As per analysis, there are features available in Deepstream to access the memory for MetaData between Python and C++. If we need to add a new python code that can access the memory metadata info from the C++ code executions and perform some of the further processing on each frames, is there any way to add this python code to the pipeline that are setup in the code.
• Hardware Platform (Jetson / GPU) NVIDIA A100-SXM
• DeepStream Version 6.0
• TensorRT Version 8.0.1
• NVIDIA GPU Driver Version (valid for GPU only) 470.57.02
• Issue Type( questions, new requirements, bugs) questions
• How to reproduce the issue? (deepstream_tao_apps/apps/tao_others/deepstream-bodypose2d-app at master · NVIDIA-AI-IOT/deepstream_tao_apps · GitHub)/ deepstream_bodypose2d_app.cpp