refiner
=======

.. py:module:: refiner


Attributes
----------

.. autoapisummary::

   refiner.plugin_name


Classes
-------

.. autoapisummary::

   refiner.MyPlugin


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

.. py:data:: plugin_name
   :value: 'refiner'


.. py:class:: MyPlugin



   A Python based gstreamer plugin template. Enables the user to:
   - Accept incoming buffers from dynamic pads
   - Define any custom plugin runtime logic
   User has to only override the run() function


   .. py:attribute:: mla


   .. py:attribute:: fmap1_shape
      :value: [1, 80, 192, 256]



   .. py:attribute:: fmap2_shape
      :value: [1, 80, 192, 256]



   .. py:attribute:: netlist0_shape
      :value: [1, 80, 192, 128]



   .. py:attribute:: netlist1_shape
      :value: [1, 40, 96, 128]



   .. py:attribute:: netlist2_shape
      :value: [1, 20, 48, 128]



   .. py:attribute:: inp_list0_shape
      :value: [1, 80, 192, 384]



   .. py:attribute:: inp_list1_shape
      :value: [1, 40, 96, 384]



   .. py:attribute:: inp_list2_shape
      :value: [1, 20, 48, 384]



   .. py:attribute:: coords0_shape
      :value: [1, 80, 192, 2]



   .. py:attribute:: coords1_shape
      :value: [1, 80, 192, 2]



   .. py:attribute:: flowup_shape
      :value: [1, 80, 192, 1]



   .. py:attribute:: upmask_shape
      :value: [1, 80, 192, 144]



   .. py:attribute:: coords0_shape_aligned
      :value: [1, 80, 192, 8]



   .. py:attribute:: coords1_shape_aligned
      :value: [1, 80, 192, 8]



   .. py:attribute:: flowup_shape_aligned
      :value: [1, 80, 192, 8]



   .. py:attribute:: fmap1


   .. py:attribute:: fmap2


   .. py:attribute:: net_list_0


   .. py:attribute:: net_list_1


   .. py:attribute:: net_list_2


   .. py:attribute:: inp_list_0


   .. py:attribute:: inp_list_1


   .. py:attribute:: inp_list_2


   .. py:attribute:: coords0


   .. py:attribute:: coords1


   .. py:attribute:: unpack_shapes


   .. py:method:: run(input_buffers: List[python_plugin_template.SimaaiPythonBuffer], output_buffer: bytes) -> None

      Define your plugin logic HERE
      Inputs:
      input_buffers List[SimaaiPythonBuffer]: List of input buffers
      Object of class SimaaiPythonBuffer has three fields:
      1. metadata MetaStruct Refer to the structure above
      2. data bytes - raw bytes of the incoming buffer
      3. size int - size of incoming buffer in bytes



   .. py:method:: unpack_buffer(single_buffer)


   .. py:method:: preprocess(l_image, r_image)


   .. py:method:: run_model(fmap1, fmap2, net_list_0, net_list_1, net_list_2, inp_list_0, inp_list_1, inp_list_2, coords0, coords1, iter)


   .. py:method:: preprocess_data_refiner(tensor)