Nvidia's $99 Jetson Nano Is an AI Computer for DIY Enthusiasts
61–70 of 218 posts
Re: Nvidia's $99 Jetson Nano Is an AI Computer for DIY Enthusiasts
#62Re: Nvidia's $99 Jetson Nano Is an AI Computer for DIY Enthusiasts
#63Re: Nvidia's $99 Jetson Nano Is an AI Computer for DIY Enthusiasts
#64> 472 gigaflops Whenever I hear a number of gigaflops or terraflops, I like to look up the history of super computers [0]. This $99 computer is faster (on paper) than the world's fastest supercomputer in 1996, or a bit over 20 years ago. That's pretty cool. [0] https://en.wikipedia.org/wiki/History_of_supercomputing#Mass...
A Pentium 90 was probably fairly common in the mid 90s. Delivered a whopping 0.09 GFLOPS :)
https://www.google.co.nz/amp/s/www.wired.com/2002/01/thats-a...
Re: Nvidia's $99 Jetson Nano Is an AI Computer for DIY Enthusiasts
#65Earlier quoted context omitted.
Quad core arm, 4gb of ram and gigE! Seems like a really nice board
Also has an M.2 slot for WiFi, as well as both HDMI and DP...supports two simultaneous displays out of the box.
Re: Nvidia's $99 Jetson Nano Is an AI Computer for DIY Enthusiasts
#66Re: Nvidia's $99 Jetson Nano Is an AI Computer for DIY Enthusiasts
#67Re: Nvidia's $99 Jetson Nano Is an AI Computer for DIY Enthusiasts
#68Hope it'll ship with better support that the first Jetson. The one they marketed with all that AI/Machine Vision stuff and then shipped without a camera driver. This is just following Google's Edge TPU, which probably competes with a Raspberry Pi + Movidius stick. The market there is getting interesting.
Re: Nvidia's $99 Jetson Nano Is an AI Computer for DIY Enthusiasts
#69Earlier quoted context omitted.
This has an M.2 Key E connector which has PCIe ×2, USB 2.0, I2C, SDIO, UART and PCM. Hypothetically an M.2 PCIe drive could work with a Key M to Key E adapter, but I couldn't find one in a cursory search.
Unfortunately it looks like you lose wireless connectivity then.
Re: Nvidia's $99 Jetson Nano Is an AI Computer for DIY Enthusiasts
#70Earlier quoted context omitted.
Cheaper than the $150 Google TPU Dev Board, and looks like it can do training as well as inference. Training is a slight win (although it's going to be too slow for anything useful really). But it looks like the TPU will outperform this somewhat for inference. The 256 core Jetson (this has 128 cores) could run MobileNet-v2 at between 12 and 20 ms per image (depending on batch size)[1], while the USB TPU adapter takes…
>> Nor does the TPU dev board. Yes it does require you to send your model to Google: https://coral.withgoogle.com/web-compiler/