# Raspberry PI4 + Coral USB + posenet 姿態識別

* URL: https://github.com/google-coral/project-posenet

* PI4先裝好Raspbian, 還有CSI camera
* PI裝上CSI camera後, 記得要去sudo rasp-config啟用Camera interface, 預設是關閉的

* 安裝library
* https://coral.ai/docs/accelerator/get-started/#set-up-on-linux-or-raspberry-pi

echo "deb https://packages.cloud.google.com/apt coral-edgetpu-stable main" | sudo tee /etc/apt/sources.list.d/coral-edgetpu.list
curl https://packages.cloud.google.com/apt/doc/apt-key.gpg | sudo apt-key add -
sudo apt-get update
sudo apt-get install libedgetpu1-std

* 安裝TensorFlow Lite library
* https://coral.ai/docs/accelerator/get-started/#set-up-on-linux-or-raspberry-pi

mkdir coral && cd coral
git clone https://github.com/google-coral/tflite.git
cd tflite/python/examples/classification
bash install_requirements.sh

* 安裝 Install just the TensorFlow Lite interpreter
* https://www.tensorflow.org/lite/guide/python

wget https://dl.google.com/coral/python/tflite_runtime-1.14.0-cp37-cp37m-linux_armv7l.whl
pip3 install tflite_runtime-1.14.0-cp37-cp37m-linux_armv7l.whl

* 安裝python3-edgetpu

sudo apt-get install python3-edgetpu

* 安裝posenet

git clone https://github.com/google-coral/project-posenet
sh install_requirements.sh
python3 simple_pose.py

速度頗快, 有40FPS. XD