Google Developers
At CES, the Google AIY team shared how it’s advancing AI at the edge with the new Edge TPU chip, integrated with an NXP i.MX8 processor.
Add accelerated ML to your embedded device with the Edge TPU → http://g.co/aiy
Subscribe to the Google Developers channel! → http://bit.ly/googledevs
Source
1:30 Google talking about Privacy!!
nice, javascript all the way
Pricing? Debian support? Is there a 2+GB RAM version? eMMC? I need more specs!
Amazing
ice cream or hot dog !!!???
Will this board be affordable?
price please. when is going to be released to the market
What differentiates this from let's say a Raspberry pi and opencv?
This look like powerful respberry. Pi. Hope google will make it affordable and available to countries like Nepal too.
Fpga?
so basically a raspberry pi with a tensorflow optimized mini GPU.
??
What is Google?
Can anybody explain me
Google caring about privacy?
Cmooon dudes
They are showcasing AI versions of Arduino projects.
The "bounding boxes around faces" is a few decades too old to wow anyone. But server-less (good) voice recognition & natural language processing could be a game-changer.
What is this?
Now you can cook something and ask it what it was …
Did he say WiFi?
Should we be concerned? LOL
I was thinking adding TPU usb sticks to raspi, then google made its own raspi
So forget the raspi if you are doing a tensorflow ML project and switch to this new device as soon as you can
We teach our kids rules and what's right andwrong. How do you teach AI that, and furthermore how do you discipline it. Are we playing with fire without understanding its capacity?
It's now actually EASY to program that on a raspberry pi.
Maybe it would be a bit slower but results would nearly be the same.
There was a glitch.
And here comes the matrix
so its a Raspberry Pi board with a Tensor flow gpu ?
so… hot-dog, not hot-dog. got it
when the orange donuts was shown to the system, before training on it, it was wrongly classified as an ice cream (red light)….False positive 🙂
How about a free giveaway?
I'm waiting.?
google: "ML on the edge can be used for smart speakers, smart dishwashers and smart TVs"…
Dude please learn how to make a video
How far off is this ?
Very Cool?️?️?
in 10 years devices from this video will be famous memes
Need a deep autoencoder for MNIST
More junk for sale.
not the ai I was hoping for
Wast of time
I really like the Demo at 2:24. What is your approach to differentiate between the objects? Is it online transfer learning or a siamese approach?
I was ready months ago. What's taking so long to release??
privacy
fool me twice
CHEEZZZZZEBURGERRRRR!!!!
Message in a bottle: I wish you told us some specifics about how large a model we can load the TPU with, that kind of things. Basically could not find any kind of information regarding the TPU's capabilities. I understand the concern for IP and such, but please at least give us functional specs.
You just killed a few start ups 😛
I already found a cool application for this. Thank you for sharing!!!
very cool!
I was wondering if they had any audio recognition examples