DeepLearing学习笔记-Planar data classification with one hidden layer(第三周作业)

0 - 背景：

前文，创建的神经网络只有一个输出层，没有隐藏层。本文将创建单隐藏层的神经网络模型。

• 二分类单隐藏层的神经网络
• 神经元节点采用非线性的激活函数，如tanh
• 计算交叉损失函数
• 运用前向和后向传播

1- 准备条件：

本文实践过程需要以下的python库：

• numpy Python中常用的科学计算库
• sklearn 是常用的数据挖掘和分析库
• matplotlib 是用于数据可视化
• testCases 是用以测试相对应函数的测试例子
• planar_utils 是本文实践中需要用到其他一些函数

模块加载代码：

import numpy as np
import matplotlib.pyplot as plt
from testCases import *
import sklearn
import sklearn.datasets
import sklearn.linear_model
from planar_utils import plot_decision_boundary, sigmoid, load_planar_dataset, load_extra_datasets

%matplotlib inline

np.random.seed(1) # set a seed so that the results are consistent

sklearn 的安装：
pip install sklearn

2-数据集介绍

下述代码将加载一个二分类的数据集并进行可视化：

X, Y = load_planar_dataset()
# Visualize the data:
plt.scatter(X[0, :], X[1, :], c=Y, s=40, cmap=plt.cm.Spectral);

可视化结果：

我们可以看出，数据点分布呈现一个花型，其中红色点表示y=0，蓝色点表示y=1。我们的目标是创建一个模型以能够分开这两类数据。
其中X是一个矩阵，包含着数据的特征信息$（x1，x2）$
Y是一个向量，包含这数据对应的标记结果，其中$(red:0, blue:1)$
尺寸信息：

### START CODE HERE ### (≈ 3 lines of code)
shape_X = X.shape
shape_Y = Y.shape
m = shape_X[1]  # training set size
### END CODE HERE ###

print ('The shape of X is: ' + str(shape_X))
print ('The shape of Y is: ' + str(shape_Y))
print ('I have m = %d training examples!' % (m))

运行结果：

The shape of X is: (2, 400)
The shape of Y is: (1, 400)
I have m = 400 training examples!

3 - 简单逻辑回归

在创建一个全神经网络之前，我们先看看逻辑回归对于这类问题是如何处理的。为此，我们可以采用sklearn的’s built-in函数实现：

# Train the logistic regression classifier
clf = sklearn.linear_model.LogisticRegressionCV();
clf.fit(X.T, Y.T);

运行结果会有如下提示：

c:\users\jason\appdata\local\programs\python\python35\lib\site-packages\sklearn\utils\validation.py:547: DataConversionWarning: A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples, ), for example using ravel().
  y = column_or_1d(y, warn=True)

上述的警告信息，可以根据提示通过Y = Y.ravel()将Y进行转换，使得尺寸从(1, 400)变为(400,)。

现在绘制出模型的边界：

# Plot the decision boundary for logistic regression
plot_decision_boundary(lambda x: clf.predict(x), X, Y)#会有告警信息
plt.title("Logistic Regression")

# Print accuracy
LR_predictions = clf.predict(X.T)
print ('Accuracy of logistic regression: %d ' % float((np.dot(Y,LR_predictions) + np.dot(1-Y,1-LR_predictions))/float(Y.size)*100) +
       '% ' + "(percentage of correctly labelled datapoints)")

输出：

Accuracy of logistic regression: 47 % (percentage of correctly labelled datapoints)

从输出结果，我们可以看出准确率为47%，数据集并不能够通过逻辑回归被很好地被线性划分。由此，我们才需要本文的正题-神经网络。

4 - 神经网络模型

从上述的逻辑回归结果我们可以看出该模型对于花形数据表现不佳，为此我们采用单隐藏层的神经网络作为尝试，模型如下：

该模型在输入层和输出层之间，只有一个隐藏层。隐藏层的激活函数是$\tanh$，输出层的激活函数是$\sigma$

模型的数学公式:

