Nvidia announces Jetson Nano 2GB, a single board computer • Hacker News Board

Re: Nvidia announces Jetson Nano 2GB, a single board computer

#161

Post by qchris » Mon, Oct 05, 2020, 9:01 PM UTC

bserge wrote: post #145

webwanderings wrote: post #58

I want to setup something like this for my daughter's primary grade school meetings using Zoom. Any suggestions? Are the Pis or this device up to par now for such use case? I totally do not like Chromebooks, and standard laptops are an overkill.

Go with the overkill, used mobile workstations are cheaper than new Chromebooks. Just imo

I tend to lean in this direction as well. A 4GB RPi4 would work, but the Pi itself costs $55, plus a dedicated USB power supply, uSD card, the HDMI adapter I usually need, webcam, possible case/cooling fan (Pi4's can get hot), plus a spare keyboard, mouse, and monitor.

The total package ends up significantly more expensive than the "list price" of an RPi itself, and it ends up not making much more sense than buying a used x230 or something off of eBay for <$200.

Re: Nvidia announces Jetson Nano 2GB, a single board computer

#162

Post by DoctorOetker » Mon, Oct 05, 2020, 9:07 PM UTC

talkingtab wrote: post #53

I have the 4GB version of the Nano and the 4GB Raspberry Pi. I like the Nano, but I use it mostly as a development machine and for that I would rank the 8GB Raspberry Pi at about $89 US the best deal. Substantially below that is the Nano, and almost tied is 4GB Pi. There may be cases where you absolutely need an Nvidia machine in which case I would argue for the 4GB version, but otherwise the 8GB Pi appears to be the…

do you happen to know the memory bandwidth if these newer Raspberry Pi's?

I can't find it on the product site, nor the BCM2711 datasheet (more like a programmers manual)

Re: Nvidia announces Jetson Nano 2GB, a single board computer

#163

Post by aardvarkr » Mon, Oct 05, 2020, 9:11 PM UTC

bserge wrote: post #144

Honest question, why would I choose this over an "old" Android phone that I already have in my drawer?

Native CUDA implementation on an Ubuntu system would be the biggest reason in my mind. There's CUDA for android but (at a glance) it didn't look stellar. It also helps that there is an active community here where everyone has the same device so if you run into issues you have somewhere to turn. Final point is NVIDIA clearly sees this as a business segment worth investing in so it will continue to grow and improve.

Re: Nvidia announces Jetson Nano 2GB, a single board computer

#164

Post by talkingtab » Mon, Oct 05, 2020, 9:19 PM UTC

Florin_Andrei wrote: post #151

talkingtab wrote: post #53

I have the 4GB version of the Nano and the 4GB Raspberry Pi. I like the Nano, but I use it mostly as a development machine and for that I would rank the 8GB Raspberry Pi at about $89 US the best deal. Substantially below that is the Nano, and almost tied is 4GB Pi. There may be cases where you absolutely need an Nvidia machine in which case I would argue for the 4GB version, but otherwise the 8GB Pi appears to be the…

I think the whole idea for the Nano was having a GPU on a small computer. The RPi doesn't have that. If you're comparing them as plain CPU-based development systems, you're missing the whole point of the Nano.

Just so there is no confusion, the Raspberry Pi 4 supports dual 4k displays out of the box. It has a built in Broadcom VideoCore VI @ 500 Mhz GPU and dual micro HDMI ports so you are good to go. Perhaps you meant a discrete GPU?

Re: Nvidia announces Jetson Nano 2GB, a single board computer

#165

Post by janoc » Mon, Oct 05, 2020, 9:20 PM UTC

banachtarski wrote: post #126

chunkyks wrote: post #42

I have a Jetson nano. It's a nice thing for what it is, and the price. But, the software misses the mark by a lot. It's still based on Ubuntu 18.04. Want python later than 3.6? Not in the box. A lot of python modules need compiling, and the cpu is what you'd expect. Good for what it is, bad for compiling large numbers or packages. They run a fancy modern desktop based on the Ubuntu one. Sure, it's Nvidia, gotta be fl…

I'm not going to lie, I don't understand the usage of Python and other such languages in the embedded space in general.

Rapid prototyping and in the case of Jetson - computer vision and Tensorflow running on the GPU. Both have excellent support for Python.

