diff options
| author | Nikhil Raj <nikhil.raj@arm.com> | 2022-11-01 12:28:22 +0000 |
|---|---|---|
| committer | Nikhil Raj <nikhil.raj@arm.com> | 2022-11-08 12:43:39 +0000 |
| commit | 717a95ee6fb732bf22adee1e4f55b7ea30db5052 (patch) | |
| tree | cd5b1b1894a2f9f194d058f53d80f4f6c7680050 | |
| parent | 730e82503112dee08dad51c9613bd0ba66dafc9a (diff) | |
| download | armnn-717a95ee6fb732bf22adee1e4f55b7ea30db5052.tar.gz | |
Update Readme files with newer versions of tools added during 22.11
* Flatbuffer version updated to 2.0.6
* Android NDK version updated to r25
* Removed cross-compilation guide as its been moved to build-tools
* Android binaries updated in Readme
Signed-off-by: Nikhil Raj <nikhil.raj@arm.com>
Change-Id: Ia7054707c9463d8ce8b344ec5d86fdd83424b2c3
| -rw-r--r-- | BuildGuideAndroidNDK.md | 18 | ||||
| -rw-r--r-- | BuildGuideCrossCompilation.md | 382 | ||||
| -rw-r--r-- | BuildGuideCrossCompilation.md.license | 4 | ||||
| -rw-r--r-- | README.md | 9 | ||||
| -rw-r--r-- | samples/ObjectDetection/Readme.md | 18 | ||||
| -rw-r--r-- | shim/BuildGuideShimSupportLibrary.md | 6 |
6 files changed, 26 insertions, 411 deletions
diff --git a/BuildGuideAndroidNDK.md b/BuildGuideAndroidNDK.md index 3f3f642d14..7cbd4f9fb3 100644 --- a/BuildGuideAndroidNDK.md +++ b/BuildGuideAndroidNDK.md @@ -26,16 +26,16 @@ All downloaded or generated files will be saved inside the `$HOME/armnn-devenv` mkdir -p $HOME/armnn-devenv/ cd $HOME/armnn-devenv/ # For Mac OS, change the NDK download link accordingly. - wget https://dl.google.com/android/repository/android-ndk-r20b-linux-x86_64.zip - unzip android-ndk-r20b-linux-x86_64.zip - export NDK=$HOME/armnn-devenv/android-ndk-r20b + wget https://dl.google.com/android/repository/android-ndk-r25-linux.zip + unzip android-ndk-r25.zip + export NDK=$HOME/armnn-devenv/android-ndk-r25 export NDK_TOOLCHAIN_ROOT=$NDK/toolchains/llvm/prebuilt/linux-x86_64 export PATH=$NDK_TOOLCHAIN_ROOT/bin/:$PATH # You may want to append the above export variables commands to your `~/.bashrc` (or `~/.bash_profile` in Mac OS). ``` -* With the android ndk-20b, you don't need to use the make_standalone_toolchain script to create a toolchain for a specific version of android. Android's current preference is for you to just specify the architecture and operating system while setting the compiler and just use the ndk directory. +* With the android ndk-25, you don't need to use the make_standalone_toolchain script to create a toolchain for a specific version of android. Android's current preference is for you to just specify the architecture and operating system while setting the compiler and just use the ndk directory. ## Install Cmake Cmake 3.19rc3 is required to build Arm NN. @@ -97,13 +97,13 @@ Note: The ANDROID_API variable should be set to the Android API version number y * Download Flatbuffers ```bash cd $HOME/armnn-devenv -wget -O flatbuffers-1.12.0.tar.gz https://github.com/google/flatbuffers/archive/v1.12.0.tar.gz -tar xf flatbuffers-1.12.0.tar.gz +wget https://github.com/google/flatbuffers/archive/v2.0.6.tar.gz +tar xf v2.0.6.tar.gz ``` * Build Flatbuffers ```bash -cd