Course 2 - 改善深层神经网络 - 第一周作业(1&2&3) - 1.1初始化

1.编程实现，神经网络传播中的三种初始化参数的方法

2.编程实现神经网络中的L2正则化，dropout正则化，

3.编程实现梯度检验

 

任务1：三种初始化参数的方式

1.1初始化的工具类：实现函数定义，前向和后向传播以及决策边界，预测函数等

# -*- coding: utf-8 -*-

import numpy as np
import matplotlib.pyplot as plt
import sklearn
import sklearn.datasets


def sigmoid(x):
    """
    Compute the sigmoid of x
 
    Arguments:
    x -- A scalar or numpy array of any size.
 
    Return:
    s -- sigmoid(x)
    """
    s = 1 / (1 + np.exp(-x))
    return s


def relu(x):
    """
    Compute the relu of x
 
    Arguments:
    x -- A scalar or numpy array of any size.
 
    Return:
    s -- relu(x)
    """
    s = np.maximum(0, x)

    return s


def compute_loss(a3, Y):
    """
    Implement the loss function
    
    Arguments:
    a3 -- post-activation, output of forward propagation
    Y -- "true" labels vector, same shape as a3
    
    Returns:
    loss - value of the loss function
    """

    m = Y.shape[1]
    logprobs = np.multiply(-np.log(a3), Y) + np.multiply(-np.log(1 - a3), 1 - Y)
    loss = 1. / m * np.nansum(logprobs)

    return loss


def forward_propagation(X, parameters):
    """
    Implements the forward propagation (and computes the loss) presented in Figure 2.
    
    Arguments:
    X -- input dataset, of shape (input size, number of examples)
    Y -- true "label" vector (containing 0 if cat, 1 if non-cat)
    parameters -- python dictionary containing your parameters "W1", "b1", "W2", "b2", "W3", "b3":
                    W1 -- weight matrix of shape ()
                    b1 -- bias vector of shape ()
                    W2 -- weight matrix of shape ()
                    b2 -- bias vector of shape ()
                    W3 -- weight matrix of shape ()
                    b3 -- bias vector of shape ()
    
    Returns:
    loss -- the loss function (vanilla logistic loss)
    """

    # retrieve parameters
    W1 = parameters["W1"]
    b1 = parameters["b1"]
    W2 = parameters["W2"]
    b2 = parameters["b2"]
    W3 = parameters["W3"]
    b3 = parameters["b3"]

    # LINEAR -> RELU -> LINEAR -> RELU -> LINEAR -> SIGMOID
    z1 = np.dot(W1, X) + b1
    a1 = relu(z1)
    z2 = np.dot(W2, a1) + b2
    a2 = relu(z2)
    z3 = np.dot(W3, a2) + b3
    a3 = sigmoid(z3)

    cache = (z1, a1, W1, b1, z2, a2, W2, b2, z3, a3, W3, b3)

    return a3, cache


def backward_propagation(X, Y, cache):
    """
    Implement the backward propagation presented in figure 2.
    
    Arguments:
    X -- input dataset, of shape (input size, number of examples)
    Y -- true "label" vector (containing 0 if cat, 1 if non-cat)
    cache -- cache output from forward_propagation()
    
    Returns:
    gradients -- A dictionary with the gradients with respect to each parameter, activation and pre-activation variables
    """
    m = X.shape[1]
    (z1, a1, W1, b1, z2, a2, W2, b2, z3, a3, W3, b3) = cache

    dz3 = 1. / m * (a3 - Y)
    dW3 = np.dot(dz3, a2.T)
    db3 = np.sum(dz3, axis=1, keepdims=True)

    da2 = np.dot(W3.T, dz3)
    dz2 = np.multiply(da2, np.int64(a2 > 0))
    dW2 = np.dot(dz2, a1.T)
    db2 = np.sum(dz2, axis=1, keepdims=True)

    da1 = np.dot(W2.T, dz2)
    dz1 = np.multiply(da1, np.int64(a1 > 0))
    dW1 = np.dot(dz1, X.T)
    db1 = np.sum(dz1, axis=1, keepdims=True)

    gradients = {"dz3": dz3, "dW3": dW3, "db3": db3,
                 "da2": da2, "dz2": dz2, "dW2": dW2, "db2": db2,
                 "da1": da1, "dz1": dz1, "dW1": dW1, "db1": db1}

    return gradients


def update_parameters(parameters, grads, learning_rate):
    """
    Update parameters using gradient descent
    
    Arguments:
    parameters -- python dictionary containing your parameters 
    grads -- python dictionary containing your gradients, output of n_model_backward
    
    Returns:
    parameters -- python dictionary containing your updated parameters 
                  parameters['W' + str(i)] = ... 
                  parameters['b' + str(i)] = ...
    """

    L = len(parameters) // 2  # number of layers in the neural networks

    # Update rule for each parameter
    for k in range(L):
        parameters["W" + str(k + 1)] = parameters["W" + str(k + 1)] - learning_rate * grads["dW" + str(k + 1)]
        parameters["b" + str(k + 1)] = parameters["b" + str(k + 1)] - learning_rate * grads["db" + str(k + 1)]

    return parameters


def predict(X, y, parameters):
    """
    This function is used to predict the results of a  n-layer neural network.
    
