Ubuntu16.04安装tensorflow

1.采用源码安装的方式安装cuda8.0  https://developer.nvidia.com/cuda-downloads

sudo chmod +x  cuda_8.0.61_375.26_linux.run

sudo ./cuda_8.0.61_375.26_linux.run ,在安装的同时选择不安装驱动

然后降低gcc版本

sudo apt-get install g++-4.9
sudo update-alternatives --install /usr/bin/gcc gcc /usr/bin/gcc-4.9 20
sudo update-alternatives --install /usr/bin/gcc gcc /usr/bin/gcc-5 10
sudo update-alternatives --install /usr/bin/g++ g++ /usr/bin/g++-4.9 20
sudo update-alternatives --install /usr/bin/g++ g++ /usr/bin/g++-5 10
sudo update-alternatives --install /usr/bin/cc cc /usr/bin/gcc 30
sudo update-alternatives --set cc /usr/bin/gcc
sudo update-alternatives --install /usr/bin/c++ c++ /usr/bin/g++ 30
sudo update-alternatives --set c++ /usr/bin/g++

2. 安装完毕后安装375.26的nvidia显卡驱动

到nvidia的官网下载对应的驱动程序NVIDIA-Linux-x86_64-375.26.run 之后，

Ubuntu系统集成的显卡驱动程序是nouveau，它是第三方为NVIDIA开发的开源驱动，我们需要先将其屏蔽才能安装NVIDIA官方驱动。
将驱动添加到黑名单blacklist.conf中，但是由于该文件的属性不允许修改。所以需要先修改文件属性。

查看属性
$sudo ls -lh /etc/modprobe.d/blacklist.conf

修改属性
$sudo chmod 666 /etc/modprobe.d/blacklist.conf

用gedit编辑器打开
$sudo gedit /etc/modprobe.d/blacklist.conf

在该文件后添加一下几行：

blacklist vga16fb
blacklist nouveau
blacklist rivafb
blacklist rivatv
blacklist nvidiafb

先按Ctrl + Alt + F1到控制台，关闭当前图形环境
$sudo service lightdm stop

再安装驱动程序
$sudo chmod +x NVIDIA-Linux-x86_64-375.26.run

sudo ./NVIDIA-Linux-x86_64-375.26.run -no-opengl-files

最后重新启动图形环境
$sudo service lightdm start

3. 安装cudnn

tar xvzf cudnn-8.0-linux-x64-v5.0-ga.tgz
sudo cp cuda/include/cudnn.h /usr/local/cuda-8.0/include###（复制）
sudo cp cuda/lib64/libcudnn* /usr/local/cuda-8.0/lib64###（复制）
sudo chmod a+r /usr/local/cuda-8.0/include/cudnn.h /usr/local/cuda-8.0/lib64/libcudnn*
然后配置环境变量

sudo gedit ~/.bash_profile 

export LD_LIBRARY_PATH="$LD_LIBRARY_PATH:/usr/local/cuda-8.0/lib64:/usr/local/cuda-8.0/extras/CUPTI/lib64"
export CUDA_HOME=/usr/local/cuda-8.0
安装其他库

sudo apt-get install python-pip python-dev 
4.安装bazel
先配置bazel的环境变量，https://docs.bazel.build/versions/master/install-ubuntu.html
1. Install JDK 8
Install JDK 8 by using:

sudo apt-get install openjdk-8-jdk

2. Add Bazel distribution URI as a package source (one time setup)

echo "deb [arch=amd64] http://storage.googleapis.com/bazel-apt stable jdk1.8" | sudo tee /etc/apt/sources.list.d/bazel.list
curl https://bazel.build/bazel-release.pub.gpg | sudo apt-key add -

3. Install and update Bazel

sudo apt-get update && sudo apt-get install bazel

然后下载bazel
https://github.com/bazelbuild/bazel/releases
下载的是
bazel-0.5.2-installer-linux-x86_64.sh
进行安装
sudo chmod +x bazel-0.5.2-installer-linux-x86_64.sh
sudo ./bazel-0.5.2-installer-linux-x86_64.sh --user
会提示输入 source /home/zhao/.bazel/bin/bazel-complete.bash

5.安装第三方库

sudo apt-get install python-numpy swig python-dev python-wheel #安装第三方库
sudo apt-get install git
git clone git://github.com/numpy/numpy.git numpy 

6.安装tenorflow

git clone https://github.com/tensorflow/tensorflow

cd ~/tensorflow #切换到tensorflow文件夹
./configure

注意要选择5.0
/usr/local/cuda-8.0
/usr/local/cuda

cd ~/tensorflow
bazel build -c opt //tensorflow/tools/pip_package:build_pip_package
bazel build -c opt --config=cuda //tensorflow/tools/pip_package:build_pip_package
bazel-bin/tensorflow/tools/pip_package/build_pip_package /tmp/tensorflow_pkg
sudo pip install /home/***（你自己的用户名）/Desktop/tensorflow-0.10.0-cp2-none-any.whl

bazel build -c opt //tensorflow/tools/pip_package:build_pip_package 

# To build with GPU support:
 bazel build -c opt --config=cuda //tensorflow/tools/pip_package:build_pip_package 
mkdir _python_build 

cd _python_build 
ln -s ../bazel-bin/tensorflow/tools/pip_package/build_pip_package.runfiles/org_tensorflow/* .
 ln -s ../tensorflow/tools/pip_package/* . python setup.py develop