flatbuffers-1.12.0 +cd flatbuffers-2.0.6 rm -f CMakeCache.txt rm -rf build mkdir build @@ -189,7 +189,7 @@ cmake .. \ -DARMCOMPUTENEON=1 -DARMCOMPUTECL=1 -DARMNNREF=1 \ -DPROTOBUF_ROOT=$HOME/armnn-devenv/google/arm64_pb_install/ -DFLATBUFFERS_ROOT=$HOME/armnn-devenv/flatbuffers \ - -DFLATC_DIR=$HOME/armnn-devenv/flatbuffers-1.12.0/build \ + -DFLATC_DIR=$HOME/armnn-devenv/flatbuffers-2.0.6/build \ ``` To include standalone sample dynamic backend tests, add the argument to enable the tests and the dynamic backend path to the CMake command: @@ -225,7 +225,7 @@ cmake \ -DCMAKE_SYSTEM_NAME=Android \ -DCMAKE_SYSTEM_VERSION=$ANDROID_API \ -DCMAKE_ANDROID_ARCH_ABI=arm64-v8a \ --DCMAKE_SYSROOT=$HOME/armnn-devenv/android-ndk-r20b/toolchains/llvm/prebuilt/linux-x86_64/sysroot \ +-DCMAKE_SYSROOT=$HOME/armnn-devenv/android-ndk-r25/toolchains/llvm/prebuilt/linux-x86_64/sysroot \ -DCMAKE_CXX_FLAGS=--std=c++14 \ -DCMAKE_EXE_LINKER_FLAGS="-pie -llog" \ -DCMAKE_MODULE_LINKER_FLAGS="-llog" \ diff --git a/BuildGuideCrossCompilation.md b/BuildGuideCrossCompilation.md deleted file mode 100644 index 9a57942baa..0000000000 --- a/BuildGuideCrossCompilation.md +++ /dev/null @@ -1,382 +0,0 @@ -# How to Cross-Compile Arm NN on x86_64 for arm64 - -- [Introduction](#introduction) -- [Cross-compiling ToolChain](#cross-compiling-toolchain) -- [Install Cmake](#build-cmake) -- [Build and install Google's Protobuf library](#build-and-install-google-s-protobuf-library) -- [Download Arm NN](#download-arm-nn) -- [Build Arm Compute Library](#build-arm-compute-library) -- [Build Flatbuffer](#build-flatbuffer) -- [Build Onnx](#build-onnx) -- [Build TfLite](#build-tflite) -- [Build Arm NN](#build-armnn) -- [Generate TF Lite Schema](#generate-tflite-schema) -- [Build Standalone Sample Dynamic Backend](#build-standalone-sample-dynamic-backend) -- [Run Unit Tests](#run-unit-tests) -- [Troubleshooting and Errors:](#troubleshooting-and-errors-) - -### NOTE: This build guide is being replaced by the [Arm NN Build Tool](build-tool/README.md) and will be removed soon. Please use the [Arm NN Build Tool](build-tool/README.md) for a user-friendly way to build Arm NN and its dependencies. - -## Introduction -These are the step by step instructions on Cross-Compiling Arm NN under an x86_64 system to target an Arm64 Ubuntu Linux system. This build flow has been tested with Ubuntu 18.04 and 20.04 and it depends on the same version of Ubuntu or Debian being installed on both the build host and target machines. The instructions assume you are using a bash shell and show how to build the Arm NN core library, Protobuf, Tflite, Flatbuffer and Compute Libraries. -Start by creating a directory to contain all components: - -``` -mkdir $HOME/armnn-devenv -cd $HOME/armnn-devenv -``` - -## Cross-compiling ToolChain -* Install the standard cross-compilation libraries for arm64: -``` -sudo apt install crossbuild-essential-arm64 -``` - -## Install Cmake -Cmake 3.19rc3 is required to build TF Lite Delegate. - -``` -sudo apt-get install libssl-dev -wget https://github.com/Kitware/CMake/releases/download/v3.19.0-rc3/cmake-3.19.0-rc3.tar.gz -tar -zxvf