浅层神经网络__NeuralNetwork

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) 

#加载数据集
X, Y = load_planar_dataset() 
#数据可视化
plt.scatter(X[0, :], X[1, :], c=Y[0, :], s=40, cmap=plt.cm.Spectral);
#查看数据集
shape_X = X.shape
shape_Y = Y.shape
m = X.shape[1]

clf = sklearn.linear_model.LogisticRegressionCV();
clf.fit(X.T, Y[0, :].T);
plot_decision_boundary(lambda x: clf.predict(x), X, Y[0, :])
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)")
       
结果：Accuracy of logistic regression: 47 % (percentage of correctly labelled datapoints)

---

输入层，中间层，输出层神经元个数

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

初始化化模型参数 W1,b1,W2,b2,采用parameters(字典)保存

def initialize_parameters(n_x, n_h, n_y):
    
    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))

    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

正向传播过程，获取预测值A2和保存有Z1、Z2、A1、A2的cache（字典，梯度更新需要用）

def forward_propagation(X, parameters):
    W1 = parameters['W1']
    b1 = parameters['b1']
    W2 = parameters['W2']
    b2 = parameters['b2']
    
    Z1 = W1.dot(X) + b1
    A1 = np.tanh(Z1)
    Z2 = W2.dot(A1) + b2
    A2 = sigmoid(Z2)

    assert(A2.shape == (1, X.shape[1]))
    
    cache = {"Z1": Z1,
             "A1": A1,
             "Z2": Z2,
             "A2": A2}
    
    return A2, cache

计算代价函数,采用以下公式：
（np.sum(-Y*np.log(A2) - (1-Y)*np.log(1-A2))/m
最终参数一样，cost就是不对）

def compute_cost(A2, Y, parameters):
    m = Y.shape[1]
    cost  = np.sum(-np.multiply(np.log(A2),Y)-np.multiply(np.log(1-A2),1-Y))/m
#     cost = np.sum(-Y*np.log(A2) - (1-Y)*np.log(1-A2))/m
    cost = np.squeeze(cost)     
    assert(isinstance(cost, float))
    
    return cost

反向传播，需要用到parameters（字典）中的W1,W2,b1,b2,和cache中的（Z1,A1,Z2,A2）

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

    W1 = parameters['W1']
    W2 = parameters['W2']    
    A1 = cache['A1']
    A2 = cache['A2']

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

梯度更新返回，更新过的parameters(字典)，保存更新后的W1,W2,b1,b2

def update_parameters(parameters, grads, learning_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 - learning_rate*dW1
    b1 = b1 - learning_rate*db1
    W2 = W2 - learning_rate*dW2
    b2 = b2 - learning_rate*db2

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

建立一个nn_model

def nn_model(X, Y, n_h, num_iterations = 10000, print_cost=False):
    np.random.seed(3)
    n_x = layer_sizes(X, Y)[0]
    n_y = layer_sizes(X, Y)[2]

    parameters = initialize_parameters(n_x, n_h, n_y)
    W1 = parameters['W1']
    b1 = parameters['b1']
    W2 = parameters['W2']
    b2 = parameters['b2']
    
    #参数初始化后便不断计算cost，W1,W2,b1,b2导数，更新W1,W2,b1,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,learning_rate=1.2)
        if print_cost and i % 1000 == 0:
            print ("Cost after iteration %i: %f" %(i, cost))
    return parameters

预测，即用前向传播在最新parameters的A2值

def predict(parameters, X):
    A2, cache = forward_propagation(X, parameters)
    predictions = np.where(A2>0.5,1,0)
    return predictions

查看预测结果

parameters = nn_model(X, Y, n_h = 4, num_iterations = 10000, print_cost=True)
plot_decision_boundary(lambda x: predict(parameters, x.T), X, Y[0, :])
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) + '%')

结果：
Cost after iteration 0: 0.693162
Cost after iteration 1000: 0.258625
Cost after iteration 2000: 0.239334
Cost after iteration 3000: 0.230802
Cost after iteration 4000: 0.225528
Cost after iteration 5000: 0.221845
Cost after iteration 6000: 0.219094
Cost after iteration 7000: 0.220660
Cost after iteration 8000: 0.219408
Cost after iteration 9000: 0.218485
Accuracy: 90%

修改中间层神经元个数，查看准确率

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[0, :])
    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))
    
结果：
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: 91.25 %
Accuracy for 20 hidden units: 91.0 %