深层神经网络2__NeuralNetwork

import time
import numpy as np
import h5py
import matplotlib.pyplot as plt
import scipy
from PIL import Image
from scipy import ndimage
from dnn_app_utils_v2 import *

%matplotlib inline
plt.rcParams['figure.figsize'] = (5.0, 4.0) # set default size of plots
plt.rcParams['image.interpolation'] = 'nearest'
plt.rcParams['image.cmap'] = 'gray'

%load_ext autoreload
%autoreload 2

np.random.seed(1)

train_x_orig, train_y, test_x_orig, test_y, classes = load_data()

m_train = train_x_orig.shape[0]
num_px = train_x_orig.shape[1]
m_test = test_x_orig.shape[0]

print ("Number of training examples: " + str(m_train))
print ("Number of testing examples: " + str(m_test))
print ("Each image is of size: (" + str(num_px) + ", " + str(num_px) + ", 3)")
print ("train_x_orig shape: " + str(train_x_orig.shape))
print ("train_y shape: " + str(train_y.shape))
print ("test_x_orig shape: " + str(test_x_orig.shape))
print ("test_y shape: " + str(test_y.shape))

结果：
Number of training examples: 209
Number of testing examples: 50
Each image is of size: (64, 64, 3)
train_x_orig shape: (209, 64, 64, 3)
train_y shape: (1, 209)
test_x_orig shape: (50, 64, 64, 3)
test_y shape: (1, 50)

# Reshape the training and test examples 
train_x_flatten = train_x_orig.reshape(train_x_orig.shape[0], -1).T   # The "-1" makes reshape flatten the remaining dimensions
test_x_flatten = test_x_orig.reshape(test_x_orig.shape[0], -1).T

# Standardize data to have feature values between 0 and 1.
train_x = train_x_flatten/255.
test_x = test_x_flatten/255.

print ("train_x's shape: " + str(train_x.shape))
print ("test_x's shape: " + str(test_x.shape))

结果：
train_x's shape: (12288, 209)
test_x's shape: (12288, 50)

两层神经网络

n_x = 12288
n_h = 7
n_y = 1
layers_dims = (n_x, n_h, n_y)
def two_layer_model(X, Y, layers_dims, learning_rate = 0.0075, num_iterations = 3000, print_cost=False):

    np.random.seed(1)
    grads = {}
    costs = []                             
    m = X.shape[1]                          
    (n_x, n_h, n_y) = layers_dims

    parameters =  initialize_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):

    
        A1, cache1 = linear_activation_forward(X,  W1, b1, 'relu')
        A2, cache2 = linear_activation_forward(A1, W2, b2, 'sigmoid')
        
        cost = - np.sum(np.multiply(Y,np.log(A2))+np.multiply((1-Y),np.log(1-A2)))/m
   
        dA2 = - (np.divide(Y, A2) - np.divide(1 - Y, 1 - A2))
      
        dA1, dW2, db2 = linear_activation_backward(dA2,cache2,'sigmoid')
        dA0, dW1, db1 = linear_activation_backward(dA1,cache1, 'relu')
        
        grads['dW1'] = dW1
        grads['db1'] = db1
        grads['dW2'] = dW2
        grads['db2'] = db2
        
        parameters = update_parameters(parameters, grads, learning_rate)
        
        W1 = parameters["W1"]
        b1 = parameters["b1"]
        W2 = parameters["W2"]
        b2 = parameters["b2"]
        
        if print_cost and i % 100 == 0:
            print("Cost after iteration {}: {}".format(i, np.squeeze(cost)))
        if print_cost and i % 100 == 0:
            costs.append(cost)
       

    plt.plot(np.squeeze(costs))
    plt.ylabel('cost')
    plt.xlabel('iterations (per tens)')
    plt.title("Learning rate =" + str(learning_rate))
    plt.show()
    
    return parameters

parameters = two_layer_model(train_x, train_y, layers_dims = (n_x, n_h, n_y), num_iterations = 2500, print_cost=True)
predictions_train = predict(train_x, train_y, parameters)
predictions_test = predict(test_x, test_y, parameters)

