文章出處：深度學(xué)習(xí)筆記11：利用numpy搭建一個卷積神經(jīng)網(wǎng)絡(luò)
免費視頻課程：Hellobi Live | 從數(shù)據(jù)分析師到機(jī)器學(xué)習(xí)(深度學(xué)習(xí))工程師的進(jìn)階之路

?

在上一講中，我們學(xué)習(xí)了如何利用?numpy?手動搭建卷積神經(jīng)網(wǎng)絡(luò)。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(xué)習(xí)中，我們也是在手動搭建之后利用?Tensorflow?去重新實現(xiàn)一遍，一來為了能夠?qū)ι窠?jīng)網(wǎng)絡(luò)的傳播機(jī)制能夠理解更加透徹，二來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?搭建一個卷積神經(jīng)網(wǎng)絡(luò)。

我們繼續(xù)以 NG 課題組提供的 sign 手勢數(shù)據(jù)集為例，學(xué)習(xí)如何通過?Tensorflow?快速搭建起一個深度學(xué)習(xí)項目。數(shù)據(jù)集標(biāo)簽共有零到五總共 6 類標(biāo)簽，示例如下：

?

先對數(shù)據(jù)進(jìn)行簡單的預(yù)處理并查看訓(xùn)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(xùn)練集圖像，120 張 64643 的測試集圖像，共有 6 類標(biāo)簽。下面我們開始搭建過程。

創(chuàng)建?placeholder

首先需要為訓(xùn)練集預(yù)測變量和目標(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(jīng)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(dāng)前損失

在?Tensorflow?中計算損失函數(shù)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(xùn)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(wǎng)絡(luò)結(jié)構(gòu)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(xùn)練集執(zhí)行模型訓(xùn)練：

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

訓(xùn)練迭代過程如下：

?

?

?

?

我們在訓(xùn)練集上取得了 0.67 的準(zhǔn)確率，在測試集上的預(yù)測準(zhǔn)確率為 0.58 ，雖然效果并不顯著，模型也有待深度調(diào)優(yōu)，但我們已經(jīng)學(xué)會了如何用?Tensorflow?快速搭建起一個深度學(xué)習(xí)系統(tǒng)了。

?

?

?

?

注：本深度學(xué)習(xí)筆記系作者學(xué)習(xí) Andrew NG 的 deeplearningai 五門課程所記筆記，其中代碼為每門課的課后assignments作業(yè)整理而成。

?

參考資料：

https://www.coursera.org/learn/machine-learning

https://www.deeplearning.ai/

總結(jié)

以上是生活随笔為你收集整理的深度学习笔记：卷积神经网络的Tensorflow实现的全部內(nèi)容，希望文章能夠幫你解決所遇到的問題。

如果覺得生活随笔網(wǎng)站內(nèi)容還不錯，歡迎將生活随笔推薦給好友。