对于训练样本$x^{(i)}$:

$$z^{[1] (i)} = W^{[1]} x^{(i)} + b^{[1] (i)}\tag{1}$$
$$a^{[1] (i)} = \tanh(z^{[1] (i)})\tag{2}$$
$$z^{[2] (i)} = W^{[2]} a^{[1] (i)} + b^{[2] (i)}\tag{3}$$
$$\hat{y}^{(i)} = a^{[2] (i)} = \sigma(z^{ [2] (i)})\tag{4}$$
$$y^{(i)}_{prediction} = \begin{cases} 1 & \mbox{if } a^{[2](i)} > 0.5 \\ 0 & \mbox{otherwise } \end{cases}\tag{5}$$

根据之前单个样本的代价函数：

$$log(p(y|x))=log (\hat{y}^y(1-\hat{y})^{(1-y)}) =ylog\hat{y} + (1-y)log(1-\hat{y})=-\mathcal{L}(\hat{y}-y)tag{6}$$
上述逻辑回归的损失函数，也被称为 cross-entropy loss,用于度量两个概率分布之间的相似性。

而m个样本的代价函数：

$$J(w,b)= \frac{1}{m}\sum_{i=1}^m\mathcal{L}(\hat{y}-y)\tag{7}$$

在计算完所有样本的预测值之后，我们可以计算整体的代价函数$J$：

$$J = - \frac{1}{m} \sum\limits_{i = 0}^{m} \large\left(\small y^{(i)}\log\left(a^{[2] (i)}\right) + (1-y^{(i)})\log\left(1- a^{[2] (i)}\right) \large \right) \small \tag{8}$$

注意: 建立神经网络的一般方法如下:
1. 定义神经网络的结构 ( 输入单元数量, 隐藏层单元数量等等).
2. 初始化模型的参数
3. 迭代循环：
- 前向传播
- 计算损失函数
- 后向传播，计算梯度
- 更新参数 (梯度下降)

一般习惯将上述1-3步分别定义成一个独立的函数，再通过模型函数将三者融合一起。在建立模型之后，迭代获取到参数之后，即可对新数据进行预测。

4-1 定义神经网络的结构

定义如下三个参数的值：
- n_x: 输入层的神经元数
- n_h: 隐藏层的神经元数(本文设置为4)
- n_y: 输出层的神经元数

# GRADED FUNCTION: layer_sizes

def layer_sizes(X, Y):
    """
    Arguments:
    X -- input dataset of shape (input size, number of examples)
    Y -- labels of shape (output size, number of examples)

    Returns:
    n_x -- the size of the input layer
    n_h -- the size of the hidden layer
    n_y -- the size of the output layer
    """
    ### START CODE HERE ### (≈ 3 lines of code)
    n_x = X.shape[0] # size of input layer
    n_h = 4
    n_y = Y.shape[0] # size of output layer
    ### END CODE HERE ###
    return (n_x, n_h, n_y)

4-2 模型参数初始化

注意参数尺寸要与上述模型一致。在定义参数的时候，对于权重矩阵我们进行随机初始化：np.random.randn(a,b) * 0.01 以获取一个尺寸为(a，b)的随机矩阵。
对于参数b，我们直接初始化为0，np.zeros((a,b))
初始化代码如下：

# GRADED FUNCTION: initialize_parameters

def initialize_parameters(n_x, n_h, n_y):
    """
    Argument:
    n_x -- size of the input layer
    n_h -- size of the hidden layer
    n_y -- size of the output layer

    Returns:
    params -- python dictionary containing your parameters:
                    W1 -- weight matrix of shape (n_h, n_x)
                    b1 -- bias vector of shape (n_h, 1)
                    W2 -- weight matrix of shape (n_y, n_h)
                    b2 -- bias vector of shape (n_y, 1)
    """

    np.random.seed(2) # we set up a seed so that your output matches ours although the initialization is random.

    ### START CODE HERE ### (≈ 4 lines of code)
    W1 = np.random.randn(n_h,n_x) * 0.01
    b1 = np.zeros((n_h,1))
    W2 = np.random.randn(n_y,n_h) * 0.01
    b2 = np.zeros((n_y,1))
    ### END CODE HERE ###

    assert (W1.shape == (n_h, n_x))
    assert (b1.shape == (n_h, 1))
    assert (W2.shape == (n_y, n_h))
    assert (b2.shape == (n_y, 1))

    parameters = {"W1": W1,
                  "b1": b1,
                  "W2": W2,
                  "b2": b2}

    return parameters

4-3 迭代循环

4-3-1 前向传播

为前向传播定义一个函数，在隐藏层的激活函数是tanh，在输出层的激活函数是sigmoid。利用初始化的参数计算$Z^{[1]}, A^{[1]}, Z^{[2]}$ 和 $A^{[2]}$，同时注意保留值到cache，因为在后续的后向传播需要用到。
前向传播代码：

