Q-engineering

A common problem. To overcome ownership issues, I use virtual environments. The wheels you're referring to are all CPU-based. When integrating CUDA acceleration, you're facing too much deviation. Not only...

You have to do it manually. See https://qengineering.eu/install-opencv-on-jetson-nano.html It is targeted for the Nano, but it works also for the Xavier NX. BTW, the script here is (almost) identical to...

Something strange is going on. When I opened your CMakeOutput.log, the first line says `The system is: Linux - 4.9.201-tegra - aarch64`. That's good, you have the genuine Jetson Nano...

@Chandanpanda , I never tested it on a 2GB Jetson Nano, but I can imagine it will not work. There are indeed some basic differences between the 2 and 4...

Due to the busyness at the office, it is very likely that we will not get around to it for a while. In addition.... 1.9 GHz is a top speed....

Sorry, I have no idea. Perhaps Google does(?)

It's all a matter of trail and error. The max frequency will work most of the time. However, when running some deep learning model with 100% CPU and 100% GPU...

OK, seems NVIDIA has changed the governor since i wrote the post. Leaves you with two options, both I didn't test. 1. Alter the 998400000 to a lower number. 2....

@Benebaby, You are absolutely right! To solve it, you have to follow another strategy. The problem is that every application requires a different solution; there is no 'one' genetic outcome....

@mxochicale, thanks for your enthusiasm! Could you tell me what you have in mind precisely? This repo intends to provide a basic skeleton for multi-threading several cameras (as you undoubtedly...