结果：
Cost after iteration 0: 0.6930497356599891
Cost after iteration 100: 0.6464320953428849
Cost after iteration 200: 0.6325140647912677
Cost after iteration 300: 0.6015024920354666
Cost after iteration 400: 0.5601966311605748
Cost after iteration 500: 0.515830477276473
Cost after iteration 600: 0.4754901313943325
Cost after iteration 700: 0.43391631512257495
Cost after iteration 800: 0.4007977536203887
Cost after iteration 900: 0.35807050113237976
Cost after iteration 1000: 0.3394281538366414
Cost after iteration 1100: 0.30527536361962654
Cost after iteration 1200: 0.2749137728213016
Cost after iteration 1300: 0.2468176821061485
Cost after iteration 1400: 0.198507350374661
Cost after iteration 1500: 0.17448318112556663
Cost after iteration 1600: 0.17080762978096894
Cost after iteration 1700: 0.11306524562164715
Cost after iteration 1800: 0.09629426845937145
Cost after iteration 1900: 0.08342617959726861
Cost after iteration 2000: 0.07439078704319078
Cost after iteration 2100: 0.06630748132267933
Cost after iteration 2200: 0.05919329501038171
Cost after iteration 2300: 0.05336140348560554
Cost after iteration 2400: 0.04855478562877018

Accuracy: 0.9999999999999998

Accuracy: 0.72

四层神经网络

layers_dims = [12288, 20, 7, 5, 1] #  5-layer model
def L_layer_model(X, Y, layers_dims, learning_rate = 0.0075, num_iterations = 3000, print_cost=False):
    np.random.seed(1)
    costs = []                         
    
    parameters = initialize_parameters_deep(layers_dims)

    for i in range(0, num_iterations):
        AL, caches = L_model_forward(X, parameters)
        cost = -np.sum(np.multiply(Y,np.log(AL))+np.multiply(1-Y,np.log(1-AL)))/AL.shape[1]
        grads = L_model_backward(AL, Y, caches)
        parameters = update_parameters(parameters, grads, learning_rate)
        if print_cost and i % 100 == 0:
            print ("Cost after iteration %i: %f" %(i, cost))
        if print_cost and i % 100 == 0:
            costs.append(cost)
            
    plt.plot(np.squeeze(costs))
    plt.ylabel('cost')
    plt.xlabel('iterations (per tens)')
    plt.title("Learning rate =" + str(learning_rate))
    plt.show()
    
    return parameters

parameters = L_layer_model(train_x, train_y, layers_dims, num_iterations = 2500, print_cost = True)
pred_train = predict(train_x, train_y, parameters)
pred_test = predict(test_x, test_y, parameters)

结果：
Cost after iteration 0: 0.771749
Cost after iteration 100: 0.672053
Cost after iteration 200: 0.648263
Cost after iteration 300: 0.611507
Cost after iteration 400: 0.567047
Cost after iteration 500: 0.540138
Cost after iteration 600: 0.527930
Cost after iteration 700: 0.465477
Cost after iteration 800: 0.369126
Cost after iteration 900: 0.391747
Cost after iteration 1000: 0.315187
Cost after iteration 1100: 0.272700
Cost after iteration 1200: 0.237419
Cost after iteration 1300: 0.199601
Cost after iteration 1400: 0.189263
Cost after iteration 1500: 0.161189
Cost after iteration 1600: 0.148214
Cost after iteration 1700: 0.137775
Cost after iteration 1800: 0.129740
Cost after iteration 1900: 0.121225
Cost after iteration 2000: 0.113821
Cost after iteration 2100: 0.107839
Cost after iteration 2200: 0.102855
Cost after iteration 2300: 0.100897
Cost after iteration 2400: 0.092878

Accuracy: 0.9856459330143539

Accuracy: 0.8

---

分错图片特征查看（机器翻译）：
猫的身体处于异常的位置
猫出现在类似颜色的背景下
猫的颜色和种类异常
相机角度
图片的亮度
比例变化（猫的图像很大或很小）

print_mislabeled_images(classes, test_x, test_y, pred_test)

注意事项：
正向传播过程需要记录每层神经元的Z,w,b，A_prev，
反向传播用dA，Z计算dw,db,dA_prev