Building a Real-time Redaction App Using NVIDIA DeepStream, Part 2: Deployment

Originally published at:

This post is the second in a series (Part 1) that addresses the challenges of training an accurate deep learning model using a large public dataset and deploying the model on the edge for real-time inference using NVIDIA DeepStream. In the previous post, you learned how to train a RetinaNet network with a ResNet34 backbone…

i got a problem when i executed the “make” command on the nano, the error is " no cub/device/device_radix_sort.cub", how to fix it.

how can i show landmarks points of face , i have written my custom parser for facedetection with landmarks. If i try to add any parameter to NvDsInferObjectDetectionInfo(nvdsinfer.h) i am getting segmentation fault.

For questions about extending the app, I recommend posting in the DeepStream SDK forum. Good luck!


I try to use my webcam feed instead of sample videos. I am getting the error : passed ‘0’ as denominator for `GstFraction’
** ERROR: <create_camera_source_bin:160>: Failed to link ‘src_elem’

I replace the function in .txt file:
#Type - 1=CameraV4L2 2=URI 3=MultiURI 4=RTSP
CameraV4L2 = /dev/video0

Please help me to solve this issue !!

Sorry to hear that you’re getting this error! I can suggest posting this question in the DeepStream developer forum. There are lots of helpful people there. Good luck!