yolov7_postproc_overlay
=======================

.. py:module:: yolov7_postproc_overlay


Attributes
----------

.. autoapisummary::

   yolov7_postproc_overlay.plugin_name
   yolov7_postproc_overlay.CLASSNAMES
   yolov7_postproc_overlay.COLORS


Classes
-------

.. autoapisummary::

   yolov7_postproc_overlay.PostProcOpt
   yolov7_postproc_overlay.MyPlugin


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

.. py:data:: plugin_name
   :value: 'python_plugin'


.. py:data:: CLASSNAMES
   :value: ['person', 'bicycle', 'car', 'motorcycle', 'airplane', 'bus', 'train', 'truck', 'boat', 'traffic...


.. py:data:: COLORS

.. py:class:: PostProcOpt(plugin, confidence_thres, iou_thres)

   .. py:attribute:: plugin


   .. py:attribute:: confidence_thres


   .. py:attribute:: iou_thres


   .. py:attribute:: grid_cells


   .. py:attribute:: final_buffer


   .. py:method:: post_process_optimized(model_output)


.. 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:: MODEL_WIDTH
      :value: 640



   .. py:attribute:: MODEL_HEIGHT
      :value: 640



   .. py:attribute:: FRAME_WIDTH
      :value: 1280



   .. py:attribute:: FRAME_HEIGHT
      :value: 720



   .. py:attribute:: classes
      :value: 80



   .. py:attribute:: color_palette


   .. py:attribute:: confidence_thres
      :value: 0.25



   .. py:attribute:: iou_thres
      :value: 0.65



   .. py:attribute:: boxes
      :value: []



   .. py:attribute:: scores
      :value: []



   .. py:attribute:: class_ids
      :value: []



   .. py:attribute:: out_size
      :value: 0



   .. py:attribute:: frame_id
      :value: 0



   .. py:attribute:: model_outs
      :value: [(1, 80, 80, 6), (1, 80, 80, 6), (1, 80, 80, 243), (1, 40, 40, 6), (1, 40, 40, 6), (1, 40, 40,...



   .. py:attribute:: post_proc_opt


   .. py:method:: compute_iou(box, boxes)


   .. py:method:: nms(boxes, scores, iou_threshold)


   .. py:method:: rescale_boxes(boxes, input_width, input_height, target_width, target_height)


   .. py:method:: xywh2xyxy(x)


   .. py:method:: extract_boxes(boxes)


   .. py:method:: get_model_outputs(input_buffer)


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

      Input:
      input_buffers: List[Gst.Buffer] List of input buffers, source from each pad.
      output_buffer: Gst.Buffer Output buffer that needs to be overwritten.

      Implement your logic within this function. Process the input buffers, and modify the output
      buffer.