Dustin Franklin

Hi @darko262, do you mean have multiple RTSP streams? Yes, you can do that by creating separate `videoSource` objects in the code

Hi @Hongstr, it would be like this: https://github.com/dusty-nv/jetson-inference/issues/786#issuecomment-721973736

Hi @r2ba7, mobilenet is a image classification model, so you may want to try running it similar to this: https://github.com/dusty-nv/jetson-inference/blob/master/docs/pytorch-cat-dog.md#processing-images-with-tensorrt You would need to specify the correct input & output...

If you're unable to get your docker daemon working correctly, I would just recommend reflashing your device or SD card instead of spending a bunch more time on it. Then...

Hi @r2ba7, I don't typically support custom UFF's in this repo, but you could try loading it by hardcoding the paths here: https://github.com/dusty-nv/jetson-inference/blob/bed39a4ed9f6477ac7337295bf6713a46caebaec/c/detectNet.cpp#L266

Yes it works here for L4T R34.1.0, if you have any errors please let me know.

Thanks @arnaudbuy - just fixed this in https://github.com/dusty-nv/jetson-inference/commit/bed39a4ed9f6477ac7337295bf6713a46caebaec

Hi @lingzijian, what is the command line you are running? Can the `video-viewer` utility view the video stream that you are using?

Hi @SpsProjectNet, please see my reply on the forums about trying to disable NVMM memory in the build: https://forums.developer.nvidia.com/t/gstreamer-gstdecoder-failed-to-retrieve-next-image-buffer/195168/3?u=dusty_nv

Hi @lingzijian, I've updated the repo in https://github.com/dusty-nv/jetson-utils/commit/0d3f59f5c0967a108ec1cd58a518ee5ad817d35b to support proper CMake option for this instead. Can you try pulling the latest and using `cmake -DENABLE_NVMM=OFF ../` instead? ``` bash...