I've spent the last few months doing GPGPU stuff on Nvidia Jetson devices and my experience has been the complete opposite. I've rarely seen something with such bad support and documentation.
Unfortunately… I'm not a hobbyist, I'm not tinkering and the aforementioned repositories are… about it. There is little documentation about
- how to build a custom OS image (necessary if you're thinking about using Jetson as part of your own product, i.e. a large-scale deployment). Ideally, I would like to do that as part of a CI/CD workflow. What proprietary drivers and libraries do I need to install? Nvidia basically says, here's our custom Ubuntu image with the usual GUI, complete driver stack and everything – take it or leave it. Unfortunately, the GUI alone is eating up a lot of the precious CPU and GPU resources, so using their OS image in production is no option for me.
- how deployment works on production modules (as opposed to the non-production module in the Developer Kit)
- what production modules are available in the first place ("Please refer to our partners")
- what wifi dongles are compatible (the most recent Jetson Nano comes w/o wifi)
- how to convert your custom models to TensorRT, what you need to pay attention to etc. (The official docs basically say: Have a look at the following nondescript sample code. Good luck.)
- how do I automize testing of TensorRT models & code? Why isn't there a compatibility layer which allows executing my models on non-Jetson devices / on a CPU (obviously at lower performance, but I don't mind).
- … (I'm sure I'm forgetting many other things that I've struggled with over the past months)
Anyway. It's not that this information isn't out there somewhere in some blog post, some obscure Github repo or some thread on the Nvidia forums[2]. (Though I have yet to find a wifi dongle that works reliably…) But it usually takes you days or weeks to find it. From a product which is supposed to be industry-grade I would have expected more.
[0]: https://github.com/dusty-nv/jetson-inference
[1]: https://github.com/jkjung-avt/tensorrt_demos
[2]: https://forums.developer.nvidia.com/c/agx-autonomous-machine...