1# How to install ArmNN via our APT repository on Ubuntu's Launchpad 2 3* [Introduction](#introduction) 4* [Add the Ubuntu Launchpad PPA to your system](#addRepo) 5* [Outline of available packages](#availablePackages) 6* [Install desired combination of packages](#InstallPackages) 7* [Uninstall packages](#uninstallPackages) 8 9 10#### <a name="introduction">Introduction</a> 11These 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. 12The packages will also be added to Debian Bullseye, their progress can be tracked here: https://tracker.debian.org/pkg/armnn 13 14 15#### <a name="addRepo">Add the Ubuntu Launchpad PPA to your system</a> 16* Add the PPA to your sources using a command contained in software-properties-common package: 17 ``` 18 sudo apt install software-properties-common 19 sudo add-apt-repository ppa:armnn/ppa 20 sudo apt update 21 ``` 22* More information about our PPA and the Ubuntu Launchpad service can be found at [launchpad.net](https://launchpad.net/~armnn/+archive/ubuntu/ppa) 23#### <a name="availablePackages"> Outline of available packages</a> 24 25We provide a number of packages for each architecture; x86_64, aarch64 and armhf: 26 27##### x86_64 28* Runtime Packages 29``` 30libarmnn-cpuref-backend22_20.08-4_amd64.deb 31libarmnn-tfliteparser22_20.08-4_amd64.deb 32libarmnn22_20.08-4_amd64.deb 33python3-pyarmnn_20.08-4_amd64.deb 34``` 35* Development Packages 36``` 37libarmnn-dev_20.08-4_amd64.deb 38libarmnn-tfliteparser-dev_20.08-4_amd64.deb 39``` 40##### arm64 41* Runtime Packages 42``` 43libarmnn-aclcommon22_20.08-4_arm64.deb 44libarmnn-cpuacc-backend22_20.08-4_arm64.deb 45libarmnn-cpuref-backend22_20.08-4_arm64.deb 46libarmnn-gpuacc-backend22_20.08-4_arm64.deb 47libarmnn-tfliteparser22_20.08-4_arm64.deb 48libarmnn22_20.08-4_arm64.deb 49python3-pyarmnn_20.08-4_arm64.deb 50 51``` 52* Development Packages 53``` 54libarmnn-dev_20.08-4_arm64.deb 55libarmnn-tfliteparser-dev_20.08-4_arm64.deb 56 57``` 58##### armhf 59* Runtime Packages 60``` 61libarmnn-aclcommon22_20.08-4_armhf.deb 62libarmnn-cpuacc-backend22_20.08-4_armhf.deb 63libarmnn-cpuref-backend22_20.08-4_armhf.deb 64libarmnn-gpuacc-backend22_20.08-4_armhf.deb 65libarmnn-tfliteparser22_20.08-4_armhf.deb 66libarmnn22_20.08-4_armhf.deb 67python3-pyarmnn_20.08-4_armhf.deb 68 69``` 70* Development Packages 71``` 72libarmnn-dev_20.08-4_armhf.deb 73libarmnn-tfliteparser-dev_20.08-4_armhf.deb 74 75``` 76 77#### <a name="InstallPackages"> Install desired combination of packages</a> 78The easiest way to install all of the available packages for your systems architecture is to run the command: 79 80(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.) 81``` 82 sudo apt-get install -y python3-pyarmnn libarmnn-cpuacc-backend22 libarmnn-gpuacc-backend22 libarmnn-cpuref-backend22 83 # Verify installation via python: 84 python3 -c "import pyarmnn as ann;print(ann.GetVersion())" 85 # Returns '22.0.0' 86``` 87This will install PyArmnn and the three backends for Neon, Compute Library and our Reference Backend. 88It will also install their dependencies including the arm-compute-library package along with the Tensorflow Lite Parser and it's dependency ArmNN Core. 89If the user does not wish to use PyArmnn they can go up a level of dependencies and instead just install the Tensorflow Lite Parser: 90``` 91 sudo apt-get install -y libarmnn-tfliteparser22 libarmnn-gpuacc-backend22 92``` 93 94#### <a name="uninstallPackages"> Uninstall packages</a> 95The easiest way to uninstall all of the previously installed packages is to run the command: 96``` 97 sudo apt autoremove -y libarmnn22 98```