1 # How to install ArmNN via our APT repository on Ubuntu's Launchpad
3 * [Introduction](#introduction)
4 * [Add the Ubuntu Launchpad PPA to your system](#add-the-ubuntu-launchpad-ppa-to-your-system)
5 * [Outline of available packages](#outline-of-available-packages)
9 * [Check latest version of packages](#check-latest-version-of-packages)
10 * [Install desired combination of packages](#install-desired-combination-of-packages)
11 * [Uninstall packages](#uninstall-packages)
15 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.
16 The packages will also be added to Debian Bullseye, their progress can be tracked here: https://tracker.debian.org/pkg/armnn
19 ## Add the Ubuntu Launchpad PPA to your system
20 * Add the PPA to your sources using a command contained in software-properties-common package:
22 sudo apt install software-properties-common
23 sudo add-apt-repository ppa:armnn/ppa
26 * More information about our PPA and the Ubuntu Launchpad service can be found at [launchpad.net](https://launchpad.net/~armnn/+archive/ubuntu/ppa)
27 ## Outline of available packages
29 We provide a number of packages for each architecture; x86_64, aarch64 and armhf as outlined below.
31 ARMNN_MAJOR_VERSION: This is the ABI version of the ArmNN source that has been packaged based on include/armnn/Version.hpp.
33 ARMNN_RELEASE_VERSION: This is the marketing release version based on the date source was released on github e.g. 20.11.
35 PACKAGE_VERSION: This is the version of the source package used to build the binaries packages from.
40 libarmnn-cpuref-backend{ARMNN_MAJOR_VERSION}_{ARMNN_RELEASE_VERSION}-{PACKAGE_VERSION}_amd64.deb
41 libarmnn-tfliteparser{ARMNN_MAJOR_VERSION}_{ARMNN_RELEASE_VERSION}-{PACKAGE_VERSION}_amd64.deb
42 libarmnn{ARMNN_MAJOR_VERSION}_{ARMNN_RELEASE_VERSION}-{PACKAGE_VERSION}_amd64.deb
43 python3-pyarmnn_{ARMNN_RELEASE_VERSION}-{PACKAGE_VERSION}_amd64.deb
45 * Development Packages
47 libarmnn-dev_{ARMNN_RELEASE_VERSION}-{PACKAGE_VERSION}_amd64.deb
48 libarmnn-tfliteparser-dev_{ARMNN_RELEASE_VERSION}-{PACKAGE_VERSION}_amd64.deb
53 libarmnn-aclcommon{ARMNN_MAJOR_VERSION}_{ARMNN_RELEASE_VERSION}-{PACKAGE_VERSION}_arm64.deb
54 libarmnn-cpuacc-backend{ARMNN_MAJOR_VERSION}_{ARMNN_RELEASE_VERSION}-{PACKAGE_VERSION}_arm64.deb
55 libarmnn-cpuref-backend{ARMNN_MAJOR_VERSION}_{ARMNN_RELEASE_VERSION}-{PACKAGE_VERSION}_arm64.deb
56 libarmnn-gpuacc-backend{ARMNN_MAJOR_VERSION}_{ARMNN_RELEASE_VERSION}-{PACKAGE_VERSION}_arm64.deb
57 libarmnn-tfliteparser{ARMNN_MAJOR_VERSION}_{ARMNN_RELEASE_VERSION}-{PACKAGE_VERSION}_arm64.deb
58 libarmnn{ARMNN_MAJOR_VERSION}_{ARMNN_RELEASE_VERSION}-{PACKAGE_VERSION}_arm64.deb
59 python3-pyarmnn_{ARMNN_RELEASE_VERSION}-{PACKAGE_VERSION}_arm64.deb
62 * Development Packages
64 libarmnn-dev_{ARMNN_RELEASE_VERSION}-{PACKAGE_VERSION}_arm64.deb
65 libarmnn-tfliteparser-dev_{ARMNN_RELEASE_VERSION}-{PACKAGE_VERSION}_arm64.deb
71 libarmnn-aclcommon{ARMNN_MAJOR_VERSION}_{ARMNN_RELEASE_VERSION}-{PACKAGE_VERSION}_armhf.deb
72 libarmnn-cpuacc-backend{ARMNN_MAJOR_VERSION}_{ARMNN_RELEASE_VERSION}-{PACKAGE_VERSION}_armhf.deb
73 libarmnn-cpuref-backend{ARMNN_MAJOR_VERSION}_{ARMNN_RELEASE_VERSION}-{PACKAGE_VERSION}_armhf.deb
74 libarmnn-gpuacc-backend{ARMNN_MAJOR_VERSION}_{ARMNN_RELEASE_VERSION}-{PACKAGE_VERSION}_armhf.deb
75 libarmnn-tfliteparser{ARMNN_MAJOR_VERSION}_{ARMNN_RELEASE_VERSION}-{PACKAGE_VERSION}_armhf.deb
76 libarmnn{ARMNN_MAJOR_VERSION}_{ARMNN_RELEASE_VERSION}-{PACKAGE_VERSION}_armhf.deb
77 python3-pyarmnn_{ARMNN_RELEASE_VERSION}-{PACKAGE_VERSION}_armhf.deb
80 * Development Packages
82 libarmnn-dev_{ARMNN_RELEASE_VERSION}-{PACKAGE_VERSION}_armhf.deb
83 libarmnn-tfliteparser-dev_{ARMNN_RELEASE_VERSION}-{PACKAGE_VERSION}_armhf.deb
87 ## Check latest version of packages
88 Due to Debian Packaging requiring the pristine tarball from our Github release, the version on Launchpad may not align with the released version on Github depending on the complexity of newly added features.
