Smart Dog Tent 🐶 with Remyx AI

Introduction

At Remyx, we are thrilled to assist creators in developing AI-powered projects and products effortlessly! This project will demonstrate how to automatically generate a personalized computer vision model to power your tinyML project. In this example, we'll create a customized dog detector to make a smart dog tent, turning on a heater when a dog is present.

Scope

This project will cover how to:

• Sign up and use the Remyx platform
• Chat/Click-to-create a new TFLite micro model
• Run your new model

Hardware

Note: You can test this model using just your computer, but if you want to fully reproduce this project, you'll need:

• Arduino Portenta H7 + vision shield

Software

This project will use:

• Remyx AI Engine (https://engine.remyx.ai)
• OpenMV IDE

Setting up your Remyx account

Sign in/Sign up: Navigate to https://engine.remyx.ai and create a new account. You can also find this link from our landing page, https://remyx.ai, by clicking the "Get Started" button.

Choose "Continue with Google" or "Continue with Github" to authenticate using your Google or GitHub account.

An account will be created for you if you haven't previously authenticated.

Ready to train: On signup, you'll have a free model training credit available! We can use this credit to train our model.

Customize Your Model

Train

Let's train a tiny image classifier for our Arduino. You can chat with the Remyx Agent to create your model.

Tell the agent about your project. The agent creates the right model for you, asking questions as necessary. Here's an example:

I’m making a dog presence project using the Arduino Nano BLE Sense 33. The Arduino needs to differentiate between an empty tent interior and dog. Name my model DoggyTentExample.

Training takes around 30 minutes and is easy to do! 🎉

Soon, you'll see your model's progress on the Home or Dashboard tab. When it's done, click to see more details.

Want to try a quick test? Go to "Predictions" on the dashboard, click "Options" and then "Run model in browser". Drop a test image and see the result.

To download for specific devices like Arduino, click "Options" then "Download" and choose "TFLite".

Hardware Assembly

Simply attach the vision shield to the Arduino Portenta H7 as these instructions show, and you're done!

Run

Repository

Find the micropython code for this project at https://github.com/remyxai/remyx_experiments.git

git clone https://github.com/remyxai/remyx_experiments.git

Make sure you have OpenMV IDE and can connect to your Portenta board. Download the .tflite model and put it on the Portenta's drive. Open the Python script in microcontroller/openmv/dog_detection. Update the labels as needed for your application.

And finally, press the run button at the bottom left of the IDE to see the streaming inference results from the camera!

Conclusion

With the Remyx Engine, turning your AI ideas into reality is easy. You created a microcontroller to detect when a dog is occupying her tent, with no data or ML expertise required.

What will you build with your custom vision sensor? Why not try to trigger a snack delivery or turn on her heater to keep her cozy?

In the next post, we'll show you how to run a model on the Arduino Nano 33 BLE Sense.

We're excited to see what you create using Remyx.

Arduino docs here

Have questions or want to share some feedback? Feel free to reach us at contact@remyx.ai or on Twitter and LinkedIn.

Don't forget to sign up for our newsletter for more machine learning goodies! And read our blog for the latest updates