# GRADED FUNCTION: forward_propagation

def forward_propagation(X, parameters):
    """
    Argument:
    X -- input data of size (n_x, m)
    parameters -- python dictionary containing your parameters (output of initialization function)

    Returns:
    A2 -- The sigmoid output of the second activation
    cache -- a dictionary containing "Z1", "A1", "Z2" and "A2"
    """
    # Retrieve each parameter from the dictionary "parameters"
    ### START CODE HERE ### (≈ 4 lines of code)
    W1 = parameters["W1"]
    b1 = parameters["b1"]
    W2 = parameters["W2"]
    b2 = parameters["b2"]
    ### END CODE HERE ###

    # Implement Forward Propagation to calculate A2 (probabilities)
    ### START CODE HERE ### (≈ 4 lines of code)
    Z1 = np.dot(W1,X)+b1
    A1 = np.tanh(Z1)
    Z2 = np.dot(W2,A1)+b2
    A2 = 1/(1+np.exp(-Z2))
    ### END CODE HERE ###
    #可以在此打印查看变量的尺寸值
    print("Z1 size=",Z1.shape)
    print("A1 size=",A1.shape)
    print("Z2 size=",Z2.shape)
    print("A2 size=",A2.shape)
    assert(A2.shape == (1, X.shape[1]))

    cache = {"Z1": Z1,
             "A1": A1,
             "Z2": Z2,
             "A2": A2}

    return A2, cache

测试代码：

def forward_propagation_test_case():
    np.random.seed(1)
    X_assess = np.random.randn(2, 3)

    parameters = {'W1': np.array([[-0.00416758, -0.00056267],
        [-0.02136196,  0.01640271],
        [-0.01793436, -0.00841747],
        [ 0.00502881, -0.01245288]]),
     'W2': np.array([[-0.01057952, -0.00909008,  0.00551454,  0.02292208]]),
     'b1': np.array([[ 0.],
        [ 0.],
        [ 0.],
        [ 0.]]),
     'b2': np.array([[ 0.]])}

    return X_assess, parameters


X_assess, parameters = forward_propagation_test_case()
print(X_assess.shape)
A2, cache = forward_propagation(X_assess, parameters)

# Note: we use the mean here just to make sure that your output matches ours. 
print(np.mean(cache['Z1']) ,np.mean(cache['A1']),np.mean(cache['Z2']),np.mean(cache['A2']))

输出结果：

(2, 3)
Z1 size= (4, 3)
A1 size= (4, 3)
Z2 size= (1, 3)
A2 size= (1, 3)
-0.000499755777742 -0.000496963353232 0.000438187450959 0.500109546852

注意各个参数的尺寸。

4-3-2 代价函数

在输出的cache中，我们是记录了 $A^{[2]}$（在代码中用A2表示），该结果包含了$a^{[2](i)}$ 的所有值，即整个样本。为此，我们可以计算整个样本的代价函数：

$$J = - \frac{1}{m} \sum\limits_{i = 0}^{m} \large{(} \small y^{(i)}\log\left(a^{[2] (i)}\right) + (1-y^{(i)})\log\left(1- a^{[2] (i)}\right) \large{)} \small\tag{9}$$

在python中计算交叉熵损失函数$- \sum\limits_{i=0}^{m} y^{(i)}\log(a^{[2](i)})$可以用如下的两步骤实现:

logprobs = np.multiply(np.log(A2),Y)    #对应元素相乘
cost = - np.sum(logprobs)                # no need to use a for loop!

