在上一講中，我們學習了如何利用 numpy 手動搭建卷積神經網絡。但在實際的圖像識別中，使用 numpy 去手寫 CNN 未免有些吃力不討好。在 DNN 的學習中，我們也是在手動搭建之后利用 Tensorflow 去重新實現一遍，一來為了能夠對神經網絡的傳播機制能夠理解更加透徹，二來也是為了更加高效使用開源框架快速搭建起深度學習項目。本節就繼續和大家一起學習如何利用 Tensorflow 搭建一個卷積神經網絡。

我們繼續以 NG 課題組提供的 sign 手勢數據集為例，學習如何通過 Tensorflow 快速搭建起一個深度學習項目。數據集標簽共有零到五總共 6 類標簽，示例如下：

先對數據進行簡單的預處理并查看訓練集和測試集維度：

X_train = X_train_orig/255.
X_test = X_test_orig/255.
Y_train = convert_to_one_hot(Y_train_orig, 6).T
Y_test = convert_to_one_hot(Y_test_orig, 6).T
print ("number of training examples = " + str(X_train.shape[0]))
print ("number of test examples = " + str(X_test.shape[0]))
print ("X_train shape: " + str(X_train.shape))
print ("Y_train shape: " + str(Y_train.shape))
print ("X_test shape: " + str(X_test.shape))
print ("Y_test shape: " + str(Y_test.shape))

可見我們總共有 1080 張 64643 訓練集圖像，120 張 64643 的測試集圖像，共有 6 類標簽。下面我們開始搭建過程。

創建 placeholder

首先需要為訓練集預測變量和目標變量創建占位符變量 placeholder ，定義創建占位符變量函數：

def create_placeholders(n_H0, n_W0, n_C0, n_y):  
  """
  Creates the placeholders for the tensorflow session.

  Arguments:
  n_H0 -- scalar, height of an input image
  n_W0 -- scalar, width of an input image
  n_C0 -- scalar, number of channels of the input
  n_y -- scalar, number of classes

  Returns:
  X -- placeholder for the data input, of shape [None, n_H0, n_W0, n_C0] and dtype "float"
  Y -- placeholder for the input labels, of shape [None, n_y] and dtype "float"
  """
  X = tf.placeholder(tf.float32, shape=(None, n_H0, n_W0, n_C0), name='X')
  Y = tf.placeholder(tf.float32, shape=(None, n_y), name='Y')  
  return X, Y

參數初始化

然后需要對濾波器權值參數進行初始化：

def initialize_parameters():  
  """
  Initializes weight parameters to build a neural network with tensorflow. 
  Returns:
  parameters -- a dictionary of tensors containing W1, W2
  """

  tf.set_random_seed(1)               

  W1 = tf.get_variable("W1", [4,4,3,8], initializer = tf.contrib.layers.xavier_initializer(seed = 0))
  W2 = tf.get_variable("W2", [2,2,8,16], initializer = tf.contrib.layers.xavier_initializer(seed = 0))

  parameters = {"W1": W1,         
         "W2": W2}  
  return parameters

執行卷積網絡的前向傳播過程

前向傳播過程如下所示：
CONV2D -> RELU -> MAXPOOL -> CONV2D -> RELU -> MAXPOOL -> FLATTEN -> FULLYCONNECTED

可見我們要搭建的是一個典型的 CNN 過程，經過兩次的卷積-relu激活-最大池化，然后展開接上一個全連接層。利用 Tensorflow 搭建上述傳播過程如下：

def forward_propagation(X, parameters):  
  """
  Implements the forward propagation for the model

  Arguments:
  X -- input dataset placeholder, of shape (input size, number of examples)
  parameters -- python dictionary containing your parameters "W1", "W2"
         the shapes are given in initialize_parameters

  Returns:
  Z3 -- the output of the last LINEAR unit
  """

  # Retrieve the parameters from the dictionary "parameters" 
  W1 = parameters['W1']
  W2 = parameters['W2']  
  # CONV2D: stride of 1, padding 'SAME'
  Z1 = tf.nn.conv2d(X,W1, strides = [1,1,1,1], padding = 'SAME')  
  # RELU
  A1 = tf.nn.relu(Z1)  
  # MAXPOOL: window 8x8, sride 8, padding 'SAME'
  P1 = tf.nn.max_pool(A1, ksize = [1,8,8,1], strides = [1,8,8,1], padding = 'SAME')  
  # CONV2D: filters W2, stride 1, padding 'SAME'
  Z2 = tf.nn.conv2d(P1,W2, strides = [1,1,1,1], padding = 'SAME')  
  # RELU
  A2 = tf.nn.relu(Z2)  
  # MAXPOOL: window 4x4, stride 4, padding 'SAME'
  P2 = tf.nn.max_pool(A2, ksize = [1,4,4,1], strides = [1,4,4,1], padding = 'SAME')  
  # FLATTEN
  P2 = tf.contrib.layers.flatten(P2)

