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 Arm NN core, TensorflowLite Parser
16 as well as PyArmNN for x86_64, Arm64 and Armhf for Ubuntu 20.04.
17 The packages will also be added to Debian Bullseye, their progress can be tracked here:
18 https://tracker.debian.org/pkg/armnn
21 ## Add the Ubuntu Launchpad PPA to your system
22 * Add the PPA to your sources using a command contained in software-properties-common package:
24 sudo apt install software-properties-common
25 sudo add-apt-repository ppa:armnn/ppa
28 * More information about our PPA and the Ubuntu Launchpad service can be found at [launchpad.net](https://launchpad.net/~armnn/+archive/ubuntu/ppa)
29 ## Outline of available packages
31 We provide a number of packages for each architecture; x86_64, aarch64 and armhf as outlined below.
33 ARMNN_MAJOR_VERSION: This is the ABI version of the Arm NN source that has been packaged based on
34 include/armnn/Version.hpp.
36 ARMNN_RELEASE_VERSION: This is the marketing release version based on the date source was released on github e.g. 20.11.
38 PACKAGE_VERSION: This is the version of the source package used to build the binaries packages from.
43 libarmnn-cpuref-backend{ARMNN_MAJOR_VERSION}_{ARMNN_RELEASE_VERSION}-{PACKAGE_VERSION}_amd64.deb
44 libarmnntfliteparser{ARMNN_MAJOR_VERSION}_{ARMNN_RELEASE_VERSION}-{PACKAGE_VERSION}_amd64.deb
45 libarmnn{ARMNN_MAJOR_VERSION}_{ARMNN_RELEASE_VERSION}-{PACKAGE_VERSION}_amd64.deb
46 python3-pyarmnn_{ARMNN_RELEASE_VERSION}-{PACKAGE_VERSION}_amd64.deb
48 * Development Packages
50 libarmnn-dev_{ARMNN_RELEASE_VERSION}-{PACKAGE_VERSION}_amd64.deb
51 libarmnntfliteparser-dev_{ARMNN_RELEASE_VERSION}-{PACKAGE_VERSION}_amd64.deb
53 * Dependency Packages (These are empty packages that provide a user-friendly name for other packages they will install)
55 armnn-latest-all_{ARMNN_RELEASE_VERSION}-{PACKAGE_VERSION}_amd64.deb
56 armnn-latest-ref_{ARMNN_RELEASE_VERSION}-{PACKAGE_VERSION}_amd64.deb
61 libarmnn-aclcommon{ARMNN_MAJOR_VERSION}_{ARMNN_RELEASE_VERSION}-{PACKAGE_VERSION}_arm64.deb
62 libarmnn-cpuacc-backend{ARMNN_MAJOR_VERSION}_{ARMNN_RELEASE_VERSION}-{PACKAGE_VERSION}_arm64.deb
63 libarmnn-cpuref-backend{ARMNN_MAJOR_VERSION}_{ARMNN_RELEASE_VERSION}-{PACKAGE_VERSION}_arm64.deb
64 libarmnn-gpuacc-backend{ARMNN_MAJOR_VERSION}_{ARMNN_RELEASE_VERSION}-{PACKAGE_VERSION}_arm64.deb
65 libarmnntfliteparser{ARMNN_MAJOR_VERSION}_{ARMNN_RELEASE_VERSION}-{PACKAGE_VERSION}_arm64.deb
66 libarmnn{ARMNN_MAJOR_VERSION}_{ARMNN_RELEASE_VERSION}-{PACKAGE_VERSION}_arm64.deb
67 python3-pyarmnn_{ARMNN_RELEASE_VERSION}-{PACKAGE_VERSION}_arm64.deb
70 * Development Packages
72 libarmnn-dev_{ARMNN_RELEASE_VERSION}-{PACKAGE_VERSION}_arm64.deb
