Gustav von Zitzewitz

@naisy which problem should this solve?

@Programmerwyl are you using the current master? 1. how does your config look like? 2. Did you change code? 3. Which python / openCV /JetPack version are you using

This is really strange as i just double checked everything today. Which TensorFlow do you use?

are you using the onboard camera of the jetson? do you know how to use it in opencv, have a look here: https://devtalk.nvidia.com/default/topic/1017860/using-on-board-tx2-camera-with-opencv-3-2-/?offset=7 and others

I make a guess: you are using OpenCV that comes preinstalled with flashing JetPack right? The problem is that Nvidia/JetPack Build OpenCV without Gstreamer support. That’s why it is not...

I use and always have used JetPack 3.2, maybe you should switch to that?

I successfully tested it on 1.4, 1.5, 1.6 but with varying performance results. If you want to achieve highest results use the versions that I recommend in the readme. Also...

@mk123qwe I did not try it out myself. But you could do, I think it should work as i tried to write it both py3 and py2 compatible. Maybe you...

Hey @mmrazlighi Are you sure you are running the latest master and have set `BBOX: True` in the config?

Nice work @naisy, your fork is really far off from the base right now :D What is necessary to get mnv2 compability? did you investigate the graph for custom split...