Dustin Franklin

@faheemasi do you have a physical display attached to your Jetson? What is the issue you are facing? The application runs and prints out detection results to the terminal, but...

Hi, it is not able to detect your camera - are you sure you have it plugged in correctly?

Are you able to view the camera with `nvgstcapture-1.0` program? Have you tried shutting off this Nano rebooting recently to reset the nvargus camera daemon?

If you have confirmed that your camera still works and is indeed plugged in correctly, I would re-flash your Nano's SD card with a fresh JetPack image. Otherwise it starts...

Hi @saeed-musashi, do you mean returning the top-K classification results or performing true multi-class classifications? For the former, the data is there but there isn't an API for retrieving it....

Hi @youngjae-avikus, I personally don't have RTSP camera(s) - I would either check this page or the forums: https://developer.nvidia.com/embedded/jetson-partner-supported-cameras

Hi @niyazFattahov, jetson-inference/jetson-utils doesn't support RTSP output, as it requires support for special server code. Otherwise I would add it if it were simple. Note that DeepStream supports RTSP output...

In theory, yes, some similar code / dependencies would need to be integrated into the videoOutput class in order to support RTSP output.

> For this model the predicted class values will be the same no matter the input image Hi @matialmar, are you sure the pre-processing is what your model expects? https://github.com/dusty-nv/jetson-inference/blob/6cf3b12f503d64903ca1e77d4c5474d9b1513a4c/c/imageNet.cpp#L447

@matialmar then you should change the code to reflect that and recompile/reinstall it