73 libarmnntfliteparser-dev_{ARMNN_RELEASE_VERSION}-{PACKAGE_VERSION}_arm64.deb
76 * Dependency Packages (These are empty packages that provide a user-friendly name for other packages they will install)
78 armnn-latest-all_{ARMNN_RELEASE_VERSION}-{PACKAGE_VERSION}_arm64.deb
79 armnn-latest-cpu_{ARMNN_RELEASE_VERSION}-{PACKAGE_VERSION}_arm64.deb
80 armnn-latest-cpu-gpu_{ARMNN_RELEASE_VERSION}-{PACKAGE_VERSION}_arm64.deb
81 armnn-latest-cpu-gpu-ref_{ARMNN_RELEASE_VERSION}-{PACKAGE_VERSION}_arm64.deb
82 armnn-latest-gpu_{ARMNN_RELEASE_VERSION}-{PACKAGE_VERSION}_arm64.deb
83 armnn-latest-ref_{ARMNN_RELEASE_VERSION}-{PACKAGE_VERSION}_arm64.deb
88 libarmnn-aclcommon{ARMNN_MAJOR_VERSION}_{ARMNN_RELEASE_VERSION}-{PACKAGE_VERSION}_armhf.deb
89 libarmnn-cpuacc-backend{ARMNN_MAJOR_VERSION}_{ARMNN_RELEASE_VERSION}-{PACKAGE_VERSION}_armhf.deb
90 libarmnn-cpuref-backend{ARMNN_MAJOR_VERSION}_{ARMNN_RELEASE_VERSION}-{PACKAGE_VERSION}_armhf.deb
91 libarmnn-gpuacc-backend{ARMNN_MAJOR_VERSION}_{ARMNN_RELEASE_VERSION}-{PACKAGE_VERSION}_armhf.deb
92 libarmnntfliteparser{ARMNN_MAJOR_VERSION}_{ARMNN_RELEASE_VERSION}-{PACKAGE_VERSION}_armhf.deb
93 libarmnn{ARMNN_MAJOR_VERSION}_{ARMNN_RELEASE_VERSION}-{PACKAGE_VERSION}_armhf.deb
94 python3-pyarmnn_{ARMNN_RELEASE_VERSION}-{PACKAGE_VERSION}_armhf.deb
97 * Development Packages
99 libarmnn-dev_{ARMNN_RELEASE_VERSION}-{PACKAGE_VERSION}_armhf.deb
100 libarmnntfliteparser-dev_{ARMNN_RELEASE_VERSION}-{PACKAGE_VERSION}_armhf.deb
103 * Dependency Packages (These are empty packages that provide a user-friendly name for other packages they will install)
105 armnn-latest-all_{ARMNN_RELEASE_VERSION}-{PACKAGE_VERSION}_armhf.deb
106 armnn-latest-cpu_{ARMNN_RELEASE_VERSION}-{PACKAGE_VERSION}_armhf.deb
107 armnn-latest-cpu-gpu_{ARMNN_RELEASE_VERSION}-{PACKAGE_VERSION}_armhf.deb
108 armnn-latest-cpu-gpu-ref_{ARMNN_RELEASE_VERSION}-{PACKAGE_VERSION}_armhf.deb
109 armnn-latest-gpu_{ARMNN_RELEASE_VERSION}-{PACKAGE_VERSION}_armhf.deb
110 armnn-latest-ref_{ARMNN_RELEASE_VERSION}-{PACKAGE_VERSION}_amd64.deb
113 ## Install desired combination of packages
114 The easiest way to install all of the available packages for your systems architecture is to run the command:
117 sudo apt-get install -y python3-pyarmnn armnn-latest-all
118 # Verify installation via python:
119 python3 -c "import pyarmnn as ann;print(ann.GetVersion())"
120 # Returns '{ARMNN_MAJOR_VERSION}.0.0' e.g. 27.0.0
122 This will install PyArmNN and the three backends for Neon (CpuAcc), OpenCL (GpuAcc) and our Reference Backend.
123 It will also install their dependencies including the arm-compute-library package along with the Tensorflow Lite Parser
124 and it's dependency Arm NN Core.