代码实现：

# GRADED FUNCTION: compute_cost

def compute_cost(A2, Y, parameters):
    """
    Computes the cross-entropy cost given in equation (13)

    Arguments:
    A2 -- The sigmoid output of the second activation, of shape (1, number of examples)
    Y -- "true" labels vector of shape (1, number of examples)
    parameters -- python dictionary containing your parameters W1, b1, W2 and b2

    Returns:
    cost -- cross-entropy cost given equation (13)
    """

    m = Y.shape[1] # number of example

    # Compute the cross-entropy cost
    ### START CODE HERE ### (≈ 2 lines of code)
    logprobs = np.multiply(np.log(A2),Y)+np.multiply(np.log(1-A2),1-Y)
    cost = -np.sum(logprobs)/m
    ### END CODE HERE ###

    cost = np.squeeze(cost)     # makes sure cost is the dimension we expect. 
                                # E.g., turns [[17]] into 17 
    assert(isinstance(cost, float))

    return cost

测试代码：

def compute_cost_test_case():
    np.random.seed(1)
    Y_assess = np.random.randn(1, 3)
    parameters = {'W1': np.array([[-0.00416758, -0.00056267],
        [-0.02136196,  0.01640271],
        [-0.01793436, -0.00841747],
        [ 0.00502881, -0.01245288]]),
     'W2': np.array([[-0.01057952, -0.00909008,  0.00551454,  0.02292208]]),
     'b1': np.array([[ 0.],
        [ 0.],
        [ 0.],
        [ 0.]]),
     'b2': np.array([[ 0.]])}

    a2 = (np.array([[ 0.5002307 ,  0.49985831,  0.50023963]]))

    return a2, Y_assess, parameters


A2, Y_assess, parameters = compute_cost_test_case()

print("cost = " + str(compute_cost(A2, Y_assess, parameters)))

运行结果：

cost = 0.692919893776

4-3-3 后向传播

基于前向传播过程中的cache，我们开始计算后向传播。后向传播的公式如下：

$\frac{\partial \mathcal{J} }{ \partial z_{2}^{(i)} } = \frac{1}{m} (a^{[2](i)} - y^{(i)})$

$\frac{\partial \mathcal{J} }{ \partial W_2 } = \frac{\partial \mathcal{J} }{ \partial z_{2}^{(i)} } a^{[1] (i) T}$

$\frac{\partial \mathcal{J} }{ \partial b_2 } = \sum_i{\frac{\partial \mathcal{J} }{ \partial z_{2}^{(i)}}}$

$\frac{\partial \mathcal{J} }{ \partial z_{1}^{(i)} } = W_2^T \frac{\partial \mathcal{J} }{ \partial z_{2}^{(i)} } * ( 1 - a^{[1] (i) 2})$

$\frac{\partial \mathcal{J} }{ \partial W_1 } = \frac{\partial \mathcal{J} }{ \partial z_{1}^{(i)} } X^T$

$\frac{\partial \mathcal{J} _i }{ \partial b_1 } = \sum_i{\frac{\partial \mathcal{J} }{ \partial z_{1}^{(i)}}}$

• 注意 $*$ 表示元素之间的乘积。

• 代码中的符号对应以下的信息:

  • dW1 = $\frac{\partial \mathcal{J} }{ \partial W_1 }$
  • db1 = $\frac{\partial \mathcal{J} }{ \partial b_1 }$
  • dW2 = $\frac{\partial \mathcal{J} }{ \partial W_2 }$
  • db2 = $\frac{\partial \mathcal{J} }{ \partial b_2 }$

  • 建议:

    • 在计算dZ1时候，我们需要先计算 $g^{[1]'}(Z^{[1]})$。这是由于 $g^{[1]}(.)$ is的激活函数是tanh，当$a = g^{[1]}(z)$则$g^{[1]'}(z) = 1-a^2$。为此，我们可以用(1 - np.power(A1, 2))来计算$g^{[1]'}(Z^{[1]})$

  • 代码实现：

    # GRADED FUNCTION: backward_propagation
    
    def backward_propagation(parameters, cache, X, Y):
        """
        Implement the backward propagation using the instructions above.
    
        Arguments:
        parameters -- python dictionary containing our parameters 
        cache -- a dictionary containing "Z1", "A1", "Z2" and "A2".
        X -- input data of shape (2, number of examples)
        Y -- "true" labels vector of shape (1, number of examples)
    
        Returns:
        grads -- python dictionary containing your gradients with respect to different parameters
        """
        m = X.shape[1]
    
        # First, retrieve W1 and W2 from the dictionary "parameters".
        ### START CODE HERE ### (≈ 2 lines of code)
        W1 = parameters["W1"]
        W2 = parameters["W2"]
        ### END CODE HERE ###
    
        # Retrieve also A1 and A2 from dictionary "cache".
        ### START CODE HERE ### (≈ 2 lines of code)
        A1 = cache["A1"]
        A2 = cache["A2"]
        ### END CODE HERE ###
    
