Hardware: Jetson Nano - Jetpack 4.4 - Python 3.6 - Deepstream 6.0
I'm currently working with deepstream-imagedate-multistream.py 1 example from NVIDIA-AI-IOT repo and I want to use face_recognition library 2 (of adam geitgey) in this sample to recognize faces in multiple video sources. So the question is that how can I directly process frames in this sample pipeline.
I have read the deepstream document and have done many tests but still don't have any results. I hope that anybody have encounter the same problem or having similar experience could help me find a solution. I would really appreciate. Thanks.