Alexander Smirnov

The idea of passing a video stream through the sequence of detectors to refine a guess is valid, I thought of using Deepstack in my setup too. The workflow inside...

Thank you for doing that. Do you want to hand PR over to me or you can finish the upgrade? I do not have much time at the moment, honestly.

Most probably it is concerned with the fact that the latest Jetson Nano system image uses the latest TensorRT 8, where several API were deprecated - Watsor images were build...

My Jetson Nano has 4GB of memory and Watsor works there. I checked that while building TensorRT engine it takes up to 3GB. I guess in your case it fails...

TensorRT engine can be built by creating a 4GB swapfile as described here: https://github.com/asmirnou/watsor/issues/29#issuecomment-1272590695

I'm closing this one in favour of #31. Thank you for your help.