cmake-3.19.0-rc3.tar.gz -cd cmake-3.19.0-rc3 -./bootstrap --prefix=$HOME/armnn-devenv/cmake/install -make all install -cd.. -``` - - -## Build and install Google's Protobuf library - -We support protobuf version 3.12.0 -* Get protobuf from here: https://github.com/protocolbuffers/protobuf: - (Requires Git if not previously installed: `sudo apt install git`) -```bash -git clone -b v3.12.0 https://github.com/google/protobuf.git protobuf -cd protobuf -git submodule update --init --recursive -./autogen.sh -``` -* Build a native (x86_64) version of the protobuf libraries and compiler (protoc): - (Requires cUrl, autoconf, llibtool, and other build dependencies if not previously installed: sudo apt install curl autoconf libtool build-essential g++) -``` -mkdir x86_64_build -cd x86_64_build -../configure --prefix=$HOME/armnn-devenv/google/x86_64_pb_install -make install -j16 -cd .. -``` -* Build the arm64 version of the protobuf libraries: -``` -mkdir arm64_build -cd arm64_build -CC=aarch64-linux-gnu-gcc \ -CXX=aarch64-linux-gnu-g++ \ -../configure --host=aarch64-linux \ ---prefix=$HOME/armnn-devenv/google/arm64_pb_install \ ---with-protoc=$HOME/armnn-devenv/google/x86_64_pb_install/bin/protoc -make install -j16 -cd .. -``` - -## Download Arm NN -* Clone Arm NN: -```bash -cd $HOME/armnn-devenv -git clone https://github.com/ARM-software/armnn.git -``` - -* Checkout Arm NN branch: -```bash -cd armnn -git checkout <branch_name> -git pull -``` -For example, if you want to check out the 21.11 release branch: -```bash -git checkout branches/armnn_21_11 -git pull -``` - -## Build Arm Compute Library -* Clone Arm Compute Library: - -```bash -cd $HOME/armnn-devenv -git clone https://github.com/ARM-software/ComputeLibrary.git -``` -* Checkout Arm Compute Library release tag: -```bash -cd ComputeLibrary -git checkout <tag_name> -``` -Arm NN and Arm Compute Library are developed closely together. If you would like to use the Arm NN 21.11 release you will need the 21.11 release of ACL too. For example, if you want to checkout the 21.11 release tag: -```bash -git checkout v21.11 -``` -Arm NN provides a script that downloads the version of Arm Compute Library that Arm NN was tested with: -```bash -git checkout $(../armnn/scripts/get_compute_library.sh -p) -``` -* Build the Arm Compute Library: - (Requires SCons if not previously installed: `sudo apt install scons`) -```bash -scons arch=arm64-v8a neon=1 opencl=1 embed_kernels=1 extra_cxx_flags="-fPIC" -j4 -``` - -## Build Flatbuffer -* Building Flatbuffer version 1.12.0 -```bash -cd $HOME/armnn-devenv -wget -O flatbuffers-1.12.0.tar.gz https://github.com/google/flatbuffers/archive/v1.12.0.tar.gz -tar xf flatbuffers-1.12.0.tar.gz -cd flatbuffers-1.12.0 -rm -f CMakeCache.txt -mkdir build -cd build -cmake .. -DFLATBUFFERS_BUILD_FLATC=1 \ - -DCMAKE_INSTALL_PREFIX:PATH=$HOME/armnn-devenv/flatbuffers \ - -DFLATBUFFERS_BUILD_TESTS=0 -make all install -``` - -* Build arm64 version of flatbuffer -```bash -cd .. -mkdir build-arm64 -cd build-arm64 -# Add -fPIC to allow us to use the libraries in shared objects. -CXXFLAGS="-fPIC" cmake .. -DCMAKE_C_COMPILER=/usr/bin/aarch64-linux-gnu-gcc \ - -DCMAKE_CXX_COMPILER=/usr/bin/aarch64-linux-gnu-g++ \ - -DFLATBUFFERS_BUILD_FLATC=1 \ - -DCMAKE_INSTALL_PREFIX:PATH=$HOME/armnn-devenv/flatbuffers-arm64 \ - -DFLATBUFFERS_BUILD_TESTS=0 -make all install -``` - -## Build Onnx -* Building Onnx -```bash -cd $HOME/armnn-devenv -git clone https://github.com/onnx/onnx.git -cd onnx -git fetch https://github.com/onnx/onnx.git 553df22c67bee5f0fe6599cff60f1afc6748c635 && git checkout FETCH_HEAD -LD_LIBRARY_PATH=$HOME/armnn-devenv/google/x86_64_pb_install/lib:$LD_LIBRARY_PATH \ -$HOME/armnn-devenv/google/x86_64_pb_install/bin/protoc \ -onnx/onnx.proto --proto_path=. --proto_path=../google/x86_64_pb_install/include --cpp_out $HOME/armnn-devenv/onnx -``` - -## Build TfLite -* Arm NN provides a script, armnn/scripts/get_tensorflow.sh, that can be used to check out the version of TensorFlow that Arm NN was tested with: -```bash -cd $HOME/armnn-devenv -git clone https://github.com/tensorflow/tensorflow.git -cd tensorflow/ -git checkout $(../armnn/scripts/get_tensorflow.sh -p) # Checks out the latest tested version of TF -cd .. -``` - -* You will need to download gcc-arm-8.3-2019.03 toolchain and continue building TF Lite as following: -``` -curl -LO https://storage.googleapis.com/mirror.tensorflow.org/developer.arm.com/media/Files/downloads/gnu-a/8.3-2019.03/binrel/gcc-arm-8.3-2019.03-x86_64-aarch64-linux-gnu.tar.xz -mkdir tflite-toolchains -tar xvf gcc-arm-8.3-2019.03-x86_64-aarch64-linux-gnu.tar.xz -C tflite-toolchains -mkdir -p tflite/build -cd tflite/build -ARMCC_PREFIX=$HOME/armnn-devenv/tflite-toolchains/gcc-arm-8.3-2019.03-x86_64-aarch64-linux-gnu/bin/aarch64-linux-gnu- \ -ARMCC_FLAGS="-funsafe-math-optimizations" \ -cmake -DCMAKE_C_COMPILER=${ARMCC_PREFIX}gcc \ - -DCMAKE_CXX_COMPILER=${ARMCC_PREFIX}g++ \ - -DCMAKE_C_FLAGS="${ARMCC_FLAGS}" -DCMAKE_CXX_FLAGS="${ARMCC_FLAGS}" \ - -DCMAKE_VERBOSE_MAKEFILE:BOOL=ON -DCMAKE_SYSTEM_NAME=Linux \ - -DTFLITE_ENABLE_XNNPACK=OFF \ - -DCMAKE_SYSTEM_PROCESSOR=aarch64 \ - $HOME/armnn-devenv/tensorflow/tensorflow/lite/ \ -cmake --build . -``` - -## Generate TF Lite Schema -``` -cd $HOME/armnn-devenv/tflite -cp $HOME/armnn-devenv/tensorflow/tensorflow/lite/schema/schema.fbs . -../flatbuffers-1.12.0/build/flatc -c --gen-object-api --reflect-types --reflect-names schema.fbs -``` - -## Build Arm NN -* Compile Arm NN for arm64: -```bash -cd $HOME/armnn-devenv/armnn -mkdir build -cd build -``` - -* Use CMake to configure your build environment, update the following script and run it from the armnn/build directory to set up the Arm NN build: -```bash -#!/bin/bash -CXX=aarch64-linux-gnu-g++ CC=aarch64-linux-gnu-gcc cmake .. \ --DARMCOMPUTE_ROOT=$HOME/armnn-devenv/ComputeLibrary \ --DARMCOMPUTE_BUILD_DIR=$HOME/armnn-devenv/ComputeLibrary/build/ \ --DARMCOMPUTENEON=1 -DARMCOMPUTECL=1 -DARMNNREF=1 \ --DONNX_GENERATED_SOURCES=$HOME/armnn-devenv/onnx \ --DBUILD_ONNX_PARSER=1 \ --DBUILD_TF_LITE_PARSER=1 \ --DTENSORFLOW_ROOT=$HOME/armnn-devenv/tensorflow \ --DTF_LITE_SCHEMA_INCLUDE_PATH=$WORKING_DIR/tflite \ --DFLATBUFFERS_ROOT=$HOME/armnn-devenv/flatbuffers-arm64 \ --DFLATC_DIR=$HOME/armnn-devenv/flatbuffers-1.12.0/build \ --DPROTOBUF_ROOT=$HOME/armnn-devenv/google/x86_64_pb_install \ --DPROTOBUF_LIBRARY_DEBUG=$HOME/armnn-devenv/google/arm64_pb_install/lib/libprotobuf.so.23.0.0 \ --DPROTOBUF_LIBRARY_RELEASE=$HOME/armnn-devenv/google/arm64_pb_install/lib/libprotobuf.so.23.0.0 -``` - -* If you want to include standalone sample dynamic backend tests, add the argument to enable the tests and the dynamic backend path to the CMake command: -```bash --DSAMPLE_DYNAMIC_BACKEND=1 \ --DDYNAMIC_BACKEND_PATHS=$SAMPLE_DYNAMIC_BACKEND_PATH -``` -* If you want to build Arm NN TF Lite Delegate, add the arguments: -```bash --DTFLITE_LIB_ROOT=$HOME/armnn-devenv/tflite/build \ --DBUILD_ARMNN_TFLITE_DELEGATE=1 -``` -* Run the build -```bash -make -j32 -``` - -## Build Standalone Sample Dynamic Backend -* The sample dynamic backend is located in armnn/src/dynamic/sample -```bash -cd $HOME/armnn-devenv/armnn/src/dynamic/sample -mkdir build -cd build -``` - -* Use CMake to configure your build environment, update the following script and run it from the armnn/src/dynamic/sample/build directory to set up the Arm NN build: -```bash -#!/bin/bash -CXX=aarch64-linux-gnu-g++ CC=aarch64-linux-gnu-gcc cmake .. \ --DCMAKE_CXX_FLAGS=--std=c++14 \ --DARMNN_PATH=$HOME/armnn-devenv/armnn/build/libarmnn.so -``` - -* Run the build -```bash -make -``` - -## Run Unit Tests -* Copy the build folder to an arm64 linux machine -* Copy the libprotobuf.so.23.0.0 library file to the build folder -* If you enable the standalone sample dynamic tests, also copy libArm_SampleDynamic_backend.so library file to the folder specified as $SAMPLE_DYNAMIC_BACKEND_PATH when you build Arm NN -* cd to the build folder on your arm64 machine and set your LD_LIBRARY_PATH to its current location: - -```bash -cd build/ -``` - -* Create a symbolic link to libprotobuf.so.23.0.0: - -```bash -ln -s libprotobuf.so.23.0.0 ./libprotobuf.so.23 -``` - -* Run the UnitTests: - -```bash -LD_LIBRARY_PATH=./:$LD_LIBRARY_PATH ./UnitTests -[doctest] doctest version is "2.4.6" -[doctest] run with "--help" for options -=============================================================================== -[doctest] test cases: 4817 | 4817 passed | 0 failed | 0 skipped -[doctest] assertions: 807634 | 807634 passed | 0 failed | -[doctest] Status: SUCCESS! -``` - -* Run the Delegate UnitTests: - -```bash -LD_LIBRARY_PATH=./:$LD_LIBRARY_PATH ./delegate/DelegateUnitTests -``` - -## Troubleshooting and Errors: -### Missing xxd -* When Cross-compiling Arm NN if you are getting error -```bash -[ 62%] Generating SchemaText.cpp -/bin/sh: 1: xxd: not found -make[2]: *** [armnn/CMakeFiles/UnitTests.dir/build.make:63: armnn/SchemaText.cpp] Error 127 -make[1]: *** [CMakeFiles/Makefile2:674: armnn/CMakeFiles/UnitTests.dir/all] Error 2 -make[1]: *** Waiting for unfinished jobs.... -``` -* Missing xxd, this can be fixed by installing it: -```bash -sudo apt-get install xxd -``` - -<br><br> - -### Missing libz.so.1 -* When compiling armNN: -```bash -/usr/lib/gcc-cross/aarch64-linux-gnu/5/../../../../aarch64-linux-gnu/bin/ld: warning: libz.so.1, needed by /home/<username>/armNN/usr/lib64/libprotobuf.so.23.0.0, not