train_action

# 导入数值计算模块
import numpy as np
import tensorflow as tf
 
# 创建计算会话
sess = tf.Session()
# 生成数据，创建占位符和变量A
x_vales = np.random.normal(, 0.1, )
y_vals = np.repeat(., )
x_data = tf.placeholder(shape=[], dtype=tf.float32)
y_target = tf.placeholder(shape=[], dtype=tf.float32)
A = tf.Variable(tf.random_normal(shape=[]))
 
# 增加乘法操作
my_output = tf.multiply(x_data, A)
# 增加L2正则损失函数
loss = tf.square(my_output - y_target)
 
# 在运行之前，需要初始化变量
#init = tf.initialize_all_tables()
init = tf.tables_initializer()
sess.run(init)
 
# 声明变量的优化器
 
# 学习率的选取
my_opt = tf.train.GradientDescentOptimizer(learning_rate=0.2)
train_step = my_opt.minimize(loss)
 
# 训练算法
for i in range():
    rand_index = np.random.choice()
    rand_x = [x_vales[rand_index]]
    rand_y = [y_vals[rand_index]]
    sess.run(train_step, feed_dict={x_data: rand_x, y_target: rand_y})
    if (i + ) %  == :
        print('Step #' + str(i + ) + 'A = ' + str(sess.run(A)))
        print('Loss = ' + str(sess.run(loss, feed_dict={x_data: rand_x, y_target: rand_y})))
#
d = 

An Op that initializes all tables. Note that if there are not tables the returned Op is a NoOp.

 

 

特征列和层一样具有内部状态，因此通常需要将它们初始化

 

Feature columns can have internal state, like layers, so they often need to be initialized. Categorical columns use lookup tables internally and these require a separate initialization op, tf.tables_initializer.

 

var_init = tf.global_variables_initializer()
table_init = tf.tables_initializer()
sess = tf.Session()
sess.run((var_init, table_init))

Once the internal state has been initialized you can run inputs like any other tf.Tensor:

# 导入数值计算模块
import numpy as np
import tensorflow as tf
 
# 构建计算图
# 生成数据，创建占位符和变量A
x_vales = np.random.normal(, 0.1, )
y_vals = np.repeat(., )
x_data = tf.placeholder(shape=[], dtype=tf.float32)
y_target = tf.placeholder(shape=[], dtype=tf.float32)
A = tf.Variable(tf.random_normal(shape=[]))
 
# 增加乘法操作
my_output = tf.multiply(x_data, A)
# 增加L2正则损失函数
loss = tf.square(my_output - y_target)
 
# 声明变量的优化器
# 学习率的选取
my_opt = tf.train.GradientDescentOptimizer(learning_rate=0.2)
train_step = my_opt.minimize(loss)
 
# 运行计算图
 
# 创建计算会话
sess = tf.Session()
 
# 内部状态初始化完成后，您就可以像运行任何其他 tf.Tensor 一样运行 inputs：
# 特征列和层一样具有内部状态，因此通常需要将它们初始化。分类列会在内部使用对照表，而这些表需要单独的初始化指令 tf.tables_initializer。
 
var_init = tf.global_variables_initializer()
table_init = tf.tables_initializer()
 
sess.run((var_init, table_init))
 
# 训练算法
for i in range():
    rand_index = np.random.choice()
    rand_x = [x_vales[rand_index]]
    rand_y = [y_vals[rand_index]]
    sess.run(train_step, feed_dict={x_data: rand_x, y_target: rand_y})
    if (i + ) %  == :
        print('Step #' + str(i + ) + 'A = ' + str(sess.run(A)))
        print('Loss = ' + str(sess.run(loss, feed_dict={x_data: rand_x, y_target: rand_y})))

2018-05-12 16:57:22.358693: I T:\src\github\tensorflow\tensorflow\core\platform\cpu_feature_guard.cc:140] Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX2
Step #25A = [10.501938]
Loss = [0.00203205]
Step #50A = [9.105795]
Loss = [0.2731857]
Step #75A = [9.097782]
Loss = [0.5107153]
Step #100A = [9.557248]
Loss = [0.00200771]