Close

Hack Chat Transcript, Part 3

A event log for Machine Learning with Microcontrollers Hack Chat

Arduinos and Pis and AI, oh my

lutetiumLutetium 09/11/2019 at 20:180 Comments

Pete Warden12:35 PM
@happyday.mjohnson the general rule is to do as little preprocessing as possible. We do run FFTs on audio to get features, but we take images and raw accelerometer data

Daniel Situnayake12:35 PM
@Sébastien Vézina keep reading :) You won't need to know much of the underlying theory to build some amazing stuff

13r1ckz12:35 PM
How well does the square identifier model detects the backs of a human as a human? (have some problems with that)

Pete Warden12:35 PM
@Dan Maloney Our Dan had a similar idea for recognizing pigeons! :)

Arsenijs12:36 PM
@mtfurlan sorry, I've been having infrastructure troubles, will look into it tonight

Daniel Situnayake12:36 PM
@Pete Warden giving away my million dollar idea!! haha

happyday.mjohnson12:36 PM
@pete - in my way minimum exploration of accel data, there seems to be a benefit on some level of filtering, But I must admit I'm a bit clueless. I guess to me it makes intuitive sense. Since modeling is such a "Dark Art"

Meghna Natraj12:36 PM
@happyday.mjohnson yes colab is awesome -- it's free and convenient -- and you get GPUs too! A lot of folks think you need a lot of data and resources to get started -- but you actually don't. :)

pt12:37 PM
from youtube "PTS

any boards planned with MCUs that include tensor accelerators like the MAIX?'

mtfurlan12:37 PM
@Arsenijs No worries I completely understand. Maybe have it echo your message back to IRC so it's clear if it doesn't work?

Andres Manjarres12:37 PM
@Pete Warden @Daniel Situnayake Incredible book, a lot thanks

happyday.mjohnson12:37 PM
@Meghan i just wish I understood the path from colab -> model on CP.

Pete Warden12:37 PM
@happyday.mjohnson I'm a newbie to accelerometer data too, but our Beijing team are working on the demo, and seem to have made a lot of progress without much preprocessing. The networks themselves are good at learning features

Daniel Situnayake12:37 PM
Thank you @Andres Manjarres !!

happyday.mjohnson12:37 PM
@pete - do you have a timeframe when we can learn from your accel work?

jdaf_1997 joined  the room.12:38 PM

happyday.mjohnson12:38 PM
@pete - it would be so cool to get this figured out before my parents pass away :-)

Foxmjay12:38 PM
@Max-Felix Müller not really , do you have a link for it ?

Daniel Situnayake12:38 PM
@happyday.mjohnson we'll have example code available by the end of the month!

Arsenijs12:38 PM
@mtfurlan as soon as I have the "it doesn't forward" detection coded in, it will just re-get the HaD token and re-send it, in short, it will fix itself instead of just signalling "broken" =)

happyday.mjohnson12:39 PM
@Daniel - thank you. Where is the best place to follow for new postings?

Max-Felix Müller12:39 PM
@Foxmjay no, I was just curious

John Loeffler12:39 PM
Limor, PT I am working on the Hackaday Finals could I DM you about your M4 and 240x240 Displays (mechanical33486@icloud.com)

pt12:39 PM
@John Loeffler post here! happy to answer anything!

Daniel Situnayake12:40 PM
@happyday.mjohnson Twitter is useful! I'd follow https://twitter.com/tensorflow for big announcements, and you can follow me (https://twitter.com/dansitu) for more fine-grained stuff

happyday.mjohnson12:40 PM
@Daniel ...sigh...ok...i stay off of THE twitter and THE Facebook...but for TF/Keras....

pt12:40 PM
@happyday.mjohnson we have a bunch of news, guides, projects, etc. that we post up here too : https://blog.adafruit.com/category/machine-learning/

pt12:41 PM
and we're adding more things here too: https://www.adafruit.com/index.php?main_page=category&cPath=1006

Don Gabriel joined  the room.12:41 PM

happyday.mjohnson12:41 PM
@pt thank you. Your learning resources are incredible. Thank you for such an amazing company.

Daniel Situnayake12:41 PM
@happyday.mjohnson Twitter is surprisingly amazing for ML stuff, you can follow a lot of very interesting folks

pt12:42 PM
one of our goals is to have something that is under $20 that does ML speech rec really good and something under $100 that does ML vision really good

pt12:42 PM
thanks @happyday.mjohnson

pt12:42 PM
all edge (not net connected)

John Loeffler12:42 PM

John Loeffler12:42 PM
How fast can the 240x240 update i wanted to explore this for a moonshot powersupply that can be a crude oscope

@limor - you've got as much time as you want. Just let me know when you've got to get back to work

pt12:42 PM
96Boards

@Adafruit Industries Have you ever done any work on a hybrid Arm cortex-A / cortex-M chipset? Something like the STM32MP1 or equivalent? Could use MCU for realtime and cortex A for heavy lifting etc..

Prof. Fartsparkle12:42 PM
why the hell is called 'edge computing' btw?

Daniel Situnayake12:43 PM
@Prof. Fartsparkle the idea is that it's happening at the "edge" of the network

limor12:43 PM
@John Loeffler you can send it SPI data as fast as 64MHz so you just need to update the display whenever ya want

Daniel Situnayake12:43 PM
instead of in the middle

Matteo Borri12:43 PM
because we keep going back and forth between client-server and distributed, and we have since what, 1970?

Matteo Borri12:44 PM
every time we call it something else

Don Gabriel12:44 PM
Hi, how hard is it to work with the PIC32 series like the PIC32MX/MZ ?

Matteo Borri12:44 PM
remember when "thin client PC" were all the rage

Andres Manjarres12:44 PM
@pt did you think in FPGAs for these low-cost and low-power solutions?

