From 42bd4f177ff6375889e1f35b4fad708af142d117 Mon Sep 17 00:00:00 2001 From: Francis Murtagh Date: Mon, 16 Nov 2020 14:43:37 +0000 Subject: IVGCVSW-5311 Debian Packaging - Host packages in public PPA * Add guide to github README.md Signed-off-by: Francis Murtagh Change-Id: I23df585ee24e90629f821af0c780ad40d8c20f97 --- InstallationViaAptRepository.md | 98 +++++++++++++++++++++++++++++++++++++++++ README.md | 2 + 2 files changed, 100 insertions(+) create mode 100644 InstallationViaAptRepository.md diff --git a/InstallationViaAptRepository.md b/InstallationViaAptRepository.md new file mode 100644 index 0000000000..e855ba60d7 --- /dev/null +++ b/InstallationViaAptRepository.md @@ -0,0 +1,98 @@ +# How to install ArmNN via our APT repository on Ubuntu's Launchpad + +* [Introduction](#introduction) +* [Add the Ubuntu Launchpad PPA to your system](#addRepo) +* [Outline of available packages](#availablePackages) +* [Install desired combination of packages](#InstallPackages) +* [Uninstall packages](#uninstallPackages) + + +#### Introduction +These are the step by step instructions on how to install the ArmNN core, TensorflowLite Parser as well as PyArmnn for x86_64, Arm64 and Armhf for Ubuntu 20.04. +The packages will also be added to Debian Bullseye, their progress can be tracked here: https://tracker.debian.org/pkg/armnn + + +#### Add the Ubuntu Launchpad PPA to your system +* Add the PPA to your sources using a command contained in software-properties-common package: + ``` + sudo apt install software-properties-common + sudo add-apt-repository ppa:armnn/ppa + sudo apt update + ``` +* More information about our PPA and the Ubuntu Launchpad service can be found at [launchpad.net](https://launchpad.net/~armnn/+archive/ubuntu/ppa) +#### Outline of available packages + +We provide a number of packages for each architecture; x86_64, aarch64 and armhf: + +##### x86_64 +* Runtime Packages +``` +libarmnn-cpuref-backend22_20.08-4_amd64.deb +libarmnn-tfliteparser22_20.08-4_amd64.deb +libarmnn22_20.08-4_amd64.deb +python3-pyarmnn_20.08-4_amd64.deb +``` +* Development Packages +``` +libarmnn-dev_20.08-4_amd64.deb +libarmnn-tfliteparser-dev_20.08-4_amd64.deb +``` +##### arm64 +* Runtime Packages +``` +libarmnn-aclcommon22_20.08-4_arm64.deb +libarmnn-cpuacc-backend22_20.08-4_arm64.deb +libarmnn-cpuref-backend22_20.08-4_arm64.deb +libarmnn-gpuacc-backend22_20.08-4_arm64.deb +libarmnn-tfliteparser22_20.08-4_arm64.deb +libarmnn22_20.08-4_arm64.deb +python3-pyarmnn_20.08-4_arm64.deb + +``` +* Development Packages +``` +libarmnn-dev_20.08-4_arm64.deb +libarmnn-tfliteparser-dev_20.08-4_arm64.deb + +``` +##### armhf +* Runtime Packages +``` +libarmnn-aclcommon22_20.08-4_armhf.deb +libarmnn-cpuacc-backend22_20.08-4_armhf.deb +libarmnn-cpuref-backend22_20.08-4_armhf.deb +libarmnn-gpuacc-backend22_20.08-4_armhf.deb +libarmnn-tfliteparser22_20.08-4_armhf.deb +libarmnn22_20.08-4_armhf.deb +python3-pyarmnn_20.08-4_armhf.deb + +``` +* Development Packages +``` +libarmnn-dev_20.08-4_armhf.deb +libarmnn-tfliteparser-dev_20.08-4_armhf.deb + +``` + +#### Install desired combination of packages +The easiest way to install all of the available packages for your systems architecture is to run the command: + +(Please Note: libarmnn-cpuacc-backend has been built with NEON support, installing this backend on an armhf device not supporting NEON may cause a crash/undefined behaviour.) +``` + sudo apt-get install -y python3-pyarmnn libarmnn-cpuacc-backend22 libarmnn-gpuacc-backend22 libarmnn-cpuref-backend22 + # Verify installation via python: + python3 -c "import pyarmnn as ann;print(ann.GetVersion())" + # Returns '22.0.0' +``` +This will install PyArmnn and the three backends for Neon, Compute Library and our Reference Backend. +It will also install their dependencies including the arm-compute-library package along with the Tensorflow Lite Parser and it's dependency ArmNN Core. +If the user does not wish to use PyArmnn they can go up a level of dependencies and instead just install the Tensorflow Lite Parser: +``` + sudo apt-get install -y libarmnn-tfliteparser22 libarmnn-gpuacc-backend22 +``` + +#### Uninstall packages +The easiest way to uninstall all of the previously installed packages is to run the command: +``` + sudo apt autoremove -y libarmnn22 +``` \ No newline at end of file diff --git a/README.md b/README.md index ad71249578..1a8770414f 100644 --- a/README.md +++ b/README.md @@ -12,6 +12,8 @@ There is a getting started guide here using ONNX: