualization of 3D checkpoints exported using `Kaolin Library`_. By scrubbing through iterations, one can see the progression of training over time, and visualize multiple textures and labels that may be predicted for each 3D model. The 3D checkpoints can include meshes, point clouds and voxel grids in any number of categories, with multiple textures and labels supported for meshes. The extension also allows creating and saving custom layouts for visualizing results consistently across experiments.

Interface
#########

.. image:: /content/images/kaolin_training-visualizer_ui.jpg

========== ================================== ====================================================================
Ref #      Option                             Result
========== ================================== ====================================================================
1          Training Directory                 | Loads checkpoints produced with the `Kaolin Library`_'s `timelapse`_ feature from the selected directory. 
2          Iteration                          | Sets scene to selected iteration number.
3          Saved Layouts                      | Load a previously saved layout.
4          Save Current Layout                | Save the current layout. Saves the loaded categories and all applied transformations.
5          Select Categories                  | Loads the selected categories onto the scene.
6          Grid Spacing Factor                | Reduces/Increases the spacing between assets.
7          Rotate                             | Rotates assets, in degrees.
8          Texture Mode                       | Selects from saved checkpoint textures.
9          Demo                               | Opens a browser window to this documentation.
========== ================================== ====================================================================