机器学习(1）——环境安装

先尝试尝试tensorflow

1. 修改/etc/hosts/ 加入如下行

#TensorFlow start 
64.233.188.121 www.tensorflow.org 

#TensorFlow end

2. 进入官网后有这些选项

• Pip install: Install TensorFlow on your machine, possibly upgrading previously installed Python packages. May impact existing Python programs on your machine.
• Virtualenv install: Install TensorFlow in its own directory, not impacting any existing Python programs on your machine.
• Anaconda install: Install TensorFlow in its own environment for those running the Anaconda Python distribution. Does not impact existing Python programs on your machine.
• Docker install: Run TensorFlow in a Docker container isolated from all other programs on your machine.
• Installing from sources: Install TensorFlow by building a pip wheel that you then install using pip.

     选择Anaconda install

3. Anaconda 安装

进入清华镜像 https://mirrors.tuna.tsinghua.edu.cn/help/anaconda/

进入下载页面 https://mirrors.tuna.tsinghua.edu.cn/anaconda/archive/

选择下载 Anaconda2-5.1.0-Linux-x86_64.sh

在控制台上进入下载后的文件目录， 默认~/Downloads/ 之下

执行 

chmod +x Anaconda2-5.1.0-Linux-x86_64.sh  

./Anaconda2-5.1.0-Linux-x86_64.sh 

加入conda源

conda config --add channels https://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/free/
conda config --add channels https://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/main/
conda config --set show_channel_urls yes

3. 安装tensorflow

创建tensorflow虚拟环境

conda create -n tensorflow python=2.7

因为要使用GPU，使用PIP进行安装

$ source activate tensorflow
(tensorflow)$  # Your prompt should change

设定Binary安装路径

# Ubuntu/Linux 64-bit, GPU enabled, Python 2.7
# Requires CUDA toolkit 8.0 and CuDNN v5. For other versions, see "Installing from sources" below.
(tensorflow)$ export TF_BINARY_URL=https://storage.googleapis.com/tensorflow/linux/gpu/tensorflow_gpu-0.12.0rc1-cp27-none-linux_x86_64.whl

安装 test flow

# Python 2
(tensorflow)$ pip install --ignore-installed --upgrade $TF_BINARY_URL

3. 激活GPU Support

1. 安装GTX 1060的驱动

参照：http://blog.csdn.net/shenqiongniujiahui/article/details/52745061

2. 安装CUDA

`sudo dpkg -i cuda-repo-ubuntu1604_8.0.61-1_amd64.deb`
`sudo apt-get update`
`sudo apt-get install cuda`

    3.Download cuDNN 5.0

    https://developer.nvidia.com/cudnn

 

tar xvzf cudnn-8.0-linux-x64-v5.1-ga.tgz
sudo cp -P cuda/include/cudnn.h /usr/local/cuda/include
sudo cp -P cuda/lib64/libcudnn* /usr/local/cuda/lib64
sudo chmod a+r /usr/local/cuda/include/cudnn.h /usr/local/cuda/lib64/libcudnn*

    4. 添加如下的参数到.profile文件中

export LD_LIBRARY_PATH="$LD_LIBRARY_PATH:/usr/local/cuda/lib64:/usr/local/cuda/extras/CUPTI/lib64"
export CUDA_HOME=/usr/local/cuda

4. 测试

   激活tesorflow环境

source activate tensorflow

  hello world!

$ python
...
>>> import tensorflow as tf
>>> hello = tf.constant('Hello, TensorFlow!')
>>> sess = tf.Session()
>>> print(sess.run(hello))
Hello, TensorFlow!
>>> a = tf.constant(10)
>>> b = tf.constant(32)
>>> print(sess.run(a + b))
42
>>>

手写识别

进入下面这个命令的执行结果的目录

$ python -c 'import os; import inspect; import tensorflow; print(os.path.dirname(inspect.getfile(tensorflow)))'

执行

python -m tensorflow.models.image.mnist.convolutional