        # Backward propagation: calculate dW1, db1, dW2, db2. 
        ### START CODE HERE ### (≈ 6 lines of code, corresponding to 6 equations on slide above)
        dZ2 = A2-Y
        dW2 = np.dot(dZ2, A1.T)/m
        db2 = np.sum(dZ2, axis=1, keepdims=True)/m
        dZ1 = np.dot(W2.T,dZ2)*(1-np.power(A1,2))#np.multiply(np.dot(W2.T, dZ2), (1 - np.power(A1, 2)))
        dW1 = np.dot(dZ1, X.T)/m
        db1 = np.sum(dZ1, axis=1, keepdims=True)/m
        ### END CODE HERE ###
    
        grads = {"dW1": dW1,
                 "db1": db1,
                 "dW2": dW2,
                 "db2": db2}
    
        return grads

    测试代码：

    def backward_propagation_test_case():
        np.random.seed(1)
        X_assess = np.random.randn(2, 3)
        Y_assess = np.random.randn(1, 3)
        parameters = {'W1': np.array([[-0.00416758, -0.00056267],
            [-0.02136196,  0.01640271],
            [-0.01793436, -0.00841747],
            [ 0.00502881, -0.01245288]]),
         'W2': np.array([[-0.01057952, -0.00909008,  0.00551454,  0.02292208]]),
         'b1': np.array([[ 0.],
            [ 0.],
            [ 0.],
            [ 0.]]),
         'b2': np.array([[ 0.]])}
    
        cache = {'A1': np.array([[-0.00616578,  0.0020626 ,  0.00349619],
             [-0.05225116,  0.02725659, -0.02646251],
             [-0.02009721,  0.0036869 ,  0.02883756],
             [ 0.02152675, -0.01385234,  0.02599885]]),
      'A2': np.array([[ 0.5002307 ,  0.49985831,  0.50023963]]),
      'Z1': np.array([[-0.00616586,  0.0020626 ,  0.0034962 ],
             [-0.05229879,  0.02726335, -0.02646869],
             [-0.02009991,  0.00368692,  0.02884556],
             [ 0.02153007, -0.01385322,  0.02600471]]),
      'Z2': np.array([[ 0.00092281, -0.00056678,  0.00095853]])}
        return parameters, cache, X_assess, Y_assess
    
    
    parameters, cache, X_assess, Y_assess = backward_propagation_test_case()
    
    grads = backward_propagation(parameters, cache, X_assess, Y_assess)
    print ("dW1 = "+ str(grads["dW1"]))
    print ("db1 = "+ str(grads["db1"]))
    print ("dW2 = "+ str(grads["dW2"]))
    print ("db2 = "+ str(grads["db2"]))

    运行结果如下：

    dW1 = [[ 0.01018708 -0.00708701]
     [ 0.00873447 -0.0060768 ]
     [-0.00530847  0.00369379]
     [-0.02206365  0.01535126]]
    db1 = [[-0.00069728]
     [-0.00060606]
     [ 0.000364  ]
     [ 0.00151207]]
    dW2 = [[ 0.00363613  0.03153604  0.01162914 -0.01318316]]
    db2 = [[ 0.06589489]]

    4-3-4 参数更新

    上述的结果我们已经可以计算出反向传播的梯度了，那么我们就可以通过梯度下降法对参数进行更新：
    $\theta = \theta - \alpha \frac{\partial J }{ \partial \theta }$ 其中 $\alpha$ 是学习率 $\theta$ 则是代表待更新的参数。
    选择好的学习率，迭代才会收敛，否则迭代过程不断振荡，呈发散状态。
    

    

    参数更新代码：

    # GRADED FUNCTION: update_parameters
    
    def update_parameters(parameters, grads, learning_rate = 1.2):
        """
        Updates parameters using the gradient descent update rule given above
    
        Arguments:
        parameters -- python dictionary containing your parameters 
        grads -- python dictionary containing your gradients 
    
        Returns:
        parameters -- python dictionary containing your updated parameters 
        """
        # Retrieve each parameter from the dictionary "parameters"
        ### START CODE HERE ### (≈ 4 lines of code)
        W1 = parameters["W1"]
        b1 = parameters["b1"]
        W2 = parameters["W2"]
        b2 = parameters["b2"]
        ### END CODE HERE ###
    