  Z3 = tf.contrib.layers.fully_connected(P2, 6, activation_fn = None)  
  return Z3

計算當前損失

在 Tensorflow 中計算損失函數非常簡單，一行代碼即可：

def compute_cost(Z3, Y):  
  """
  Computes the cost
  Arguments:
  Z3 -- output of forward propagation (output of the last LINEAR unit), of shape (6, number of examples)
  Y -- "true" labels vector placeholder, same shape as Z3

  Returns:
  cost - Tensor of the cost function
  """

  cost = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(logits=Z3, labels=Y))  
  return cost

定義好上述過程之后，就可以封裝整體的訓練過程模型。可能你會問為什么沒有反向傳播，這里需要注意的是 Tensorflow 幫助我們自動封裝好了反向傳播過程，無需我們再次定義，在實際搭建過程中我們只需將前向傳播的網絡結構定義清楚即可。

封裝模型

def model(X_train, Y_train, X_test, Y_test, learning_rate = 0.009,
     num_epochs = 100, minibatch_size = 64, print_cost = True):  
  """
  Implements a three-layer ConvNet in Tensorflow:
  CONV2D -> RELU -> MAXPOOL -> CONV2D -> RELU -> MAXPOOL -> FLATTEN -> FULLYCONNECTED

  Arguments:
  X_train -- training set, of shape (None, 64, 64, 3)
  Y_train -- test set, of shape (None, n_y = 6)
  X_test -- training set, of shape (None, 64, 64, 3)
  Y_test -- test set, of shape (None, n_y = 6)
  learning_rate -- learning rate of the optimization
  num_epochs -- number of epochs of the optimization loop
  minibatch_size -- size of a minibatch
  print_cost -- True to print the cost every 100 epochs

  Returns:
  train_accuracy -- real number, accuracy on the train set (X_train)
  test_accuracy -- real number, testing accuracy on the test set (X_test)
  parameters -- parameters learnt by the model. They can then be used to predict.
  """

  ops.reset_default_graph()             
  tf.set_random_seed(1)               
  seed = 3                    
  (m, n_H0, n_W0, n_C0) = X_train.shape       
  n_y = Y_train.shape[1]              
  costs = []                   

  # Create Placeholders of the correct shape
  X, Y = create_placeholders(n_H0, n_W0, n_C0, n_y)  
  # Initialize parameters
  parameters = initialize_parameters()  
  # Forward propagation
  Z3 = forward_propagation(X, parameters)  
  # Cost function
  cost = compute_cost(Z3, Y)  
  # Backpropagation
  optimizer = tf.train.AdamOptimizer(learning_rate = learning_rate).minimize(cost)  # Initialize all the variables globally
  init = tf.global_variables_initializer()  
  # Start the session to compute the tensorflow graph
  with tf.Session() as sess:    
    # Run the initialization
    sess.run(init)    
    # Do the training loop
    for epoch in range(num_epochs):

      minibatch_cost = 0.
      num_minibatches = int(m / minibatch_size)
      seed = seed + 1
      minibatches = random_mini_batches(X_train, Y_train, minibatch_size, seed)      
      for minibatch in minibatches:        
        # Select a minibatch
        (minibatch_X, minibatch_Y) = minibatch
        _ , temp_cost = sess.run([optimizer, cost], feed_dict={X: minibatch_X, Y: minibatch_Y})
        minibatch_cost += temp_cost / num_minibatches      
        # Print the cost every epoch
      if print_cost == True and epoch % 5 == 0:        
        print ("Cost after epoch %i: %f" % (epoch, minibatch_cost))      
      if print_cost == True and epoch % 1 == 0:
        costs.append(minibatch_cost)    
    # plot the cost
    plt.plot(np.squeeze(costs))
    plt.ylabel('cost')
    plt.xlabel('iterations (per tens)')
    plt.title("Learning rate =" + str(learning_rate))
    plt.show()    # Calculate the correct predictions
    predict_op = tf.argmax(Z3, 1)
    correct_prediction = tf.equal(predict_op, tf.argmax(Y, 1))    
    # Calculate accuracy on the test set
    accuracy = tf.reduce_mean(tf.cast(correct_prediction, "float"))
    print(accuracy)
    train_accuracy = accuracy.eval({X: X_train, Y: Y_train})
    test_accuracy = accuracy.eval({X: X_test, Y: Y_test})
    print("Train Accuracy:", train_accuracy)
    print("Test Accuracy:", test_accuracy)    
    
    return train_accuracy, test_accuracy, parameters

對訓練集執行模型訓練：

_,_,parameters=model(X_train,Y_train,X_test,Y_test)

訓練迭代過程如下：

我們在訓練集上取得了 0.67 的準確率，在測試集上的預測準確率為 0.58 ，雖然效果并不顯著，模型也有待深度調優，但我們已經學會了如何用 Tensorflow 快速搭建起一個深度學習系統了。