ubuntu14.04系统中安装tensorflow（cpu版）

第一步：安装pip工具

sudo apt-get install python-pip python-dev

第二步：安装tensorflow-cpu版

#安装cpu版0.9.0版本
sudo pip install https://storage.googleapis.com/tensorflow/linux/cpu/tensorflow-0.9.0-cp27-none-linux_x86_64.whl
#安装cpu版0.5.0版本：
sudo pip install https://storage.googleapis.com/tensorflow/linux/cpu/tensorflow-0.5.0-cp27-none-linux_x86_64.whl
#安装gpu版0.9.0
sudo pip install https://storage.googleapis.com/tensorflow/linux/gpu/tensorflow-0.9.0-cp27-none-linux_x86_64.whl
#安装gpu版0.5.0版本：
sudo pip install https://storage.googleapis.com/tensorflow/linux/gpu/tensorflow-0.5.0-cp27-none-linux_x86_64.whl

第三步：打开sublime-text3 使用SFTP连接ubuntu系统出现如下错误

The SSH host key has changed. This could indicate a potential security breach, or that the domain you are connecting to recently moved servers.
If you are confident this is not a security breach you can delete the old host key and try again.
 1. Win XP: Start > Run > regedit.exe
    Win Vista/7: Start > regedit
 2. Expand to HKEY_CURRENT_USER\Software\SimonTatham\PuTTY\SshHostKeys and delete the entry including @22:10.0.83.202
打开windows7下按以上步骤打开并删除相应记录

第四步：linux上测试tensor测试文件

test.py

import numpy
import tensorflow as tf
hello = tf.constant("hello,tensorflow")
sess = tf.Session()
print sess.run(hello)
a = tf.constant(10)
b = tf.constant(20)
print sess.run(a+b)

linux安装anaconda2 下载地址：https://repo.continuum.io/archive/index.html  安装到/usr/local/anaconda2中
或者指令：sudo apt-get install python-dev 软件后在安装numpy   指令：sudo apt-get install python-numpy
tensorflow的安装目录：/usr/local/lib/python2.7/dist-packages/tensorflow
mnist的数据集下载地址为： http://yann.lecun.com/exdb/mnist/
train-images-idx3-ubyte.gz:  training set images (9912422 bytes) 
train-labels-idx1-ubyte.gz:  training set labels (28881 bytes) 
t10k-images-idx3-ubyte.gz:   test set images (1648877 bytes) 
t10k-labels-idx1-ubyte.gz:   test set labels (4542 bytes)