yum install zlib
yum install zlib-devel

yum install openssl
yum install openssl-devel

   wget https://raw.githubusercontent.com/lawlite19/LinuxSoftware/master/python/Python-2.7.12.tgz --no-check-certificate

#!/usr/bin/python

#!/usr/bin/python2.6

   ImportError: No module named _tkinter

cp /usr/lib/python2.6/lib-dynload/bz2.so /usr/local/python2.7/lib/python2.7/lib-dynload

    # Ubuntu/Linux 64-bit, CPU only, Python 2.7
   $ export TF_BINARY_URL=https://storage.googleapis.com/tensorflow/linux/cpu/tensorflow-0.12.0rc0-cp27-none-linux_x86_64.whl
   
   # 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.
   $ export TF_BINARY_URL=https://storage.googleapis.com/tensorflow/linux/gpu/tensorflow_gpu-0.12.0rc0-cp27-none-linux_x86_64.whl
   
   # Mac OS X, CPU only, Python 2.7:
   $ export TF_BINARY_URL=https://storage.googleapis.com/tensorflow/mac/cpu/tensorflow-0.12.0rc0-py2-none-any.whl
   
   # Mac OS X, GPU enabled, Python 2.7:
   $ export TF_BINARY_URL=https://storage.googleapis.com/tensorflow/mac/gpu/tensorflow_gpu-0.12.0rc0-py2-none-any.whl
   
   # Ubuntu/Linux 64-bit, CPU only, Python 3.4
   $ export TF_BINARY_URL=https://storage.googleapis.com/tensorflow/linux/cpu/tensorflow-0.12.0rc0-cp34-cp34m-linux_x86_64.whl
   
   # Ubuntu/Linux 64-bit, GPU enabled, Python 3.4
   # Requires CUDA toolkit 8.0 and CuDNN v5. For other versions, see "Installing from sources" below.
   $ export TF_BINARY_URL=https://storage.googleapis.com/tensorflow/linux/gpu/tensorflow_gpu-0.12.0rc0-cp34-cp34m-linux_x86_64.whl
   
   # Ubuntu/Linux 64-bit, CPU only, Python 3.5
   $ export TF_BINARY_URL=https://storage.googleapis.com/tensorflow/linux/cpu/tensorflow-0.12.0rc0-cp35-cp35m-linux_x86_64.whl
   
   # Ubuntu/Linux 64-bit, GPU enabled, Python 3.5
   # Requires CUDA toolkit 8.0 and CuDNN v5. For other versions, see "Installing from sources" below.
   $ export TF_BINARY_URL=https://storage.googleapis.com/tensorflow/linux/gpu/tensorflow_gpu-0.12.0rc0-cp35-cp35m-linux_x86_64.whl
   
   # Mac OS X, CPU only, Python 3.4 or 3.5:
   $ export TF_BINARY_URL=https://storage.googleapis.com/tensorflow/mac/cpu/tensorflow-0.12.0rc0-py3-none-any.whl
   
   # Mac OS X, GPU enabled, Python 3.4 or 3.5:
   $ export TF_BINARY_URL=https://storage.googleapis.com/tensorflow/mac/gpu/tensorflow_gpu-0.12.0rc0-py3-none-any.whl

    # Python 2
   $ sudo pip install --upgrade $TF_BINARY_URL
   
   # Python 3
   $ sudo pip3 install --upgrade $TF_BINARY_URL

ImportError: /usr/lib64/libstdc++.so.6: version `GLIBCXX_3.4.19' not found (required by /usr/local/python2.7/lib/python2.7/site-packages/tensorflow/python/_pywrap_tensorflow.so)

../configure  \
   --prefix=/usr          \
   --disable-profile      \
   --enable-add-ons       \
   --enable-kernel=2.6.25 \
   --libexecdir=/usr/lib/glibc

   x_data = np.random.rand(100).astype(np.float32)
   y_data = x_data*1.0+3.0

   Weights = tf.Variable(tf.random_uniform([1], -1.0, 1.0)) # 创建变量Weight是，范围是 -1.0~1.0
   biases = tf.Variable(tf.zeros([1]))                      # 创建偏置，初始值为0
   y = Weights*x_data+biases                                # 定义方程
   loss = tf.reduce_mean(tf.square(y-y_data))               # 定义损失，为真实值减去我们每一步计算的值
   optimizer = tf.train.GradientDescentOptimizer(0.5)       # 0.5 是学习率
   train = optimizer.minimize(loss)                         # 使用梯度下降优化
   init = tf.initialize_all_variables()                     # 初始化所有变量

   sess = tf.Session()
   sess.run(init)

for i in range(201):
   sess.run(train)
   if i%20 == 0:
       print i,sess.run(Weights),sess.run(biases)

0 [ 1.60895896] [ 3.67376709]
20 [ 1.04673827] [ 2.97489643]
40 [ 1.011392] [ 2.99388123]
60 [ 1.00277638] [ 2.99850869]
80 [ 1.00067675] [ 2.99963641]
100 [ 1.00016499] [ 2.99991131]
120 [ 1.00004005] [ 2.99997854]
140 [ 1.00000978] [ 2.99999475]
160 [ 1.0000025] [ 2.99999857]
180 [ 1.00000119] [ 2.99999928]
200 [ 1.00000119] [ 2.99999928]

   sess = tf.Session()
   print sess.run(product)
   sess.close()

   with tf.Session() as sess:
   print sess.run(product)

input1 = tf.placeholder(tf.float32) #在 Tensorflow 中需要定义 placeholder 的 type ，一般为 float32 形式
input2 = tf.placeholder(tf.float32)

output = tf.mul(input1,input2)  # 乘法运算

with tf.Session() as sess:
    print sess.run(output,feed_dict={input1:7.,input2:2.}) # placeholder 与 feed_dict={} 是绑定在一起出现的

