Pinned Tweet
Do you want to run @EdgeImpulse FOMO on your #esp32 camera using @arduino IDE?
Don't know where to start?
Look no further!
Here's the BEST tutorial you'll find on the entire internet.
Don't believe me? Keep reading 👇
eloquentarduino.com/esp32-ca…
Turn your #esp32 p4 into a searchable knowledge base: convert your notes into embeddings and find top-K most relevant entirely on board.
Everything is packaged into a single executable to invoke with 1 line. Read the full tutorial to replicate in 10 minutes: salernosimone.com/en/blog/es…
I (aka AI) ported @EspressifSystem esp-dl framework to @arduino for efficient NN deployment. Also wrote a companion Python library for easy model training and conversion to .espdl format. See KWS example (runs in 16ms on S3) 👉 salernosimone.com/en/blog/es…
I published a Docker image to play with
@TencentHunyuan
#WorldMirror model easily. I'm still figuring out if it can replace COLMAP for #gaussiansplatting (OOM errors with tens of images)...
dub.sh/world-mirror
I started fiddling with #esp32 WiFi CSI (Channel State Information) to detect motion/gestures totally wireless.
Contrasting results so far: clear signals sometimes, no noticeable changes other times.
Will continue investigating.. promising applications on the horizon...
Hey @TencentHunyuan, I've been playing with World-1.0 model but all my results exhibit this poor quality, no matter the input image (2048x1536, see first comment). Command is as per your Github README.
Can you suggest how to fix this?
Simone Salerno retweeted
🔊📷 From sound to images, author @EloquentArduino explores 9 hands-on projects that teach you how to classify, predict & analyze data on #microcontrollers. No supercomputer needed! #EmbeddedML #TinyML #ArduinoProjects #AI #EdgeComputing #tensorflow
🔗 ow.ly/g68h50Wf61U
IMO the most approachable way to get started with #tinyml for Arduino
🔊📷 From sound to images, author @EloquentArduino explores 9 hands-on projects that teach you how to classify, predict & analyze data on #microcontrollers. No supercomputer needed! #EmbeddedML #TinyML #ArduinoProjects #AI #EdgeComputing #tensorflow
🔗 ow.ly/g68h50Wf61U
This is the motivation from someone who asked for a refund for my book.
Looks like my 30 day money back guarantee will soon become a 7 day guarantee... 😔
One more tutorial on my to-do list...
I hooked up this little ESP32-CAM to my wifi. It takes a picture every 30s and sends it to flash-8B with a prompt like 'is there a person in this image?'. If the model says yes (with structured outputs), it turns on an LED. If I left this on for a month it would cost about $1.
Obviously this is the worst security cam ever, BUT I think it's a compelling demo. You can put some 'intelligence' in the loop of a hobby project with <$10 in hardware and fractions of a cent per API call. You can 'program' it in natural language like 'if there is an orange cat playing with my plant'. And with LLM help, modifying the code is possibly as easy as 'make this send me a discord notification if the alarm is triggered twice in an hour'.
Anyway, now that I know this thing works it has other projects it is destined for. But cool to know how easy it is to whip this up :)
ALT A tiny board with camera module (the ESP32-CAM)
ALT A potato-quality picture in the test interface I (OK, o1) made.
I asked ChatGPT to suggest to me 3 books about a given topic, explaining what they were about and why they were relevant to my query.
1/3 was completely made up. Non existent (from a real author, though).
How can one ever confidently trust LLMs?
Turn your @arduino board into an Alexa-like, voice controlled personal assistant - powered by ChatGP!
𝗘𝗮𝘀𝘆 & 𝗳𝗼𝗿 𝗙𝗥𝗘𝗘!
Link in the first comment 👇