found (try using -rpath or -rpath-link) -``` - -* Missing arm64 libraries for libz.so.1, these can be added by adding a second architecture to dpkg and explicitly installing them: -```bash -sudo dpkg --add-architecture arm64 -sudo apt-get install zlib1g:arm64 -sudo apt-get update -sudo ldconfig -``` -* If apt-get update returns 404 errors for arm64 repos refer to section 5 below. -* Alternatively the missing arm64 version of libz.so.1 can be downloaded and installed from a .deb package here: - https://launchpad.net/ubuntu/wily/arm64/zlib1g/1:1.2.8.dfsg-2ubuntu4 -```bash -sudo dpkg -i zlib1g_1.2.8.dfsg-2ubuntu4_arm64.deb -``` -<br><br> - -### Unable to install arm64 packages after adding arm64 architecture -* Using sudo apt-get update should add all of the required repos for arm64 but if it does not or you are getting 404 errors the following instructions can be used to add the repos manually: -* From stackoverflow: -https://askubuntu.com/questions/430705/how-to-use-apt-get-to-download-multi-arch-library/430718 -* Open /etc/apt/sources.list with your preferred text editor. - -* Mark all the current (default) repos as \[arch=<current_os_arch>], e.g. -```bash -deb [arch=amd64] http://archive.ubuntu.com/ubuntu/ xenial main restricted -``` -* Then add the following: -```bash -deb [arch=arm64] http://ports.ubuntu.com/ xenial main restricted -deb [arch=arm64] http://ports.ubuntu.com/ xenial-updates main restricted -deb [arch=arm64] http://ports.ubuntu.com/ xenial universe -deb [arch=arm64] http://ports.ubuntu.com/ xenial-updates universe -deb [arch=arm64] http://ports.ubuntu.com/ xenial multiverse -deb [arch=arm64] http://ports.ubuntu.com/ xenial-updates multiverse -deb [arch=arm64] http://ports.ubuntu.com/ xenial-backports main restricted universe multiverse -``` -* Update and install again: -```bash -sudo apt-get install zlib1g:arm64 -sudo apt-get update -sudo ldconfig -``` -<br><br> - -### Undefined references to google::protobuf:: functions -* Missing or out of date protobuf compilation libraries. - Use the command 'protoc --version' to check which version of protobuf is available (version 3.12.0 is required). - Follow the instructions above to install protobuf 3.12.0 -<br><br> - -### Errors on strict-aliasing rules when compiling the Compute Library -* When compiling the Compute Library there are multiple errors on strict-aliasing rules: - ``` -cc1plus: error: unrecognized command line option ‘-Wno-implicit-fallthrough’ [-Werror] - ``` -* Add Werror=0 to the scons command: -``` -scons arch=arm64-v8a neon=1 opencl=1 embed_kernels=1 extra_cxx_flags="-fPIC" -j8 Werror=0 -``` diff --git a/BuildGuideCrossCompilation.md.license b/BuildGuideCrossCompilation.md.license deleted file mode 100644 index 739dc2d88e..0000000000 --- a/BuildGuideCrossCompilation.md.license +++ /dev/null @@ -1,4 +0,0 @@ -# -# Copyright © 2018-2022 Arm Ltd and Contributors. All rights reserved. -# SPDX-License-Identifier: MIT -# @@ -62,10 +62,11 @@ Arm NN from scratch is the ability to **exactly choose which components to build | Operating System | Architecture-specific Release Archive (Download) | |-----------------------------------------------|----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------| -| Android (AAR) | [](https://github.com/ARM-software/armnn/releases/download/v22.08/ArmnnDelegate-release.aar) | -| Android 8.1 "O/Oreo" (API level 27) | [](https://github.com/ARM-software/armnn/releases/download/v22.08/ArmNN-android-27-arm64-v8.2-a.tar.gz) [](https://github.com/ARM-software/armnn/releases/download/v22.08/ArmNN-android-27-arm64-v8a.tar.gz) | -| Android 9 "P/Pie" (API level 28) | [](https://github.com/ARM-software/armnn/releases/download/v22.08/ArmNN-android-28-arm64-v8.2-a.tar.gz) [](https://github.com/ARM-software/armnn/releases/download/v22.08/ArmNN-android-28-arm64-v8a.tar.gz) | -| Android 10 "Q/Quince Tart" (API level 29) | [](https://github.com/ARM-software/armnn/releases/download/v22.08/ArmNN-android-29-arm64-v8.2-a.tar.gz) [](https://github.com/ARM-software/armnn/releases/download/v22.08/ArmNN-android-29-arm64-v8a.tar.gz) | +| Android (AAR) | [](https://github.com/ARM-software/armnn/releases/download/v22.11/ArmnnDelegate-release.aar) | +| Android 10 "Q/Quince Tart" (API level 29) | [](https://github.com/ARM-software/armnn/releases/download/v22.11/ArmNN-android-29-arm64-v8.2-a.tar.gz) [](https://github.com/ARM-software/armnn/releases/download/v22.11/ArmNN-android-29-arm64-v8a.tar.gz) | +| Android 11 "R/Red Velvet Cake" (API level 30) | [](https://github.com/ARM-software/armnn/releases/download/v22.11/ArmNN-android-30-arm64-v8.2-a.tar.gz) [](https://github.com/ARM-software/armnn/releases/download/v22.11/ArmNN-android-30-arm64-v8a.tar.gz) | +| Android 12 "S/Snow Cone" (API level 31) | [](https://github.com/ARM-software/armnn/releases/download/v22.11/ArmNN-android-31-arm64-v8.2-a.tar.gz) [](https://github.com/ARM-software/armnn/releases/download/v22.11/ArmNN-android-31-arm64-v8a.tar.gz) | +| Android 13 "T/Tirimase" (API level 32) | [](https://github.com/ARM-software/armnn/releases/download/v22.11/ArmNN-android-32-arm64-v8.2-a.tar.gz) [](https://github.com/ARM-software/armnn/releases/download/v22.11/ArmNN-android-32-arm64-v8a.tar.gz) | | Linux | [](https://github.com/ARM-software/armnn/releases/download/v22.08/ArmNN-linux-aarch64.tar.gz) [](https://github.com/ARM-software/armnn/releases/download/v22.08/ArmNN-linux-x86_64.tar.gz) | diff --git a/samples/ObjectDetection/Readme.md b/samples/ObjectDetection/Readme.md index 169546e038..4a119e5266 100644 --- a/samples/ObjectDetection/Readme.md +++ b/samples/ObjectDetection/Readme.md @@ -20,8 +20,8 @@ with detections shown in bounding boxes, class labels and confidence. This example utilizes OpenCV functions to capture and output video data. 1. Public Arm NN C++ API is provided by Arm NN library. 