deep_learning_week3_BP神经网络

最新推荐文章于 2020-11-26 13:21:19 发布

PerfectDemoT

最新推荐文章于 2020-11-26 13:21:19 发布

阅读量226

点赞数

分类专栏：机器学习深度学习

本文链接：https://blog.csdn.net/ttt6688/article/details/80232615

版权

机器学习深度学习专栏收录该内容

9 篇文章 0 订阅

订阅专栏

deep_learning_week3_BP神经网络

标签：机器学习深度学习

代码已上传github:
https://github.com/PerfectDemoT/my_deeplearning_homework

deep_learning_week3_BP神经网络
- - 这是吴恩达深度学习里的第二次作业
- 实现BP神经网络
  - 现在开始真正的弄bp神经网络的各层啦

这是吴恩达深度学习里的第二次作业

实现BP神经网络

首先先导入包

#先导入包
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
import matplotlib.pyplot as plt
import pylab

然后我们设置一个随机数种子备用，再导入数据，然后可视化一下（PS：这个不知道什么原因，显示不出来，虽然原来的代码有问题会报错，不过我看了库中函数的运行方式，将Y修改后不会报错了，但是还是显示不出，就很迷，不过对后面的结果没影响）

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

#现在开始导入数据，一个X一个Y
X, Y = load_planar_dataset()

print (np.shape(X))
print (np.shape(Y))
#可知，这个X为一个包含400个具有两个参数样本的矩阵，Y为其标签

#将数据可视化一下，看起来像一朵红花(很奇怪，我这里已开始运行不了，然后改正后不报错了，不过还是显示不出图片)
plt.scatter(X[0, :], X[1, :], c=Y.reshape(X[0,:].shape), s=40, cmap=plt.cm.Spectral);

小红花
3. 现在，我们可以来处理这些数据了，比如，先看看这些矩阵的大小

### START CODE HERE ### (≈ 3 lines of code)
shape_X = X.shape
shape_Y = Y.shape
m = X.shape[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))

然后呢，老师贴心地给了训练好了的单个logistic分类器，我们可以试试

# Train the logistic regression classifier(这里先用写好的分类器训练一下)
clf = sklearn.linear_model.LogisticRegressionCV();
clf.fit(X.T, Y.T);

但是呢，你会发现，这个的分类效果并不好，准确率只有百分之四十九

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

# Print accuracy，现在这里画出这些点的分类边界(好吧这里有点小问题，还是上面那个画图的问题，)
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)")
#可以看出，这个线性分类器效果并不好，就算是训练集，准确率也很低所以这里就要用bp网络了

#这是输出
Accuracy of logistic regression: 47 % (percentage of correctly labelled datapoints)

现在开始真正的弄bp神经网络的各层啦

首先，我们设计一个定义网络结构的函数

#首先定义各层网络的结构
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)

返回的是X输入的参数个数，隐藏层的神经元个数，输出层神经元个数，现在我们来输出网络看一看

#现在输出来看看我们的网络结构
X_assess, Y_assess = layer_sizes_test_case() #这里是将数据导入
(n_x, n_h, n_y) = layer_sizes(X_assess, Y_assess)
print("The size of the input layer is: n_x = " + str(n_x))
print("The size of the hidden layer is: n_h = " + str(n_h))
print("The size of the output layer is: n_y = " + str(n_y))

输出是这样(就不截图了。。。)

The size of the input layer is: n_x = 5
The size of the hidden layer is: n_h = 4
The size of the output layer is: n_y = 2

2 . 现在来初始化（函数里面本身就写了随机的种子，这里为2）

#接下来是初始化函数
# 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)) #记着这里是两个括号
    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

然后现在来看看初始化的样子
代码长这样：

#现在可以看看初始化结构咋样
n_x, n_h, n_y = initialize_parameters_test_case()

parameters = initialize_parameters(n_x, n_h, n_y)
print("W1 = " + str(parameters["W1"]))
print("b1 = " + str(parameters["b1"]))
print("W2 = " + str(parameters["W2"]))
print("b2 = " + str(parameters["b2"]))

输出是

W1 = [[-0.00416758 -0.00056267]
 [-0.02136196  0.01640271]
 [-0.01793436 -0.00841747]
 [ 0.00502881 -0.01245288]]
b1 = [[ 0.]
 [ 0.]
 [ 0.]
 [ 0.]]
W2 = [[-0.01057952 -0.00909008  0.00551454  0.02292208]]
b2 = [[ 0.]]