    Arguments:
    X -- data set of examples you would like to label
    parameters -- parameters of the trained model
    
    Returns:
    p -- predictions for the given dataset X
    """

    m = X.shape[1]
    p = np.zeros((1, m), dtype=np.int)

    # Forward propagation
    a3, caches = forward_propagation(X, parameters)

    # convert probas to 0/1 predictions
    for i in range(0, a3.shape[1]):
        if a3[0, i] > 0.5:
            p[0, i] = 1
        else:
            p[0, i] = 0

    # print results
    print("Accuracy: " + str(np.mean((p[0, :] == y[0, :]))))

    return p


def load_dataset(is_plot=True):
    np.random.seed(1)
    train_X, train_Y = sklearn.datasets.make_circles(n_samples=300, noise=.05)
    np.random.seed(2)
    test_X, test_Y = sklearn.datasets.make_circles(n_samples=100, noise=.05)
    # Visualize the data
    if is_plot:
        plt.scatter(train_X[:, 0], train_X[:, 1], c=train_Y, s=40, cmap=plt.cm.Spectral)
        plt.show()
    train_X = train_X.T
    train_Y = train_Y.reshape((1, train_Y.shape[0]))
    test_X = test_X.T
    test_Y = test_Y.reshape((1, test_Y.shape[0]))
    return train_X, train_Y, test_X, test_Y


def plot_decision_boundary(model, X, y):
    # Set min and max values and give it some padding
    x_min, x_max = X[0, :].min() - 1, X[0, :].max() + 1
    y_min, y_max = X[1, :].min() - 1, X[1, :].max() + 1
    h = 0.01
    # Generate a grid of points with distance h between them
    # 415行 422列
    xx, yy = np.meshgrid(np.arange(x_min, x_max, h), np.arange(y_min, y_max, h))
    # Predict the function value for the whole grid
    # (175120,)行，1列
    x1=xx.ravel()
    y1=yy.ravel()
    # 175120行，2列,创建数据点，每一行代表一个数据点的坐标，列代表数据点的个数
    xy1=np.c_[x1, y1]
    # 415行 422列
    Z = model(xy1)
    Z = Z.reshape(xx.shape)
    # Plot the contour and training examples
    plt.contourf(xx, yy, Z, cmap=plt.cm.Spectral)
    plt.ylabel('x2')
    plt.xlabel('x1')
    y = np.squeeze(y)
    plt.scatter(X[0, :], X[1, :], c=y, cmap=plt.cm.Spectral)
    plt.show()


def predict_dec(parameters, X):
    """
    Used for plotting decision boundary.
    
    Arguments:
    parameters -- python dictionary containing your parameters 
    X -- input data of size (m, K)
    
    Returns
    predictions -- vector of predictions of our model (red: 0 / blue: 1)
    """

    # Predict using forward propagation and a classification threshold of 0.5
    a3, cache = forward_propagation(X, parameters)
    predictions = (a3 > 0.5)
    return predictions

1.2实现初始化的testCase，实现model函数的定义，以及实现三种初始化的方式

#!/usr/bin/env python
# _*_ coding:utf-8 _*_

import numpy as np
import matplotlib.pyplot as plt
import sklearn
import sklearn.datasets

import init_utils  # 第一部分初始化
import reg_utils  # 第二部分正则化
import gc_utils  # 第三部分梯度校验

plt.rcParams['figure.figsize'] = (7.0, 4.0)  # set default size of plots
plt.rcParams['image.interpolation'] = 'nearest'
plt.rcParams['image.cmap'] = 'gray'

# 1.读取并绘制数据
train_X, train_Y, test_X, test_Y = init_utils.load_dataset(True)


# 2.以3中方式初始化参数w
# 2.1全部初始化为0；2.2随机初始化；2.3以he方式初始化
def model(X, Y, learning_rate=0.01, num_iterations=15000, print_cost=True, initialization="he", is_polt=True):
    grads = {}
    costs = []
    m = X.shape[1]
    layers_dims = [X.shape[0], 10, 5, 1]