125 If the user does not wish to use PyArmNN they can go up a level of dependencies and instead just install the
126 armnn-latest-all package:
128 # Install ArmNN Core, CpuAcc Backend, GpuAcc Backend and Reference Backend as well as the TensorFlow Lite Parser:
129 # (This will only install CpuAcc and GpuAcc Backends on arm64 and armhf architectures)
130 sudo apt-get install -y armnn-latest-all
132 # Install ArmNN Core, CpuAcc Backend as well as the TensorFlow Lite Parser:
133 sudo apt-get install -y armnn-latest-cpu
135 # Install ArmNN Core, CpuAcc Backend, GpuAcc Backend as well as the TensorFlow Lite Parser:
136 sudo apt-get install -y armnn-latest-cpu-gpu
138 # Install ArmNN Core, GpuAcc Backend as well as the TensorFlow Lite Parser:
139 sudo apt-get install -y armnn-latest-gpu
141 # Install ArmNN Core, Reference Backend as well as the TensorFlow Lite Parser:
142 sudo apt-get install -y armnn-latest-ref
145 ## Installation of specific ABI versioned packages
146 Due to Debian Packaging requiring the pristine tarball from our Github release, the version on Launchpad may not align
147 with the released version on Github depending on the complexity of newly added features.
148 In order to check for the latest available Arm NN version use apt-cache search:
150 apt-cache search libarmnn
152 # This returns a list of matching packages including versions from previous releases
153 libarmnn-cpuref-backend23 - Arm NN is an inference engine for CPUs, GPUs and NPUs
154 libarmnn-cpuref-backend24 - Arm NN is an inference engine for CPUs, GPUs and NPUs
155 libarmnn-dev - Arm NN is an inference engine for CPUs, GPUs and NPUs
156 libarmnntfliteparser-dev - Arm NN is an inference engine for CPUs, GPUs and NPUs # Note: removal of dash to suit debian naming conventions
157 libarmnn-tfliteparser23 - Arm NN is an inference engine for CPUs, GPUs and NPUs
158 libarmnntfliteparser24 - Arm NN is an inference engine for CPUs, GPUs and NPUs # Note: removal of dash to suit debian naming conventions
159 libarmnn23 - Arm NN is an inference engine for CPUs, GPUs and NPUs
160 libarmnn24 - Arm NN is an inference engine for CPUs, GPUs and NPUs
161 libarmnn25 - Arm NN is an inference engine for CPUs, GPUs and NPUs
162 libarmnn-aclcommon23 - Arm NN is an inference engine for CPUs, GPUs and NPUs
163 libarmnnaclcommon24 - Arm NN is an inference engine for CPUs, GPUs and NPUs # Note: removal of dash to suit debian naming conventions
164 libarmnn-cpuacc-backend23 - Arm NN is an inference engine for CPUs, GPUs and NPUs
165 libarmnn-cpuacc-backend24 - Arm NN is an inference engine for CPUs, GPUs and NPUs
166 libarmnn-gpuacc-backend23 - Arm NN is an inference engine for CPUs, GPUs and NPUs
167 libarmnn-gpuacc-backend24 - Arm NN is an inference engine for CPUs, GPUs and NPUs
170 # Export the ARMNN_MAJOR_VERSION to the latest visible e.g. libarmnn25 to allow installation using the below examples
171 export ARMNN_MAJOR_VERSION=27
173 # As the Tensorflow Lite Parser is now ABI stable it will have a different version to ARMNN_MAJOR_VERSION please choose latest version:
174 apt-cache search libarmnntfliteparser
175 # Returns e.g. libarmnntfliteparser24 so we then export that version, for reference this comes from include/armnnTfLiteParser/Version.hpp:
176 export TFLITE_PARSER_VERSION=24
178 sudo apt-get install -y libarmnntfliteparser${TFLITE_PARSER_VERSION} libarmnn-cpuacc-backend${ARMNN_MAJOR_VERSION}
181 ## Uninstall packages
182 The easiest way to uninstall all of the previously installed packages is to run the command:
184 sudo apt-get purge -y armnn-latest-all
185 sudo apt autoremove -y armnn-latest-all