前期准备算是做的差不多啦，现在开始正向传播啦
先上公式：

大家注意看23到26行，那里是正向传播的精髓之处

#OK，现在开始正向传播啦
# 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 = sigmoid(Z2)
    ### END CODE HERE ###

    assert (A2.shape == (1, X.shape[1]))

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

    return A2, cache

好了，正向传播完毕后，我们来看看结果，结果输出的代码如下：

#现在来看看正向传播的结果
X_assess, parameters = forward_propagation_test_case()

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']))

然后，结果如下：

-0.000499755777742 -0.000496963353232 0.000438187450959 0.500109546852

到了这里，我们可以来看看cost函数了，
先看看公式：
$J = - 1 m \sum i = 0 m (y (i) l o g (a [2] (i)) + (1 - y (i)) l o g (1 - a [2] (i)))$ $J=-\frac1m\sum_{i=0}^m(y^{(i)}log(a^{[2](i)})+(1-y_{(i)})log(1-a^{[2](i)}))$

下面是他的代码（重点关注28,29行）

#现在来算算代价函数J
#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

    # Retrieve W1 and W2 from parameters
    ### START CODE HERE ### (≈ 2 lines of code)
    W1 = parameters['W1']
    W2 = parameters['W2']
    ### END CODE HERE ###

    # 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

我在完成这个的时候通过这个发现了一个前面犯的一个错误，程序一直警告logprobs和cost这两个参数运算的时候不可用，于是我怀疑是不是有小于零的参数存在式子中，最后发现，A2在前面的计算中我已开始用的tanh函数，和A1混啦，其实A2要用sigmoid函数，A1是tanh函数

OK，我们已经完成了cost函数的代码，我么来看看效果
下面是输出代码

#现在来检测下代价函数的计算
A2, Y_assess, parameters = compute_cost_test_case()
print("cost = " + str(compute_cost(A2, Y_assess, parameters)))

输出是这样

cost = 0.692919893776

难点来了，反向传播。(重点是32-37行，这是精髓)

#难点来了，反向传播
# 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 - 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

对于此，我们完成了反向传播，
现在来看看输出代码

#反向传播完毕，我们来看看
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"]))

输出是这样的

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]]

好了，反向传播页做完了，现在开始更新参数矩阵吧！！！

#反向传播完毕后，开始更新参数
# 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 = W1 - learning_rate * dW1
    b1 = b1 - learning_rate * db1
    W2 = W2 - learning_rate * dW2
    b2 = b2 - learning_rate * db2
    ### END CODE HERE ###

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

    return parameters

老规矩，跑一跑(代码如下)

#现在验证一下反向传播算法的参数更新
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"]))

结果长这样：

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]]

ODK，各种功能函数终于可以说是写的差不多啦，现在来整合一个model函数吧

#好了，所有的函数都写完了，现在来整合一下，组成一个分类器模型
# 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)
    import pdb

    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

接着，调用一下这个函数，看看效果，还不是美滋滋(调用代码如下)

#现在我们来跑一跑这个模型
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']))

上面设置的隐藏层是4个，迭代次数是10000
输出以下结果：

W1 = [[-4.18493855  5.33220875]
 [-7.52989335  1.24306212]
 [-4.19297397  5.32630669]
 [ 7.52983568 -1.24309519]]
b1 = [[ 2.32926551]
 [ 3.79459096]
 [ 2.33002105]
 [-3.79469147]]
W2 = [[-6033.83673001 -6008.12981298 -6033.1009627   6008.06639333]]
b2 = [[-52.66607002]]

最后，跑一下预测函数

#现在来写一写预测函数
# 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 = np.array([0 if i <= 0.5 else 1 for i in np.squeeze(A2)])
    ### END CODE HERE ###

    return predictions

看看预测值吧

#来看看预测值
parameters, X_assess = predict_test_case()
predictions = predict(parameters, X_assess)
print("predictions mean = " + str(np.mean(predictions)))

结果长这样：

predictions mean = 0.666666666667

最后，没有对比就没有伤害，，，来看看用这个模型训练的效果之前用单个logistic回归训练的效果的比较吧

#现在用刚才那个用单个逻辑回归只有百分之47的例子来训练
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))
pylab.show()
predictions=predict(parameters,X)
print ('Accuracy: %d' % float((np.dot(Y,predictions.T) + np.dot(1-Y,1-predictions.T))/float(Y.size)*100) + '%')
#可以看到，预测准确率达到了百分之89，

果然美滋滋，准确度达到了百分之九十，秒啊。上图

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: 0.219501
Cost after iteration 9000: 0.218620
Accuracy: 90%