'''参数：输入数据，前一层size，当前层size，激活函数'''
def add_layer(inputs,in_size,out_size,activation_function=None):
    Weights = tf.Variable(tf.random_normal([in_size,out_size]))  #随机初始化权重
    biases = tf.Variable(tf.zeros([1,out_size]) + 0.1)  # 初始化偏置，+0.1
    Ws_plus_b = tf.matmul(inputs,Weights) + biases      # 未使用激活函数的值
    if activation_function is None:
        outputs = Ws_plus_b
    else:
        outputs = activation_function(Ws_plus_b)   # 使用激活函数激活
    return outputs

x_data = np.linspace(-1,1,300,dtype=np.float32)[:,np.newaxis]
noise = np.random.normal(0,0.05,x_data.shape).astype(np.float32)
y_data = np.square(x_data)-0.5+noise

xs = tf.placeholder(tf.float32,[None,1]) # None代表无论输入有多少都可以,只有一个特征，所以这里是1
ys = tf.placeholder(tf.float32,[None,1])

layer1 = add_layer(xs, 1, 10, activation_function=tf.nn.relu) # 第一层，输入层为1，隐含层为10个神经元，Tensorflow 自带的激励函数tf.nn.relu

prediction = add_layer(layer1, 10, 1) # 利用上一层作为输入

loss = tf.reduce_mean(tf.reduce_sum(tf.square(ys-prediction),reduction_indices=[1])) # 对二者差的平方求和再取平均

train = tf.train.GradientDescentOptimizer(0.1).minimize(loss)

init = tf.initialize_all_variables()

sess = tf.Session()
sess.run(init)

for i in range(1000):
    sess.run(train,feed_dict={xs:x_data,ys:y_data})
    if i%50==0:
        print sess.run(loss,feed_dict={xs:x_data,ys:y_data})

0.45402
0.0145364
0.00721318
0.0064215
0.00614493
0.00599307
0.00587578
0.00577039
0.00567172
0.00558008
0.00549546
0.00541595
0.00534059
0.00526139
0.00518873
0.00511403
0.00504063
0.0049613
0.0048874
0.004819

    fig = plt.figure()
    ax = fig.add_subplot(111)
    ax.scatter(x_data,y_data)
    plt.ion()   # 绘画之后不暂停
    plt.show()

        try:
            ax.lines.remove(lines[0])   # 每次绘画需要移除上次绘画的结果，放在try catch里因为第一次执行没有，所以直接pass
        except Exception:
            pass
        prediction_value = sess.run(prediction, feed_dict={xs: x_data})
        # plot the prediction
        lines = ax.plot(x_data, prediction_value, 'r-', lw=3)  # 绘画
        plt.pause(0.1)  # 停0.1s

with tf.name_scope('input'):
    xs = tf.placeholder(tf.float32,[None,1],name='x_in')  # 
    ys = tf.placeholder(tf.float32,[None,1],name='y_in')

def add_layer(inputs,in_size,out_size,activation_function=None):
    with tf.name_scope('layer'):
        with tf.name_scope('Weights'):
            Weights = tf.Variable(tf.random_normal([in_size,out_size]),name='W')
        with tf.name_scope('biases'):
            biases = tf.Variable(tf.zeros([1,out_size]) + 0.1,name='b')
        with tf.name_scope('Ws_plus_b'):
            Ws_plus_b = tf.matmul(inputs,Weights) + biases
        if activation_function is None:                                       outputs = Ws_plus_b
        else:                                                            
            outputs = activation_function(Ws_plus_b)  
        return outputs

with tf.name_scope('loss'):
    loss = tf.reduce_mean(tf.reduce_sum(tf.square(ys-prediction),reduction_indices=[1]))

with tf.name_scope('train'):
    train = tf.train.GradientDescentOptimizer(0.1).minimize(loss)

writer = tf.train.SummaryWriter("logs/", sess.graph)

layer_name = 'layer%s'%n_layer

def add_layer(inputs,in_size,out_size,n_layer,activation_function=None):
   layer_name = 'layer%s'%n_layer
   with tf.name_scope(layer_name):
       with tf.name_scope('Weights'):
           Weights = tf.Variable(tf.random_normal([in_size,out_size]),name='W')
           tf.histogram_summary(layer_name+'/weights', Weights)
       with tf.name_scope('biases'):
           biases = tf.Variable(tf.zeros([1,out_size]) + 0.1,name='b')
           tf.histogram_summary(layer_name+'/biases',biases)
       with tf.name_scope('Ws_plus_b'):
           Ws_plus_b = tf.matmul(inputs,Weights) + biases
                                     
       if activation_function is None:             
           outputs = Ws_plus_b 
       else:                                                         
           outputs = activation_function(Ws_plus_b)      
       tf.histogram_summary(layer_name+'/outputs',outputs)
       return outputs

merged =tf.merge_all_summaries() 

writer = tf.train.SummaryWriter("logs/", sess.graph)

for i in range(1000):
   sess.run(train,feed_dict={xs:x_data,ys:y_data})
   if i%50==0:
       summary = sess.run(merged, feed_dict={xs: x_data, ys:y_data})
       writer.add_summary(summary, i)