tensorflow学习

1.例子

        import tensorflow as tf
        import numpy as np
        # create data
        x_data = np.random.rand(100).astype(np.float32)
        y_data = x_data*0.1 + 0.3
        Weights = tf.Variable(tf.random_uniform([1], -1.0, 1.0))
        biases = tf.Variable(tf.zeros([1]))
    
        y = Weights*x_data+ biases
        loss = tf.reduce_mean(tf.square(y-y_data))
        optimizer = tf.train.GradientDescentOptimizer(0.5)  # 0.5 is learning rate
        train = optimizer.minimize(loss)  # 使优化器优化损失函数
        init = tf.global_variables_initializer()   # 初始化所有变量
        sess = tf.Session()
        sess.run(init)          # Very important激活所有变量
    
      for step in range(201):
          sess.run(train)
          if step % 20 == 0:
              print(step, sess.run(Weights), sess.run(biases))

2.session会话控制

import tensorflow as tf

# create two matrixes

matrix1 = tf.constant([[3,3]])
matrix2 = tf.constant([[2],
                       [2]])
product = tf.matmul(matrix1,matrix2)
#因为 product 不是直接计算的步骤, 所以我们会要使用 Session 来激活 product 并得到计算结果.
#有两种形式使用会话控制 Session 。
# method 1
sess = tf.Session()
result = sess.run(product)
print(result)
sess.close()
# [[12]]

# method 2
with tf.Session() as sess: # session自动close
    result2 = sess.run(product)
    print(result2)
# [[12]]

3.variable

import tensorflow as tf

state = tf.Variable(0, name='counter')

# 定义常量 one
one = tf.constant(1)

# 定义加法步骤 (注: 此步并没有直接计算)
new_value = tf.add(state, one)

# 将 State 更新成 new_value
update = tf.assign(state, new_value)
# 如果定义 Variable, 就一定要 initialize

init = tf.global_variables_initializer()  # 初始化所有变量
 
# 使用 Session
with tf.Session() as sess:
    sess.run(init)  # 激活所有变量
    for _ in range(3):
        sess.run(update)
        print(sess.run(state))  # 输出一定要sess.run（）

4.placeholder

如果想要从外部传入data, 那就需要用到 tf.placeholder(), 然后以这种形式传输数据 sess.run(***, feed_dict={input: **}).,需要传入的值放在了feed_dict={} 并一一对应每一个 input. placeholder 与 feed_dict={} 是绑定在一起出现的。

import tensorflow as tf

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

# mul = multiply 是将input1和input2 做乘法运算，并输出为 output 
ouput = tf.multiply(input1, input2)

with tf.Session() as sess:
    print(sess.run(ouput, feed_dict={input1: [7.], input2: [2.]}))
# [ 14.]

5.添加层

import tensorflow as tf
def add_layer(inputs, in_size, out_size, activation_function=None):    
    # 因为在生成初始参数时，随机变量(normal distribution)会比全部为0要好很多，所以我们
    # 这里的weights为一个in_size行, out_size列的随机变量矩阵。
    Weights = tf.Variable(tf.random_normal([in_size, out_size]))
    # 在机器学习中，biases的推荐值不为0，所以我们这里是在0向量的基础上又加了0.1。
    biases = tf.Variable(tf.zeros([1, out_size]) + 0.1)
    Wx_plus_b = tf.matmul(inputs, Weights) + biases
    if activation_function is None:
        outputs = Wx_plus_b
    else:
        outputs = activation_function(Wx_plus_b)
    return outputs

6.建造神经网络

import tensorflow as tf
import numpy as np
def add_layer(inputs, in_size, out_size, activation_function=None):
    Weights = tf.Variable(tf.random_normal([in_size, out_size]))
    biases = tf.Variable(tf.zeros([1, out_size]) + 0.1)
    Wx_plus_b = tf.matmul(inputs, Weights) + biases
    if activation_function is None:
        outputs = Wx_plus_b
    else:
        outputs = activation_function(Wx_plus_b)
    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

# 利用占位符定义我们所需的神经网络的输入。 tf.placeholder()就是代表占位符，
# 这里的None代表无论输入有多少都可以，因为输入只有一个特征，所以这里是1。
xs = tf.placeholder(tf.float32, [None, 1])
ys = tf.placeholder(tf.float32, [None, 1])

# 我们构建的是——输入层1个、隐藏层10个、输出层1个的神经网络。
# 隐藏层
l1 = add_layer(xs, 1, 10, activation_function=tf.nn.relu)
# 输出层
prediction = add_layer(l1, 10, 1, activation_function=None)
loss = tf.reduce_mean(tf.reduce_sum(tf.square(ys - prediction),
                     reduction_indices=[1]))
train_step = tf.train.GradientDescentOptimizer(0.1).minimize(loss)
init = tf.global_variables_initializer()  
sess = tf.Session()
sess.run(init)
for i in range(1000):
    # training
    sess.run(train_step, feed_dict={xs: x_data, ys: y_data})
    if i % 50 == 0:
    # to see the step improvement
    print(sess.run(loss, feed_dict={xs: x_data, ys: y_data}))