Don Gabriel12:44 PM
For ML

Daniel Situnayake12:44 PM
in many cases, there's no network connection involved whatsoever

limor12:44 PM
PIC32 is not based on ARM so it will be tougher

limor12:44 PM
there's no strong optimization efforts going that we know of

pt12:45 PM
@Andres Manjarres for FPGAs tough for low cost and harder to learn/use

happyday.mjohnson12:45 PM
Do you see the need for custom chip solution to really take advantage of "edge" Deep learning?

Don Gabriel12:45 PM
Have you considered the Lattice ECP series?

limor12:45 PM
nope

limor12:45 PM
want to keep things easy for everyone to use!

gh7873112:46 PM
@Don Gabriel The PIC32 is a MIPS processor, and MIPS went bankrupt, so no future products coming. Better to invest your software effort in ARM.

Don Gabriel12:46 PM
Thx gh78731

Daniel Situnayake12:46 PM
@happyday.mjohnson there is a ton of ML-optimized hardware on the way, but even a Cortex-M can do really useful stuff today

Andres Manjarres12:46 PM
@pt Okey, very understandable

pt12:46 PM
ok! ladyada says we need to go back to engineering

limor12:47 PM
thank you everyone!

limor12:47 PM
keep hangin out here and posting up your questions and more!

Christopher Bero12:47 PM
Thanks!

pt12:47 PM
'so i think we're gonna go! that said, we have a show tonight too at 8pm ET

happyday.mjohnson12:47 PM
Adafruit / Google/ Hackaday - thanks very much.

3gmarquardt12:47 PM
thank you!

Pete Warden12:47 PM
Thanks for hosting us, and all the great questions!

Daniel Situnayake12:47 PM
Is anyone considering a particular project they'd like to build? I'd be happy to help figure out if it's feasible and point you at the right resources to get started!

Phillip Scruggs12:47 PM
Great links!

Dave Blundell12:47 PM
thanks

@limor and @pt - As always, it's a rush to have you guys on. Lot's of info, lots to digest. Thanks so much for your time, and thanks to @Daniel Situnayake , @Meghna Natraj , and @Pete Warden for everything!

pt12:47 PM
special thanks to google folks for being here!

John Loeffler12:47 PM
Thank you

Tara12:48 PM
Thanks!

Daniel Situnayake12:48 PM
Thanks everyone!! Great chatting with you :D

Daniel Situnayake12:48 PM
Feel free to ping me on https://twitter.com/dansitu if you have more q's

Andres Manjarres12:48 PM
Thanks

Daniel Situnayake12:48 PM
And I will hang out in here for a while longer :)

as.instrumedglobal12:48 PM
thanks everyone for all the good resources and updates. it took me 6 months of stalking the PyBadge to finally be able to order our makerspace some boards. They're still clearing customs but we can't wait to give them a try!

pt12:48 PM
thank you @Dan Maloney and hackaday!

Daniel Situnayake12:48 PM
Thank you @Dan Maloney!!

@pt - Great Chat, thanks so much!

Daniel Situnayake12:48 PM
And thanks @pt and @limor for inviting us :D

Max-Felix Müller12:48 PM
@Daniel Situnayake I want to build a traffic sign detector (german signs) with a camera and a jetson nano. Where do I start? Getting images of signs / finished networks etc.?

as.instrumedglobal12:49 PM
hopefully we'll get them in for our Google DevFest come October 5th

cet12:49 PM
Are you planning to do any examples on GANs?

jcradford12:49 PM
Thank you for the information all and adafruit for the chat,

Kunti joined  the room.12:49 PM

Daniel Situnayake12:49 PM
@max-fe

Don Gabriel12:49 PM
What ML libraries are you planning to use? TensorFlow, Keras, etc.. ??

Gonna take me a while to post the transcript, but it'll be here: https://hackaday.io/event/166253-machine-learning-with-microcontrollers-hack-chat

And don't forget to tune in next week for the SDR Hack Chat with Corrosive!


https://hackaday.io/event/167395-software-defined-radio-hack-chat

HACKADAY

Software Defined Radio Hack Chat

SDR guru Corrosive joins us for the Hack Chat on Wednesday, September 18 2019 at noon PDT. Time zones got you down? Here's a handy time converter! If you've been into hobby electronics for even a short time, chances are you've got at least one software-defined radio lying around.

Read this on Hackaday

Daniel Situnayake12:50 PM
@Max-Felix Müller yes! I'd first of all look for datasets of signs, or a trained network you can use. Since they're pan-EU signs, I bet there's something out there. then, train the best model that you can without even thinking about the "edge" part. you might want to try transfer learning with an existing vision model

Daniel Situnayake12:51 PM
@Max-Felix Müller after that, try and shrink the model down so it fits on your device while still being accurate

13r1ckz12:51 PM
what would be the recommended point of start for learning machine learning from scratch?

Daniel Situnayake12:51 PM
@cet we have some Google tutorials on GANs, e.g. https://www.tensorflow.org/beta/tutorials/generative/dcgan

Daniel Situnayake12:51 PM
@13r1

Max-Felix Müller12:52 PM
@Daniel Situnayake I heard about transfer learning and know what it's about but I have no idea how to use it. Do you have a link for a tutorial?

13r1ckz12:52 PM
Thank you @Daniel Situnayake

Pete Warden12:52 PM
@Max-Felix Müller here's a good place to start: https://codelabs.developers.google.com/codelabs/tensorflow-for-poets/#0

Daniel Situnayake12:52 PM
@13r1ckz I recommended a couple of books earlier in the chat:

https://www.manning.com/books/deep-learning-with-python

https://www.amazon.com/Hands-Machine-Learning-Scikit-Learn-TensorFlow/dp/1491962291

Discussions