    # 选择初始化的类型
    if initialization == "zeros":
        parameters = initialize_parameters_zeros(layers_dims)
    elif initialization == "random":
        parameters = initialize_parameters_random(layers_dims)
    elif initialization == "he":
        parameters = initialize_parameters_he(layers_dims)
    else:
        print("错误的初始化参数！程序退出")
        exit

    # 开始学习
    for i in range(0, num_iterations):
        # 前向计算
        a3, cache = init_utils.forward_propagation(X, parameters)
        # 计算损失函数
        cost = init_utils.compute_loss(a3, Y)
        # 反向传播
        grads = init_utils.backward_propagation(X, Y, cache)
        # 更新参数
        parameters = init_utils.update_parameters(parameters, grads, learning_rate)

        if i % 1000 == 0:
            costs.append(cost)
            if print_cost:
                print("第" + str(i) + "次的成本为：" + str(cost))

    return parameters


# 2.1定义初始化为0的w
def initialize_parameters_zeros(layers_dims):
    parameters = {}
    L = len(layers_dims)
    for i in range(1, L):
        parameters["W" + str(i)] = np.zeros((layers_dims[i], layers_dims[i - 1]))
        parameters["b" + str(i)] = np.zeros((layers_dims[i], 1))
    return parameters


# 测试初始化为0的w
# parameters = model(train_X, train_Y, initialization="zeros", is_polt=True)
# # 根据参数进行预测
#
# accury = init_utils.predict(train_X, train_Y, parameters)
# # print("训练集："+str(accury))
#
# accury = init_utils.predict(test_X, test_Y, parameters)
# # print("测试集："+str(accury))
#
# # 预测和决策边界
#
# plt.title("Model with Zeros initialization")
# axis = plt.gca()
# axis.set_xlim([-1.5, 1.5])
# axis.set_ylim([-1.5, 1.5])
# # 决策边界中划分的所有的数据都是一个颜色，即划分为了同一类
# init_utils.plot_decision_boundary(lambda x: init_utils.predict_dec(parameters, x.T), train_X, train_Y)
#

# 2.2定义随机初始化的w
def initialize_parameters_random(layers_dims):
    np.random.seed(3)
    parameters = {}
    L = len(layers_dims)
    for i in range(1, L):
        parameters["W" + str(i)] = np.random.randn(layers_dims[i], layers_dims[i - 1]) * 10  # 10倍缩放
        parameters["b" + str(i)] = np.zeros((layers_dims[i], 1))
    return parameters


# 测试初始化为随机的w和b的值
# parameters = initialize_parameters_random([3, 2, 1])
# print("W1 = " + str(parameters["W1"]))
# print("b1 = " + str(parameters["b1"]))
# print("W2 = " + str(parameters["W2"]))
# print("b2 = " + str(parameters["b2"]))
# 用初始化的参数进行训练
# parameters=model(train_X,train_Y,initialization='random')
# print('训练集')
# print(init_utils.predict(train_X,train_Y,parameters))
# print("测试集")
# print(init_utils.predict(test_X,test_Y,parameters))
#
# # 绘制图查看分类的结果
# plt.title("Model with large random initialization")
# axes = plt.gca()
# axes.set_xlim([-1.5, 1.5])
# axes.set_ylim([-1.5, 1.5])
# init_utils.plot_decision_boundary(lambda x: init_utils.predict_dec(parameters, x.T), train_X, train_Y)

# 2.3定义抑梯度异常初始化的w,比随机初始化的参数要小一些，接近于1
def initialize_parameters_he(layers_dims):
    np.random.seed(3)
    parameters = {}
    L = len(layers_dims)
    for i in range(1, L):
        parameters["W" + str(i)] = np.random.randn(layers_dims[i], layers_dims[i - 1]) * np.sqrt(2 / layers_dims[i - 1])
        parameters["b" + str(i)] = np.zeros((layers_dims[i], 1))
    return parameters


# 测试初始化为随机的w
# 用初始化的参数进行训练
parameters = model(train_X, train_Y, initialization='he')
print('训练集')
print(init_utils.predict(train_X, train_Y, parameters))
print("测试集")
print(init_utils.predict(test_X, test_Y, parameters))

# 绘制图查看分类的结果
plt.title("Model with large random initialization")
axes = plt.gca()
axes.set_xlim([-1.5, 1.5])
axes.set_ylim([-1.5, 1.5])
init_utils.plot_decision_boundary(lambda x: init_utils.predict_dec(parameters, x.T), train_X, train_Y)