        # Retrieve each gradient from the dictionary "grads"
        ### START CODE HERE ### (≈ 4 lines of code)
        dW1 = grads["dW1"]
        db1 = grads["db1"]
        dW2 = grads["dW2"]
        db2 = grads["db2"]
        ## END CODE HERE ###
    
        # Update rule for each parameter
        ### START CODE HERE ### (≈ 4 lines of code)
        W1 -= learning_rate * dW1
        b1 -= learning_rate * db1
        W2 -= learning_rate * dW2
        b2 -= learning_rate * db2
        ### END CODE HERE ###
    
        parameters = {"W1": W1,
                      "b1": b1,
                      "W2": W2,
                      "b2": b2}
    
        return parameters

    测试代码：

    def update_parameters_test_case():
        parameters = {'W1': np.array([[-0.00615039,  0.0169021 ],
            [-0.02311792,  0.03137121],
            [-0.0169217 , -0.01752545],
            [ 0.00935436, -0.05018221]]),
     'W2': np.array([[-0.0104319 , -0.04019007,  0.01607211,  0.04440255]]),
     'b1': np.array([[ -8.97523455e-07],
            [  8.15562092e-06],
            [  6.04810633e-07],
            [ -2.54560700e-06]]),
     'b2': np.array([[  9.14954378e-05]])}
    
        grads = {'dW1': np.array([[ 0.00023322, -0.00205423],
            [ 0.00082222, -0.00700776],
            [-0.00031831,  0.0028636 ],
            [-0.00092857,  0.00809933]]),
     'dW2': np.array([[ -1.75740039e-05,   3.70231337e-03,  -1.25683095e-03,
              -2.55715317e-03]]),
     'db1': np.array([[  1.05570087e-07],
            [ -3.81814487e-06],
            [ -1.90155145e-07],
            [  5.46467802e-07]]),
     'db2': np.array([[ -1.08923140e-05]])}
        return parameters, grads
    
    
    
    parameters, grads = update_parameters_test_case()
    parameters = update_parameters(parameters, grads)
    
    print("W1 = " + str(parameters["W1"]))
    print("b1 = " + str(parameters["b1"]))
    print("W2 = " + str(parameters["W2"]))
    print("b2 = " + str(parameters["b2"]))

    测试运行结果：

    W1 = [[-0.00643025  0.01936718]
     [-0.02410458  0.03978052]
     [-0.01653973 -0.02096177]
     [ 0.01046864 -0.05990141]]
    b1 = [[ -1.02420756e-06]
     [  1.27373948e-05]
     [  8.32996807e-07]
     [ -3.20136836e-06]]
    W2 = [[-0.01041081 -0.04463285  0.01758031  0.04747113]]
    b2 = [[ 0.00010457]]

    4-4 模型融合

    将上述4-1~4-3的各个模块进行整合成一个完整的神经网络模型。代码如下：

    # GRADED FUNCTION: nn_model
    
    def nn_model(X, Y, n_h, num_iterations = 10000, print_cost=False):
        """
        Arguments:
        X -- dataset of shape (2, number of examples)
        Y -- labels of shape (1, number of examples)
        n_h -- size of the hidden layer
        num_iterations -- Number of iterations in gradient descent loop
        print_cost -- if True, print the cost every 1000 iterations
    
        Returns:
        parameters -- parameters learnt by the model. They can then be used to predict.
        """
    
        np.random.seed(3)
        n_x = layer_sizes(X, Y)[0]
        n_y = layer_sizes(X, Y)[2]
    
        # Initialize parameters, then retrieve W1, b1, W2, b2. Inputs: "n_x, n_h, n_y". Outputs = "W1, b1, W2, b2, parameters".
        ### START CODE HERE ### (≈ 5 lines of code)
        parameters = initialize_parameters(n_x, n_h, n_y)
        W1 = parameters["W1"]
        b1 = parameters["b1"]
        W2 = parameters["W2"]
        b2 = parameters["b2"]
        ### END CODE HERE ###
    
        # Loop (gradient descent)
    
        for i in range(0, num_iterations):
    
            ### START CODE HERE ### (≈ 4 lines of code)
            # Forward propagation. Inputs: "X, parameters". Outputs: "A2, cache".
            A2, cache = forward_propagation(X, parameters)
    