2. For Delegate file mode following dependencies exist: -2.1 Tensorflow version 2.5.0 -2.2 Flatbuffers version 1.12.0 +2.1 Tensorflow version 2.10 +2.2 Flatbuffers version 2.0.6 2.3 Arm NN delegate library ## System @@ -97,7 +97,7 @@ Please see [find_opencv.cmake](./cmake/find_opencv.cmake) for implementation det ### Tensorflow Lite (Needed only in delegate file mode) -This application uses [Tensorflow Lite)](https://www.tensorflow.org/) version 2.5.0 for demonstrating use of 'armnnDelegate'. +This application uses [Tensorflow Lite)](https://www.tensorflow.org/) version 2.10 for demonstrating use of 'armnnDelegate'. armnnDelegate is a library for accelerating certain TensorFlow Lite operators on Arm hardware by providing the TensorFlow Lite interpreter with an alternative implementation of the operators via its delegation mechanism. You may clone and build Tensorflow lite and provide the path to its root and output library directories through the cmake @@ -106,13 +106,13 @@ For implementation details see the scripts FindTfLite.cmake and FindTfLiteSrc.cm The application links with the Tensorflow lite library libtensorflow-lite.a -#### Download and build Tensorflow Lite version 2.5.0 +#### Download and build Tensorflow Lite version 2.10 Example for Tensorflow Lite native compilation ```commandline sudo apt install build-essential git clone https://github.com/tensorflow/tensorflow.git cd tensorflow/tensorflow -git checkout tags/v2.5.0 +git checkout 359c3cdfc5fabac82b3c70b3b6de2b0a8c16874f #Tensorflow 2.10 mkdir build && cd build cmake ../lite -DTFLITE_ENABLE_XNNPACK=OFF make @@ -127,12 +127,12 @@ Please see [FindFlatbuffers.cmake] for implementation details. The application links with the Flatbuffers library libflatbuffers.a -#### Download and build flatbuffers version 1.12.0 +#### Download and build flatbuffers version 2.0.6 Example for flatbuffer native compilation ```commandline -wget -O flatbuffers-1.12.0.zip https://github.com/google/flatbuffers/archive/v1.12.0.zip -unzip -d . flatbuffers-1.12.0.zip -cd flatbuffers-1.12.0 +wget https://github.com/google/flatbuffers/archive/v2.0.6.tar.gz +tar xf v2.0.6.tar.gz +cd flatbuffers-2.0.6 mkdir install && cd install cmake .. -DCMAKE_INSTALL_PREFIX:PATH=`pwd` make install diff --git a/shim/BuildGuideShimSupportLibrary.md b/shim/BuildGuideShimSupportLibrary.md index c0b0f8570b..4a45596ed6 100644 --- a/shim/BuildGuideShimSupportLibrary.md +++ b/shim/BuildGuideShimSupportLibrary.md @@ -16,9 +16,9 @@ This work is currently in an experimental phase. ## Prerequisites The following are required to build the Arm NN support library -* Android NDK r20b +* Android NDK r25 * Detailed setup can be found in [BuildGuideAndroidNDK.md](../BuildGuideAndroidNDK.md) -* Flatbuffer version 1.12.0 +* Flatbuffer version 2.0.6 * Detailed setup can be found in [BuildGuideCrossCompilation.md](../BuildGuideCrossCompilation.md) The following is required to build the Arm NN shim @@ -33,7 +33,7 @@ export WORKING_DIR=<path to where the Arm NN source code, clframework and aosp r export AOSP_ROOT=<path to the root of Android tree where the shim will be built> export AOSP_MODULES_ROOT=<path to where AOSP modules will be cloned i.e. $WORKING_DIR/aosp> export ARMNN_BUILD_DIR=<path to the Arm NN build directory i.e. $WORKING_DIR/build> -export NDK=<path to>android-ndk-r20b +export NDK=<path to>android-ndk-r25 export NDK_TOOLCHAIN_ROOT=$NDK/toolchains/llvm/prebuilt/linux-x86_64 export PATH=$NDK_TOOLCHAIN_ROOT/bin/:$PATH export FLATBUFFERS_ANDROID_BUILD=<path to flatbuffers target android build> |