tensorflow：实战Google深度学习框架第四章02神经网络优化（学习率，避免过拟合，滑动平均模型）

import tensorflow as tf
TRAINING_STEPS = 10
LEARNING_RATE = 1
x = tf.Variable(tf.constant(5, dtype=tf.float32), name="x")
y = tf.square(x)

train_op = tf.train.GradientDescentOptimizer(LEARNING_RATE).minimize(y)

with tf.Session() as sess:
    sess.run(tf.global_variables_initializer())
    for i in range(TRAINING_STEPS):
        sess.run(train_op)
        x_value = sess.run(x)
        print "After %s iteration(s): x%s is %f."% (i+1, i+1, x_value) 

TRAINING_STEPS = 1000
LEARNING_RATE = 0.001
x = tf.Variable(tf.constant(5, dtype=tf.float32), name="x")
y = tf.square(x)

train_op = tf.train.GradientDescentOptimizer(LEARNING_RATE).minimize(y)

with tf.Session() as sess:
    sess.run(tf.global_variables_initializer())
    for i in range(TRAINING_STEPS):
        sess.run(train_op)
        if i % 100 == 0: 
            x_value = sess.run(x)
            print "After %s iteration(s): x%s is %f."% (i+1, i+1, x_value)

TRAINING_STEPS = 100
global_step = tf.Variable(0)
LEARNING_RATE = tf.train.exponential_decay(0.1, global_step, 1, 0.96, staircase=True)

x = tf.Variable(tf.constant(5, dtype=tf.float32), name="x")
y = tf.square(x)
train_op = tf.train.GradientDescentOptimizer(LEARNING_RATE).minimize(y, global_step=global_step)

with tf.Session() as sess:
    sess.run(tf.global_variables_initializer())
    for i in range(TRAINING_STEPS):
        sess.run(train_op)
        if i % 10 == 0:
            LEARNING_RATE_value = sess.run(LEARNING_RATE)
            x_value = sess.run(x)
            print "After %s iteration(s): x%s is %f, learning rate is %f."% (i+1, i+1, x_value, LEARNING_RATE_value)

import tensorflow as tf
import matplotlib.pyplot as plt
import numpy as np

data = []
label = []
np.random.seed(0)

# 以原点为圆心，半径为1的圆把散点划分成红蓝两部分，并加入随机噪音。
for i in range(150):
    x1 = np.random.uniform(-1,1)
    x2 = np.random.uniform(0,2)
    if x1**2 + x2**2 <= 1:
        data.append([np.random.normal(x1, 0.1),np.random.normal(x2,0.1)])
        label.append(0)
    else:
        data.append([np.random.normal(x1, 0.1), np.random.normal(x2, 0.1)])
        label.append(1)
        
data = np.hstack(data).reshape(-1,2)
label = np.hstack(label).reshape(-1, 1)
plt.scatter(data[:,0], data[:,1], c=label,
           cmap="RdBu", vmin=-.2, vmax=1.2, edgecolor="white")
plt.show()

def get_weight(shape, lambda1):
    var = tf.Variable(tf.random_normal(shape), dtype=tf.float32)
    tf.add_to_collection(‘losses‘, tf.contrib.layers.l2_regularizer(lambda1)(var))
    return var

x = tf.placeholder(tf.float32, shape=(None, 2))
y_ = tf.placeholder(tf.float32, shape=(None, 1))
sample_size = len(data)

# 每层节点的个数
layer_dimension = [2,10,5,3,1]

n_layers = len(layer_dimension)

cur_layer = x
in_dimension = layer_dimension[0]

# 循环生成网络结构
for i in range(1, n_layers):
    out_dimension = layer_dimension[i]
    weight = get_weight([in_dimension, out_dimension], 0.003)
    bias = tf.Variable(tf.constant(0.1, shape=[out_dimension]))
    cur_layer = tf.nn.elu(tf.matmul(cur_layer, weight) + bias)
    in_dimension = layer_dimension[i]

y= cur_layer

# 损失函数的定义。
mse_loss = tf.reduce_sum(tf.pow(y_ - y, 2)) / sample_size
tf.add_to_collection(‘losses‘, mse_loss)
loss = tf.add_n(tf.get_collection(‘losses‘))

# 定义训练的目标函数mse_loss，训练次数及训练模型
train_op = tf.train.AdamOptimizer(0.001).minimize(mse_loss)
TRAINING_STEPS = 40000

with tf.Session() as sess:
    tf.global_variables_initializer().run()
    for i in range(TRAINING_STEPS):
        sess.run(train_op, feed_dict={x: data, y_: label})
        if i % 2000 == 0:
            print("After %d steps, mse_loss: %f" % (i,sess.run(mse_loss, feed_dict={x: data, y_: label})))

    # 画出训练后的分割曲线       
    xx, yy = np.mgrid[-1.2:1.2:.01, -0.2:2.2:.01]
    grid = np.c_[xx.ravel(), yy.ravel()]
    probs = sess.run(y, feed_dict={x:grid})
    probs = probs.reshape(xx.shape)

plt.scatter(data[:,0], data[:,1], c=label,
           cmap="RdBu", vmin=-.2, vmax=1.2, edgecolor="white")
plt.contour(xx, yy, probs, levels=[.5], cmap="Greys", vmin=0, vmax=.1)
plt.show()

# 定义训练的目标函数loss，训练次数及训练模型
train_op = tf.train.AdamOptimizer(0.001).minimize(loss)
TRAINING_STEPS = 40000

with tf.Session() as sess:
    tf.global_variables_initializer().run()
    for i in range(TRAINING_STEPS):
        sess.run(train_op, feed_dict={x: data, y_: label})
        if i % 2000 == 0:
            print("After %d steps, loss: %f" % (i, sess.run(loss, feed_dict={x: data, y_: label})))

    # 画出训练后的分割曲线       
    xx, yy = np.mgrid[-1:1:.01, 0:2:.01]
    grid = np.c_[xx.ravel(), yy.ravel()]
    probs = sess.run(y, feed_dict={x:grid})
    probs = probs.reshape(xx.shape)

plt.scatter(data[:,0], data[:,1], c=label,
           cmap="RdBu", vmin=-.2, vmax=1.2, edgecolor="white")
plt.contour(xx, yy, probs, levels=[.5], cmap="Greys", vmin=0, vmax=.1)
plt.show()

import tensorflow as tf
v1 = tf.Variable(0, dtype=tf.float32)
step = tf.Variable(0, trainable=False)
ema = tf.train.ExponentialMovingAverage(0.99, step)
maintain_averages_op = ema.apply([v1]) 

with tf.Session() as sess:
    
    # 初始化
    init_op = tf.global_variables_initializer()
    sess.run(init_op)
    print sess.run([v1, ema.average(v1)])
    
    # 更新变量v1的取值
    sess.run(tf.assign(v1, 5))
    sess.run(maintain_averages_op)
    print sess.run([v1, ema.average(v1)]) 
    
    # 更新step和v1的取值
    sess.run(tf.assign(step, 10000))  
    sess.run(tf.assign(v1, 10))
    sess.run(maintain_averages_op)
    print sess.run([v1, ema.average(v1)])       
    
    # 更新一次v1的滑动平均值
    sess.run(maintain_averages_op)
    print sess.run([v1, ema.average(v1)])