吴恩达老师的《深度学习》系列课程学习笔记

【深度学习】卷积神经网络：应用

本次学习的主要内容是，使用 TensorFlow 实现模型，即：使用 TensorFlow 创建一个卷积神经网络来解决分类问题。

导入需要的包

import math
import numpy as np
import h5py
import matplotlib.pyplot as plt
import scipy
from PIL import Image
from scipy import ndimage
import tensorflow as tf
from tensorflow.python.framework import ops
from cnn_utils import *%matplotlib inline
np.random.seed(1)

加载前面使用过的的手势数据集（SIGNS dataset）

# Loading the data (signs)
X_train_orig, Y_train_orig, X_test_orig, Y_test_orig, classes = load_dataset()

查看数据集中某一个样本数据：

# Example of a picture
index = 6
plt.imshow(X_train_orig[index])
print ("y = " + str(np.squeeze(Y_train_orig[:, index])))

对数据进行一个简单的预处理，变为 One Hot，这在前面的学习中，详细介绍过这个操作。

创建占位符（placeholder）

TensorFlow 需要为输入数据创建占位符。

初始化参数

使用 tf.contrib.layers.xavier_initializer(seed = 0) 初始化权重。

# GRADED FUNCTION: initialize_parametersdef initialize_parameters():"""Initializes weight parameters to build a neural network with tensorflow. The shapes are:W1 : [4, 4, 3, 8]W2 : [2, 2, 8, 16]Returns:parameters -- a dictionary of tensors containing W1, W2"""tf.set_random_seed(1)                              # so that your "random" numbers match ours### START CODE HERE ### (approx. 2 lines of code)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))### END CODE HERE ###parameters = {"W1": W1,"W2": W2}return parameters

前向传播

在 TensorFlow 中，有内置的函数可以帮助我们实现卷积神经网络的前向传播过程：

# 输入X ，过滤器 W1，W1 过滤器在 X 上进行卷积
tf.nn.conv2d(X,W1, strides = [1,s,s,1], padding = ‘SAME’)# 输入A，函数使用大小为(f, f)的窗口和大小为(s,s)的步长进行最大池化
tf.nn.max_pool(A, ksize = [1,f,f,1], strides = [1,s,s,1], padding = ‘SAME’)# 激活函数 ReLU
tf.nn.relu(Z1)# 输入 P，该函数在保持批量大小的前提下，将每个例子扁平化为一个1D向量
tf.contrib.layers.flatten(P)# 给定一个扁平化的输入F，它返回使用全连接层计算的输出。
tf.contrib.layers.fully_connected(F, num_outputs)

CONV2D -> RELU -> MAXPOOL -> CONV2D -> RELU -> MAXPOOL -> FLATTEN -> FULLYCONNECTED

# GRADED FUNCTION: forward_propagationdef forward_propagation(X, parameters):"""Implements the forward propagation for the model:CONV2D -> RELU -> MAXPOOL -> CONV2D -> RELU -> MAXPOOL -> FLATTEN -> FULLYCONNECTEDArguments: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_parametersReturns:Z3 -- the output of the last LINEAR unit"""# Retrieve the parameters from the dictionary "parameters" W1 = parameters['W1']W2 = parameters['W2']### START CODE HERE #### CONV2D: stride of 1, padding 'SAME'Z1 = tf.nn.conv2d(X, W1, strides = [1, 1, 1, 1], padding='SAME')# RELUA1 = 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')# RELUA2 = 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')# FLATTENP2 = tf.contrib.layers.flatten(P2)# FULLY-CONNECTED without non-linear activation function (not not call softmax).# 6 neurons in output layer. Hint: one of the arguments should be "activation_fn=None" Z3 = tf.contrib.layers.fully_connected(P2, num_outputs=6, activation_fn=None)### END CODE HERE ###return Z3

计算代价 Cost

# GRADED FUNCTION: compute_cost def compute_cost(Z3, Y):"""Computes the costArguments: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 Z3Returns:cost - Tensor of the cost function"""### START CODE HERE ### (1 line of code)cost = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(logits=Z3, labels=Y))### END CODE HERE ###return cost

模型

创建模型的基本操作有：

• create placeholders
• initialize parameters
• forward propagate
• compute the cost
• create an optimizer

# GRADED FUNCTION: modeldef 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 -> FULLYCONNECTEDArguments: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 optimizationnum_epochs -- number of epochs of the optimization loopminibatch_size -- size of a minibatchprint_cost -- True to print the cost every 100 epochsReturns: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()                         # to be able to rerun the model without overwriting tf variablestf.set_random_seed(1)                             # to keep results consistent (tensorflow seed)seed = 3                                          # to keep results consistent (numpy seed)(m, n_H0, n_W0, n_C0) = X_train.shape             n_y = Y_train.shape[1]                            costs = []                                        # To keep track of the cost# Create Placeholders of the correct shape### START CODE HERE ### (1 line)X, Y = create_placeholders(n_H0, n_W0, n_C0, n_y)### END CODE HERE #### Initialize parameters### START CODE HERE ### (1 line)parameters = initialize_parameters()### END CODE HERE #### Forward propagation: Build the forward propagation in the tensorflow graph### START CODE HERE ### (1 line)Z3 = forward_propagation(X, parameters)### END CODE HERE #### Cost function: Add cost function to tensorflow graph### START CODE HERE ### (1 line)cost = compute_cost(Z3, Y)### END CODE HERE #### Backpropagation: Define the tensorflow optimizer. Use an AdamOptimizer that minimizes the cost.### START CODE HERE ### (1 line)optimizer = tf.train.AdamOptimizer(learning_rate=learning_rate).minimize(cost)### END CODE HERE #### Initialize all the variables globallyinit = tf.global_variables_initializer()# Start the session to compute the tensorflow graphwith tf.Session() as sess:# Run the initializationsess.run(init)# Do the training loopfor epoch in range(num_epochs):minibatch_cost = 0.num_minibatches = int(m / minibatch_size) # number of minibatches of size minibatch_size in the train setseed = seed + 1minibatches = random_mini_batches(X_train, Y_train, minibatch_size, seed)for minibatch in minibatches:# Select a minibatch(minibatch_X, minibatch_Y) = minibatch# IMPORTANT: The line that runs the graph on a minibatch.# Run the session to execute the optimizer and the cost, the feedict should contain a minibatch for (X,Y).### START CODE HERE ### (1 line)_ , temp_cost = sess.run([optimizer, cost], feed_dict={X:minibatch_X, Y:minibatch_Y})### END CODE HERE ###minibatch_cost += temp_cost / num_minibatches# Print the cost every epochif 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 costplt.plot(np.squeeze(costs))plt.ylabel('cost')plt.xlabel('iterations (per tens)')plt.title("Learning rate =" + str(learning_rate))plt.show()# Calculate the correct predictionspredict_op = tf.argmax(Z3, 1)correct_prediction = tf.equal(predict_op, tf.argmax(Y, 1))# Calculate accuracy on the test setaccuracy = 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

在训练了 100 epochs 后，模型的表现如下：

这个模型在测试集上识别手势图片的准确率接近 80%，而训练集上的准确率接近 93%，显然，模型的方差很大，模型出现了过拟合的现象。

总结

本次学到的主要内容有：

• 使用 TensorFlow 实现卷积神经网络
• 实现一个模型，并且进行训练，准确率达到了近 80%

PS：欢迎关注我的公众号「蓝本本」，和我一起学习、进修和放纵好奇心。