89 In order to check for the latest available ArmNN version use apt-cache search:
91 apt-cache search libarmnn
93 # This returns a list of matching packages, the latest being libarmnn23 i.e. ARMNN_MAJOR_VERSION=23
94 libarmnn-cpuref-backend22 - Arm NN is an inference engine for CPUs, GPUs and NPUs
95 libarmnn-cpuref-backend23 - Arm NN is an inference engine for CPUs, GPUs and NPUs
96 libarmnn-dev - Arm NN is an inference engine for CPUs, GPUs and NPUs
97 libarmnn-tfliteparser-dev - Arm NN is an inference engine for CPUs, GPUs and NPUs
98 libarmnn-tfliteparser22 - Arm NN is an inference engine for CPUs, GPUs and NPUs
99 libarmnn-tfliteparser23 - Arm NN is an inference engine for CPUs, GPUs and NPUs
100 libarmnn22 - Arm NN is an inference engine for CPUs, GPUs and NPUs
101 libarmnn23 - Arm NN is an inference engine for CPUs, GPUs and NPUs
102 libarmnn-aclcommon22 - Arm NN is an inference engine for CPUs, GPUs and NPUs
103 libarmnn-aclcommon23 - Arm NN is an inference engine for CPUs, GPUs and NPUs
104 libarmnn-cpuacc-backend22 - Arm NN is an inference engine for CPUs, GPUs and NPUs
105 libarmnn-cpuacc-backend23 - Arm NN is an inference engine for CPUs, GPUs and NPUs
106 libarmnn-gpuacc-backend22 - Arm NN is an inference engine for CPUs, GPUs and NPUs
107 libarmnn-gpuacc-backend23 - Arm NN is an inference engine for CPUs, GPUs and NPUs
110 # Export the ARMNN_MAJOR_VERSION to allow installation using the below examples
111 export ARMNN_MAJOR_VERSION=23
115 ## Install desired combination of packages
116 The easiest way to install all of the available packages for your systems architecture is to run the command:
119 sudo apt-get install -y python3-pyarmnn libarmnn-cpuacc-backend${ARMNN_MAJOR_VERSION} libarmnn-gpuacc-backend${ARMNN_MAJOR_VERSION} libarmnn-cpuref-backend${ARMNN_MAJOR_VERSION}
120 # Verify installation via python:
121 python3 -c "import pyarmnn as ann;print(ann.GetVersion())"
122 # Returns '{ARMNN_MAJOR_VERSION}.0.0' e.g. 23.0.0
124 This will install PyArmnn and the three backends for Neon, Compute Library and our Reference Backend.
125 It will also install their dependencies including the arm-compute-library package along with the Tensorflow Lite Parser and it's dependency ArmNN Core.
126 If the user does not wish to use PyArmnn they can go up a level of dependencies and instead just install the Tensorflow Lite Parser:
128 sudo apt-get install -y libarmnn-tfliteparser${ARMNN_MAJOR_VERSION} libarmnn-gpuacc-backend${ARMNN_MAJOR_VERSION}
131 ## Uninstall packages
132 The easiest way to uninstall all of the previously installed packages is to run the command:
134 sudo apt autoremove -y libarmnn${ARMNN_MAJOR_VERSION}