This article describes how to establish written primarily for Tensorflow-lite compiler environment on Ubuntu16.04, involving the target hardware Armv7 architecture, 8-core Cortex-A7.
1. Introduction development environment:
OS: Ubuntu16.04 64 of
Target platforms: Armv7
Cross tool chain: gcc-linaro-arm-linux-gnueabihf-4.9-2014.9_linux
Tensorflow Version: 2.0.0
2, download Tensorflow
git clone https://github.com/tensorflow/tensorlfow.git
3, installation Bazel
Open the Web page, use the first method: Use the binary installer
https://docs.bazel.build/versions/master/install-ubuntu.html
1) sudo apt-get install pkg-config zip g++ zlib1g-dev unzip python3
2) Open the link: https://github.com/bazelbuild/bazel/releases , download the latest sh file: bazel-0.29.0-installer-linux-x86_64.sh
3) Run Bazel: chmod + x bazel-0.29.0-installer-linux-x86_64.sh
./bazel-0.29.0-installer-linux-x86_64.sh --user
--user flag installs bazel to the $HOME/bin directory on your system and set .bazelrc path to $HOME/.bazelrc
4)set up your environment:
export PATH="$PATH:$HOME/bin"
you can also add this command to your ~/.bashrc file.