Introduction

CircuitPython prediction library for the Azure custom vision service.

To use this library, you will need to create a custom vision project at CustomVision.ai. Once you have your project, you will need to train either an image classification model, or an object detection model. You can then use this library to make predictions against this model.

You can read more on how to do this in the Microsoft docs:

• Train an image classifier
• Train an object detection model

Dependencies

This driver depends on:

• Adafruit CircuitPython
• Adafruit CircuitPython Requests

Please ensure all dependencies are available on the CircuitPython filesystem. This is easily achieved by downloading the Adafruit library and driver bundle.

Installing from PyPI

On supported GNU/Linux systems like the Raspberry Pi, you can install the driver locally from PyPI. To install for current user:

pip3 install circuitpython-azurecustomvision-prediction

To install system-wide (this may be required in some cases):

sudo pip3 install circuitpython-azurecustomvision-prediction

To install in a virtual environment in your current project:

mkdir project-name && cd project-name
python3 -m venv .env
source .env/bin/activate
pip3 install circuitpython-azurecustomvision-prediction

Usage Example

client = CustomVisionPredictionClient("api_key", "endpoint")

predictions = client.classify_image_url("project_id", "published_name", "https://www.adafruit.com/includes/templates/shop2019/images/adafruit-logo.png")

Contributing

Contributions are welcome! Please read our Code of Conduct before contributing to help this project stay welcoming.

Documentation

For information on building library documentation, please check out this guide.