机器学习进阶笔记之三 | 深入理解Alexnet

 　　这个是基于原生tensorflow的一版代码，好长而且看着比较麻烦一点，还load了caffe里面生成的网络模型，比较麻烦

1.  # 输入数据
2.  import input_data
3.  mnist = input_data.read_data_sets("/tmp/data/", one_hot=True)
4. 
   
5.  import tensorflow as tf
6. 
   
7.  # 定义网络超参数
8.  learning_rate = 0.001
9.  training_iters = 200000
10.  batch_size = 64
11.  display_step = 20
12. 
    
13.  # 定义网络参数
14.  n_input = 784 # 输入的维度
15.  n_classes = 10 # 标签的维度
16.  dropout = 0.8 # Dropout 的概率
17. 
    
18.  # 占位符输入
19.  x = tf.placeholder(tf.types.float32, [None, n_input])
20.  y = tf.placeholder(tf.types.float32, [None, n_classes])
21.  keep_prob = tf.placeholder(tf.types.float32)
22. 
    
23.  # 卷积操作
24.  def conv2d(name, l_input, w, b):
25.      return tf.nn.relu(tf.nn.bias_add(tf.nn.conv2d(l_input, w, strides=[1, 1, 1, 1], padding='SAME'),b), name=name)
26. 
    
27.  # 最大下采样操作
28.  def max_pool(name, l_input, k):
29.      return tf.nn.max_pool(l_input, ksize=[1, k, k, 1], strides=[1, k, k, 1], padding='SAME', name=name)
30. 
    
31.  # 归一化操作
32.  def norm(name, l_input, lsize=4):
33.      return tf.nn.lrn(l_input, lsize, bias=1.0, alpha=0.001 / 9.0, beta=0.75, name=name)
34. 
    
35.  # 定义整个网络 
36.  def alex_net(_X, _weights, _biases, _dropout):
37.      # 向量转为矩阵
38.      _X = tf.reshape(_X, shape=[-1, 28, 28, 1])
39. 
    
40.      # 卷积层
41.      conv1 = conv2d('conv1', _X, _weights['wc1'], _biases['bc1'])
42.      # 下采样层
43.      pool1 = max_pool('pool1', conv1, k=2)
44.      # 归一化层
45.      norm1 = norm('norm1', pool1, lsize=4)
46.      # Dropout
47.      norm1 = tf.nn.dropout(norm1, _dropout)
48. 
    
49.      # 卷积
50.      conv2 = conv2d('conv2', norm1, _weights['wc2'], _biases['bc2'])
51.      # 下采样
52.      pool2 = max_pool('pool2', conv2, k=2)
53.      # 归一化
54.      norm2 = norm('norm2', pool2, lsize=4)
55.      # Dropout
56.      norm2 = tf.nn.dropout(norm2, _dropout)
57. 
    
58.      # 卷积
59.      conv3 = conv2d('conv3', norm2, _weights['wc3'], _biases['bc3'])
60.      # 下采样
61.      pool3 = max_pool('pool3', conv3, k=2)
62.      # 归一化
63.      norm3 = norm('norm3', pool3, lsize=4)
64.      # Dropout
65.      norm3 = tf.nn.dropout(norm3, _dropout)
66. 
    
67.      # 全连接层，先把特征图转为向量
68.      dense1 = tf.reshape(norm3, [-1, _weights['wd1'].get_shape().as_list()[0]]) 
69.      dense1 = tf.nn.relu(tf.matmul(dense1, _weights['wd1']) + _biases['bd1'], name='fc1') 
70.      # 全连接层
71.      dense2 = tf.nn.relu(tf.matmul(dense1, _weights['wd2']) + _biases['bd2'], name='fc2') # Relu activation
72. 
    
73.      # 网络输出层
74.      out = tf.matmul(dense2, _weights['out']) + _biases['out']
75.      return out
76. 
    
77.  # 存储所有的网络参数
78.  weights = {
79.      'wc1': tf.Variable(tf.random_normal([3, 3, 1, 64])),
80.      'wc2': tf.Variable(tf.random_normal([3, 3, 64, 128])),
81.      'wc3': tf.Variable(tf.random_normal([3, 3, 128, 256])),
82.      'wd1': tf.Variable(tf.random_normal([4\*4\*256, 1024])),
83.      'wd2': tf.Variable(tf.random_normal([1024, 1024])),
84.      'out': tf.Variable(tf.random_normal([1024, 10]))
85.  }
86.  biases = {
87.      'bc1': tf.Variable(tf.random_normal([64])),
88.      'bc2': tf.Variable(tf.random_normal([128])),
89.      'bc3': tf.Variable(tf.random_normal([256])),
90.      'bd1': tf.Variable(tf.random_normal([1024])),
91.      'bd2': tf.Variable(tf.random_normal([1024])),
92.      'out': tf.Variable(tf.random_normal([n_classes]))
93.  }
94. 
    
95.  # 构建模型
96.  pred = alex_net(x, weights, biases, keep_prob)
97. 
    
98.  # 定义损失函数和学习步骤
99.  cost = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(pred, y))
100.  optimizer = tf.train.AdamOptimizer(learning_rate=learning_rate).minimize(cost)
101. 
     
102.  # 测试网络
103.  correct_pred = tf.equal(tf.argmax(pred,1), tf.argmax(y,1))
104.  accuracy = tf.reduce_mean(tf.cast(correct_pred, tf.float32))
105. 
     
106.  # 初始化所有的共享变量
107.  init = tf.initialize_all_variables()
108. 
     
109.  # 开启一个训练
110.  with tf.Session() as sess:
111.      sess.run(init)
112.      step = 1
113.      # Keep training until reach max iterations
114.      while step \* batch_size < training_iters:
115.          batch_xs, batch_ys = mnist.train.next_batch(batch_size)
116.          # 获取批数据
117.          sess.run(optimizer, feed_dict={x: batch_xs, y: batch_ys, keep_prob: dropout})
118.          if step % display_step == 0:
119.              # 计算精度
120.              acc = sess.run(accuracy, feed_dict={x: batch_xs, y: batch_ys, keep_prob: 1.})
121.              # 计算损失值
122.              loss = sess.run(cost, feed_dict={x: batch_xs, y: batch_ys, keep_prob: 1.})
123.              print "Iter " + str(step\*batch_size) + ", Minibatch Loss= " + "{:.6f}".format(loss) + ", Training Accuracy= " + "{:.5f}".format(acc)
124.          step += 1
125.      print "Optimization Finished!"
126.      # 计算测试精度
127.      print "Testing Accuracy:", sess.run(accuracy, feed_dict={x: mnist.test.images[:256], y: mnist.test.labels[:256], keep_prob: 1.})

　　基于mnist 构建alexnet，这里的input可以去tensorflow的github上去找找，这一版代码比较简单。