Sure you can make those things run natively but people using them are used to Python, lot of code is written in Python for it and there is little to no performance penalty of running the code in Python (everything perf. critical is running natively anyway, Python is only used to "glue" those bits seamlessly together).

And once you have RAM in gigabytes even the extra memory overhead of Python becomes a moot point.

Re: Nvidia announces Jetson Nano 2GB, a single board computer

#166

Post by am_lu » Mon, Oct 05, 2020, 9:20 PM UTC

I have Odroid H2 in here as my main system, quad core X86, M2 slot for SSD, user-friendly RAM (SO-DIMM, currently 8GB installed supports up to 32GB), SATA ports, runs fanless 40degrees Celsius for most of the time. Lovely bit of kit.

Re: Nvidia announces Jetson Nano 2GB, a single board computer

#167

Post by janoc » Mon, Oct 05, 2020, 9:22 PM UTC

pikrzyszto wrote: post #104

chunkyks wrote: post #42

I have a Jetson nano. It's a nice thing for what it is, and the price. But, the software misses the mark by a lot. It's still based on Ubuntu 18.04. Want python later than 3.6? Not in the box. A lot of python modules need compiling, and the cpu is what you'd expect. Good for what it is, bad for compiling large numbers or packages. They run a fancy modern desktop based on the Ubuntu one. Sure, it's Nvidia, gotta be fl…

> Want python later than 3.6? apt-get install python3.7 or apt-get install python3.8

That will most likely break OpenCV, Tensorflow and CUDA which depend on binary packages compiled for the given version of Python.

Re: Nvidia announces Jetson Nano 2GB, a single board computer

#168

Post by MuffinFlavored » Mon, Oct 05, 2020, 9:24 PM UTC

am_lu wrote: post #166

I have Odroid H2 in here as my main system, quad core X86, M2 slot for SSD, user-friendly RAM (SO-DIMM, currently 8GB installed supports up to 32GB), SATA ports, runs fanless 40degrees Celsius for most of the time. Lovely bit of kit.

$111 for anybody out of the loop: https://www.hardkernel.com/shop/odroid-h2/ (and seemingly out of stock?)

Re: Nvidia announces Jetson Nano 2GB, a single board computer

#169

Post by janoc » Mon, Oct 05, 2020, 9:29 PM UTC

CydeWeys wrote: post #36

nobrains wrote: post #5

What are the use-cases for a GPU-accelerated single board computer?

Same as it's always been: Gaming. I bet even this $59 computer can play games surprisingly well. Obviously not modern AAA titles or anything like that, but there's many decades' worth of games it can play (including ones originally released for non-PC platforms). There's lot of interesting Pi-powered handhelds and mini-arcade setups running emulated games; this seems like it'd be significantly better at that.

None of those emulators need accelerated graphics in the form of the Nvidia GPU and emulators for the ARM platform most likely can't even use it as most of these SBCs don't have anything like that.

This Jetson really isn't a platform to run emulated games - for that there are much better boards, with more RAM. Which is a lot more important issue. You can't do miracles with 2GB of RAM.

Jetson is made for computer vision, neural networks and signal processing, where the GPU isn't used as a GPU but as a massively parallel co-processor to crunch through a lot of data at once.

Re: Nvidia announces Jetson Nano 2GB, a single board computer

#170

Post by varispeed » Mon, Oct 05, 2020, 9:33 PM UTC

barkingcat wrote: post #51

varispeed wrote: post #29

What is exactly the point of such devices? If you create something worthwhile with it, you cannot exactly include it in your product. I get that you can create something like a one off garage opener based on face recognition, but you won't learn any real world knowledge of developing a product and if you later on decide that this is something for you, you'll have to learn a whole new ecosystem. These devices remind m…

The Jetson Nano is the "small" SDK for the Jetson Xavier series which is Nvidia's embedded ai platform for volume (ie they will sell you thousands of units of them for volume manufacturing in cars, etc) - that's always been the draw for the Jetson Nano - you use the hardware for prototyping and when you are ready, buy the larger and more expensive Xavier and that goes into your hardware product. https://www.nvidia.co…

I tried to find any documentation, code, schematics but gave up after 30 minutes. Who is this for? It seems like this product is for people who want to say they do AI and show some PCBs on their Instagram.