神经网络与深度学习编程练习(coursera 吴恩达 )（2）

神经网络与深度学习(吴恩达)第三周编程

原coursera课程主页
代码如下：

import numpy as np
import matplotlib.pyplot as plt
from testCases_v2 import *
import sklearn
import sklearn.datasets
import sklearn.linear_model
from planar_utils import plot_decision_boundary, sigmoid, load_planar_dataset,load_extra_datasets

np.random.seed(1)

noisy_circles, noisy_moons, blobs, gaussian_quantiles, no_structure = load_extra_datasets()

datasets = {"noisy_circles": noisy_circles,
            "noisy_moons": noisy_moons,
            "blobs": blobs,
            "gaussian_quantiles": gaussian_quantiles,
            'no_structure':no_structure }
dataset='blobs'

X,Y=datasets[dataset]
X, Y = X.T, Y.reshape(1, Y.shape[0])
#X, Y = load_planar_dataset()
if dataset == "blobs":
    Y = Y%2
plt.scatter(X[0, :], X[1, :], c=Y, s=40, cmap=plt.cm.Spectral)



shape_X=X.shape 
shape_Y=Y.shape
m=X.shape[1]
'''
clf=sklearn.linear_model.LogisticRegressionCV()
clf.fit(X.T,Y.T)

plot_decision_boundary(lambda x:clf.predict(x),X,Y)
plt.title('Logistic Regression')

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)")
'''
def lay_sizes(X,Y):
    n_x=X.shape[0]
    n_h=4
    n_y=Y.shape[0]
    return (n_x,n_h,n_y)


def initial_parameters(n_x,n_h,n_y):
    np.random.seed(2)
    W1=np.random.randn(n_h,n_x)*0.01
    b1=np.zeros((n_h,1))
    W2=np.random.randn(n_y,n_h)
    b2=np.zeros((n_y,1))
    parameters={'W1':W1,'b1':b1,'W2':W2,'b2':b2}
    return parameters

def forward_propagation(X,parameters):
    W1=parameters['W1']
    b1=parameters['b1']
    W2=parameters['W2']
    b2=parameters['b2']

    Z1=np.dot(W1,X)+b1
    A1=np.tanh(Z1)
    Z2=np.dot(W2,A1)+b2
    A2=sigmoid(Z2)

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

    return A2,cache

def compute_cost(A2,Y,parameters):
    m=Y.shape[1]
    logprobs=np.multiply(np.log(A2),Y)+np.multiply(np.log(1-A2),(1-Y))
    cost=-np.sum(logprobs)/m
    cost=np.squeeze(cost)
    return cost

def backward_propagation(parameters,cache,X,Y):
    m=X.shape[1]
    W1=parameters['W1']
    W2=parameters['W2']

    A2,cache=forward_propagation(X,parameters)
    A1=cache['A1']

    dZ2=A2-Y
    dW2=np.dot(dZ2,A1.T)/m
    db2=1/m*np.sum(dZ2,axis=1,keepdims=True)
    dZ1=np.multiply(np.dot(W2.T,dZ2),(1-np.power(A1,2)))
    dW1=1/m*np.dot(dZ1,X.T)
    db1=1/m*np.sum(dZ1,axis=1,keepdims=True)

    grads={
        'dW1':dW1,
        'db1':db1,
        'dW2':dW2,
        'db2':db2
    }
    return grads

def update_parameters(parameters,grads,learn_rate=1.2):
    W1=parameters['W1']
    b1=parameters['b1']
    W2=parameters['W2']
    b2=parameters['b2']

    dW1=grads['dW1']
    db1=grads['db1']
    dW2=grads['dW2']
    db2=grads['db2']

    W1=W1-learn_rate*dW1
    W2=W2-learn_rate*dW2
    b1=b1-learn_rate*db1
    b2=b2-learn_rate*db2

    parameters={
        'W1':W1,
        'W2':W2,
        'b1':b1,
        'b2':b2
    }
    return parameters

def nn_model(X,Y,n_h,num_iterations=10000,print_cost=False):
    np.random.seed(3)
    n_x,tmp,n_y=lay_sizes(X,Y)

    parameters=initial_parameters(n_x,n_h,n_y)
    W1=parameters['W1']
    b1=parameters['b1']
    W2=parameters['W2']
    b2=parameters['b2']

    for i in range(0,num_iterations):
        A2,cache=forward_propagation(X,parameters)
        cost=compute_cost(A2,Y,parameters)
        grads=backward_propagation(parameters,cache,X,Y)
        parameters=update_parameters(parameters,grads,learn_rate=0.7)
        if print_cost and i%1000==0:
            print ("Cost after iteration %i: %f" %(i, cost))
    return parameters

def predict(parameters,X):
    A2,cache=forward_propagation(X,parameters)
    predictions=np.around(A2)
    return predictions
'''
parameters = nn_model(X, Y, n_h = 10, num_iterations = 10000, print_cost=True)
print(parameters)

plot_decision_boundary(lambda x: predict(parameters, x.T), X, Y)
plt.title("Decision Boundary for hidden layer size " + str(4))

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

plt.figure(figsize=(32, 32))
hidden_layer_sizes = [1, 10, 20,30]
for i, n_h in enumerate(hidden_layer_sizes):
    plt.subplot(2, 2, i+1)
    plt.title('Hidden Layer of size %d' % n_h)
    parameters = nn_model(X, Y, n_h, num_iterations = 10000)
    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))
plt.show()

---

测试结果：
原始数据

训练结果：

训练/测试数据集下载链接
注：我找到的testCases_v2发现与coursera上的测试数据并不一样，不过不影响结果。
程序中可设定hidden layer的个数不要设置的过大，可能把电脑跑死，我试过50可以100就不行了，而且训练效果会下降，过拟合了。