            # Cost function. Inputs: "A2, Y, parameters". Outputs: "cost".
            cost = compute_cost(A2, Y, parameters)
    
            # Backpropagation. Inputs: "parameters, cache, X, Y". Outputs: "grads".
            grads = backward_propagation(parameters, cache, X , Y)
    
            # Gradient descent parameter update. Inputs: "parameters, grads". Outputs: "parameters".
            parameters = update_parameters(parameters, grads)
    
            ### END CODE HERE ###
    
            # Print the cost every 1000 iterations
            if print_cost and i % 1000 == 0:
                print ("Cost after iteration %i: %f" %(i, cost))
    
        return parameters

    测试代码：

    def nn_model_test_case():
        np.random.seed(1)
        X_assess = np.random.randn(2, 3)
        Y_assess = np.random.randn(1, 3)
        return X_assess, Y_assess
    
    X_assess, Y_assess = nn_model_test_case()
    
    parameters = nn_model(X_assess, Y_assess, 4, num_iterations=10000, print_cost=False)
    print("W1 = " + str(parameters["W1"]))
    print("b1 = " + str(parameters["b1"]))
    print("W2 = " + str(parameters["W2"]))
    print("b2 = " + str(parameters["b2"]))

    测试代码运行结果：

    W1 = [[-4.18494502  5.33220306]
     [-7.52989352  1.24306198]
     [-4.19295477  5.32631754]
     [ 7.52983748 -1.24309404]]
    b1 = [[ 2.32926814]
     [ 3.79459053]
     [ 2.3300254 ]
     [-3.79468789]]
    W2 = [[-6033.83672183 -6008.12981297 -6033.10095335  6008.0663689 ]]
    b2 = [[-52.666077]]
    c:\users\jason\appdata\local\programs\python\python35\lib\site-packages\ipykernel_launcher.py:26: RuntimeWarning: overflow encountered in exp

    4-5 预测

    至此，我们已经训练获得了最优的参数，那么我们可以基于该模型对新数据进行预测：
    

    $$y_{prediction} = \mathbb 1 \text{{activation > 0.5}} = \begin{cases} 1 & \text{if}\ activation > 0.5 \\ 0 & \text{otherwise} \end{cases}$$

    As an example, if you would like to set the entries of a matrix X to 0 and 1 based on a threshold you would do: X_new = (X > threshold)

    代码：

    # GRADED FUNCTION: predict
    
    def predict(parameters, X):
        """
        Using the learned parameters, predicts a class for each example in X
    
        Arguments:
        parameters -- python dictionary containing your parameters 
        X -- input data of size (n_x, m)
    
        Returns
        predictions -- vector of predictions of our model (red: 0 / blue: 1)
        """
    
        # Computes probabilities using forward propagation, and classifies to 0/1 using 0.5 as the threshold.
        ### START CODE HERE ### (≈ 2 lines of code)
        A2, cache = forward_propagation(X, parameters)
        predictions = (A2 > 0.5)
        #predictions = np.around(A2)#这种方式也可以
        ### END CODE HERE ###
        print ("predictions:", predictions)
        return predictions

    测试代码：

    def predict_test_case():
        np.random.seed(1)
        X_assess = np.random.randn(2, 3)
        parameters = {'W1': np.array([[-0.00615039,  0.0169021 ],
            [-0.02311792,  0.03137121],
            [-0.0169217 , -0.01752545],
            [ 0.00935436, -0.05018221]]),
         'W2': np.array([[-0.0104319 , -0.04019007,  0.01607211,  0.04440255]]),
         'b1': np.array([[ -8.97523455e-07],
            [  8.15562092e-06],
            [  6.04810633e-07],
            [ -2.54560700e-06]]),
         'b2': np.array([[  9.14954378e-05]])}
        return parameters, X_assess
    
    
    parameters, X_assess = predict_test_case()
    
    predictions = predict(parameters, X_assess)
    print("predictions mean = " + str(np.mean(predictions)))

    测试代码运行结果：

    predictions: [[ True False  True]]
    predictions mean = 0.666666666667

    4-5-1 边界绘制

    对于隐藏层为4的神经网络，我们来绘制下边界：

    # Build a model with a n_h-dimensional hidden layer
    parameters = nn_model(X, Y, n_h = 4, num_iterations = 10000, print_cost=True)
    
