[{"element_type":"text","content":"\n        \u003cp\u003eGoogle Coral's USB Accelerator (\u003ca href=\"https://coral.ai/docs/accelerator/get-started\"\u003ehttps://coral.ai/docs/accelerator/get-started\u003c/a\u003e) currently doesn't work on the Raspberry Pi OS Bookworm. In order to get the USB Accelerator to work we need to do a few extra things like install Python 3.9 and create a python virtual environment\u003cspan class=\"spoiler tagged\"\u003e.\u003c/span\u003e\u003c/p\u003e\n\u003cp\u003eInstall dependencies\u003c/p\u003e\n\u003cp\u003e\u003ccode\u003esudo apt-get install -y build-essential tk-dev libncurses5-dev libncursesw5-dev libreadline6-dev libdb5.3-dev libgdbm-dev libsqlite3-dev libssl-dev libbz2-dev libexpat1-dev liblzma-dev zlib1g-dev libffi-dev\u003c/code\u003e\u003c/p\u003e\n\u003cp\u003eBuild Python from scratch\u003c/p\u003e\n\u003cp\u003e\u003ccode\u003ewget https://www.python.org/ftp/python/3.9.18/Python-3.9.18.tar.xz\u003c/code\u003e\u003cbr\u003e\u003ccode\u003etar xf Python-3.9.18.tar.xz\u003c/code\u003e\u003cbr\u003e\u003ccode\u003ecd Python-3.9.18\u003c/code\u003e\u003cbr\u003e\u003ccode\u003e./configure --enable-optimizations\u0026nbsp;\u003c/code\u003e\u003cbr\u003e\u003ccode\u003esudo make altinstall\u003c/code\u003e\u003c/p\u003e\n\u003cp\u003eMake a virtual environment\u003c/p\u003e\n\u003cp\u003e\u003ccode\u003ePython-3.9.18/python -m venv --system-site-packages tf\u003c/code\u003e\u003c/p\u003e\n\u003cp\u003eNext we can install Pycoral\u003c/p\u003e\n\u003cp\u003e\u003ccode\u003eecho \"deb https://packages.cloud.google.com/apt coral-edgetpu-stable main\" | sudo tee /etc/apt/sources.list.d/coral-edgetpu.list\u003cbr\u003ecurl https://packages.cloud.google.com/apt/doc/apt-key.gpg | sudo apt-key add -\u003cbr\u003esudo apt-get update\u003cbr\u003esudo apt-get install libedgetpu1-std -y\u003cbr\u003esudo usermod -aG plugdev \u003c/code\u003e\u003c/p\u003e\n\u003cp\u003e\u003ccode\u003esudo ./tf/bin/pip3 install --extra-index-url https://google-coral.github.io/py-repo/ pycoral\u003c/code\u003e\u003c/p\u003e\n\u003cp\u003eInstall any extra python libraries\u003c/p\u003e\n\u003cp\u003e\u003ccode\u003esudo ./tf/bin/pip3 install opencv-python\u003c/code\u003e\u003c/p\u003e\n\u003cp\u003e\u003ccode\u003esudo apt install libcap-dev libcamera-dev\u0026nbsp;\u003c/code\u003e\u003c/p\u003e\n\u003cp\u003e\u003ccode\u003esudo ./tf/bin/pip3 install rpi-libcamera\u003c/code\u003e\u003c/p\u003e\n\u003cp\u003e\u003ccode\u003esudo ./tf/bin/pip3 install rpi-kms\u003c/code\u003e\u003c/p\u003e\n\u003cp\u003e\u003ccode\u003esudo ./tf/bin/pip3 install picamera2\u003c/code\u003e\u003c/p\u003e\n\u003cp\u003eNote: rpi-libcamera and rpi-kms may need to be updated if your system package is updated.\u003c/p\u003e\n\u003cp\u003eAs of 2/21/2024, If your are installing \u003ca title=\"rpi-libcamera 0.1a2\" href=\"https://pypi.org/project/rpi-libcamera/\" target=\"_blank\"\u003erpi-libcamera 0.1a2\u003c/a\u003e and have updated to libcamera0.2, you will need to run the following:\u003c/p\u003e\n\u003cp\u003e\u003ccode\u003ecd /usr/lib/aarch64-linux-gnu\u003c/code\u003e\u003c/p\u003e\n\u003cp\u003e\u003ccode\u003esudo ln -s /usr/lib/aarch64-linux-gnu/libcamera-base.so.0.2.0 libcamera-base.so.0.1\u003c/code\u003e\u003c/p\u003e\n\u003cp\u003e\u003ccode\u003esudo ln -s /usr/lib/aarch64-linux-gnu/libcamera.so.0.2.0 libcamera.so.0.1\u003c/code\u003e\u003c/p\u003e\n\u003cp\u003eRun the python virtual environment\u003c/p\u003e\n\u003cp\u003e\u003ccode\u003esource ./tf/bin/activate\u003c/code\u003e\u003c/p\u003e\n\u003cp\u003eAt this point you should be able to use the USB Accelerator against the pycoral repo: https://github.com/google-coral/pycoral.git\u003c/p\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n      ","metadata":{}}]