????? 在上一講中商叹，我們學(xué)習(xí)了如何利用 numpy 手動(dòng)搭建卷積神經(jīng)網(wǎng)絡(luò)估蹄。但在實(shí)際的圖像識(shí)別中次绘，使用 numpy 去手寫 CNN 未免有些吃力不討好始锚。在 DNN 的學(xué)習(xí)中，我們也是在手動(dòng)搭建之后利用 Tensorflow 去重新實(shí)現(xiàn)一遍喳逛，一來(lái)為了能夠?qū)ι窠?jīng)網(wǎng)絡(luò)的傳播機(jī)制能夠理解更加透徹瞧捌，二來(lái)也是為了更加高效使用開源框架快速搭建起深度學(xué)習(xí)項(xiàng)目。本節(jié)就繼續(xù)和大家一起學(xué)習(xí)如何利用 Tensorflow 搭建一個(gè)卷積神經(jīng)網(wǎng)絡(luò)润文。
????? 我們繼續(xù)以 NG 課題組提供的 sign 手勢(shì)數(shù)據(jù)集為例姐呐，學(xué)習(xí)如何通過(guò) Tensorflow 快速搭建起一個(gè)深度學(xué)習(xí)項(xiàng)目。數(shù)據(jù)集標(biāo)簽共有零到五總共 6 類標(biāo)簽典蝌，示例如下：
????? 先對(duì)數(shù)據(jù)進(jìn)行簡(jiǎn)單的預(yù)處理并查看訓(xùn)練集和測(cè)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(jiàn)我們總共有 1080 張 64643 訓(xùn)練集圖像曙砂，120 張 64643 的測(cè)試集圖像，共有 6 類標(biāo)簽骏掀。下面我們開始搭建過(guò)程鸠澈。
創(chuàng)建 placeholder
????? 首先需要為訓(xùn)練集預(yù)測(cè)變量和目標(biāo)變量創(chuàng)建占位符變量 placeholder ，定義創(chuàng)建占位符變量函數(shù)：
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(shù)初始化
????? 然后需要對(duì)濾波器權(quán)值參數(shù)進(jìn)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(zhí)行卷積網(wǎng)絡(luò)的前向傳播過(guò)程
前向傳播過(guò)程如下所示：
CONV2D -> RELU -> MAXPOOL -> CONV2D -> RELU -> MAXPOOL -> FLATTEN -> FULLYCONNECTED
可見(jiàn)我們要搭建的是一個(gè)典型的 CNN 過(guò)程截驮，經(jīng)過(guò)兩次的卷積-relu激活-最大池化笑陈，然后展開接上一個(gè)全連接層。利用
Tensorflow ?搭建上述傳播過(guò)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(jì)算當(dāng)前損失
????? 在 Tensorflow ?中計(jì)算損失函數(shù)非常簡(jiǎn)單葵袭，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(guò)程之后涵妥，就可以封裝整體的訓(xùn)練過(guò)程模型∑挛可能你會(huì)問(wèn)為什么沒(méi)有反向傳播蓬网，這里需要注意的是 Tensorflow 幫助我們自動(dòng)封裝好了反向傳播過(guò)程，無(wú)需我們?cè)俅味x鹉勒，在實(shí)際搭建過(guò)程中我們只需將前向傳播的網(wǎng)絡(luò)結(jié)構(gòu)定義清楚即可帆锋。
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(duì)訓(xùn)練集執(zhí)行模型訓(xùn)練：
_, _, parameters = model(X_train, Y_train, X_test, Y_test)
?????訓(xùn)練迭代過(guò)程如下：
????我們?cè)谟?xùn)練集上取得了 0.67 的準(zhǔn)確率，在測(cè)試集上的預(yù)測(cè)準(zhǔn)確率為 0.58 贸弥，雖然效果并不顯著窟坐，模型也有待深度調(diào)優(yōu)，但我們已經(jīng)學(xué)會(huì)了如何用 Tensorflow ?快速搭建起一個(gè)深度學(xué)習(xí)系統(tǒng)了