    # Plot the decision boundary
    plot_decision_boundary(lambda x: predict(parameters, x.T), X, Y)
    plt.title("Decision Boundary for hidden layer size " + str(4))

    运行结果：

    Cost after iteration 0: 0.693048
    Cost after iteration 1000: 0.288083
    Cost after iteration 2000: 0.254385
    Cost after iteration 3000: 0.233864
    Cost after iteration 4000: 0.226792
    Cost after iteration 5000: 0.222644
    Cost after iteration 6000: 0.219731
    Cost after iteration 7000: 0.217504
    Cost after iteration 8000: 0.219528
    Cost after iteration 9000: 0.218627
    predictions: [[ 1.  1.  1. ...,  0.  0.  0.]]

    waning信息：

    c:\users\jason\appdata\local\programs\python\python35\lib\site-packages\numpy\ma\core.py:6385: MaskedArrayFutureWarning: In the future the default for ma.maximum.reduce will be axis=0, not the current None, to match np.maximum.reduce. Explicitly pass 0 or None to silence this warning.
      return self.reduce(a)
    c:\users\jason\appdata\local\programs\python\python35\lib\site-packages\numpy\ma\core.py:6385: MaskedArrayFutureWarning: In the future the default for ma.minimum.reduce will be axis=0, not the current None, to match np.minimum.reduce. Explicitly pass 0 or None to silence this warning.
      return self.reduce(a)

    输出的边界如下：
    

    4-5-2 准确率

    统计真实矩阵和预测矩阵中相同位置，值相同的个数。

    # Print accuracy
    predictions = predict(parameters, X)
    print ('Accuracy: %d' % float((np.dot(Y,predictions.T) + np.dot(1-Y,1-predictions.T))/float(Y.size)*100) + '%')

    运行结果：

    Accuracy: 90%

    相比于逻辑回归，此处90%的准确率是高出许多的。

    4-6 隐藏层神经元数量的影响

    我们在隐藏层的神经元数量分别取1, 2, 3, 4, 5, 10, 20做如下观察：

    # This may take about 2 minutes to run
    
    plt.figure(figsize=(16, 32))
    hidden_layer_sizes = [1, 2, 3, 4, 5, 10, 20]
    for i, n_h in enumerate(hidden_layer_sizes):
        plt.subplot(5, 2, i+1)
        plt.title('Hidden Layer of size %d' % n_h)
        parameters = nn_model(X, Y, n_h, num_iterations = 5000)
        plot_decision_boundary(lambda x: predict(parameters, x.T), X, Y)
        predictions = predict(parameters, X)
        accuracy = float((np.dot(Y,predictions.T) + np.dot(1-Y,1-predictions.T))/float(Y.size)*100)
        print ("Accuracy for {} hidden units: {} %".format(n_h, accuracy))

    warning信息：

    c:\users\jason\appdata\local\programs\python\python35\lib\site-packages\numpy\ma\core.py:6385: MaskedArrayFutureWarning: In the future the default for ma.maximum.reduce will be axis=0, not the current None, to match np.maximum.reduce. Explicitly pass 0 or None to silence this warning.
      return self.reduce(a)
    c:\users\jason\appdata\local\programs\python\python35\lib\site-packages\numpy\ma\core.py:6385: MaskedArrayFutureWarning: In the future the default for ma.minimum.reduce will be axis=0, not the current None, to match np.minimum.reduce. Explicitly pass 0 or None to silence this warning.
      return self.reduce(a)

    输出结果如下：

    Accuracy for 1 hidden units: 67.5 %
    Accuracy for 2 hidden units: 67.25 %
    Accuracy for 3 hidden units: 90.75 %
    Accuracy for 4 hidden units: 90.5 %
    Accuracy for 5 hidden units: 91.25 %
    Accuracy for 10 hidden units: 90.25 %
    Accuracy for 20 hidden units: 90.5 %

    
    从上图的对比，我们可以看出，隐藏层的神经元数量越多，则对训练数据集的拟合效果越好，直到最后出现过拟合。本文这里隐藏层的神经元数量，最适值是n_h=5，即能够较好地拟合训练数据集，也不会出现过拟合现象。另外，对于n_h过大而产生的过拟合是可以通过正则化来消除的，这点后续再补充介绍。