|author||Scott Main <email@example.com>||Thu May 12 10:04:14 2022 -0700|
|committer||Scott Main <firstname.lastname@example.org>||Thu May 12 10:04:14 2022 -0700|
Declare readme content type for PyPi Change-Id: I2ac05bfe9f2e695fa9caaa2ec8d96fe9d574a0ec
The aiymakerkit API greatly simplifies the amount of code needed to perform common operations with TensorFlow Lite models, such as performing image classification, object detection, pose estimation, and speech recognition (usually in combination with the Coral Edge TPU).
This repo also includes scripts to collect training images and perform transfer learning with an image classification model, directly on your device (such as a Raspberry Pi).
This project was designed specifically for the AIY Maker Kit, which uses a Raspberry Pi with a Coral USB Accelerator, camera, and microphone.
If you‘re on a Raspberry Pi, we recommend you flash our custom Raspberry Pi OS system image before installing this library, as documented at https://aiyprojects.withgoogle.com/maker/. That way, you’re sure to have all the required software installed and there should be no trouble.
But if you want to do things differently and can tolerate some extra steps and risk troubleshooting, you can build our system image yourself and/or install the required libraries on an existing RPI OS system as documented at https://github.com/google-coral/aiy-maker-kit-tools (but we do not recommend it).
For other situations where you want to install only the
aiymakerkit library, you must manually install the
pycoral libraries first. Assuming that you are also using the Coral USB Accelerator, you can get these libraries by following the Coral USB Accelerator setup guide at coral.ai.
Then you can clone this repo and install the library as follows:
git clone https://github.com/google-coral/aiy-maker-kit.git cd aiymakerkit python3 -m pip install .