【吴恩达L1W4】构建两层和深层神经网络

主要步骤

1. 初始化两层和深层的神经网络参数。

2. 实现正向传播模块（紫色图）。

• 完成模型正向传播步骤的linear部分。
• 提供使用的activation函数（relu / Sigmoid）。
• 将前两个步骤合并为新的[linear->activation]前向函数。
• 堆叠[linear->relu]正向函数L-1次（第1到L-1层），并在末尾添加[linear-> sigmoid]（最后的层），合成了一个新的L_model_forward函数。

     3.计算损失。

     4.实现反向传播模块（红色图）。

• 完成模型反向传播步骤的linear部分。
• 提供的activation函数的梯度（relu_backward / sigmoid_backward）
• 将前两个步骤组合成新的[linear-> sigmoid]反向函数。
• 将[linear->relu]向后堆叠L-1次，并在新的L_model_backward函数中后向添加[inear-> sigmoid] 最后更新参数。

运行结果

        打印cost，画出cost下降曲线。

import numpy as np
import h5py
import matplotlib.pyplot as plt
import pylab
def sigmoid(Z):
    A = 1 / (1 + np.exp(-Z))
    cache = Z
    return A, cache

def relu(Z):
    A = np.maximum(0, Z)
    assert (A.shape == Z.shape)
    cache = Z
    return A, cache

def relu_backward(dA, cache):
    Z = cache
    dZ = np.array(dA, copy=True)  # just converting dz to a correct object.
    # When z <= 0, you should set dz to 0 as well.
    dZ[Z <= 0] = 0
    assert (dZ.shape == Z.shape)
    return dZ

def sigmoid_backward(dA, cache):
    Z = cache
    s = 1 / (1 + np.exp(-Z))
    dZ = dA * s * (1 - s)
    assert (dZ.shape == Z.shape)
    return dZ

np.random.seed(1)

# 初始化参数,2层
def initialize_parameters(n_x, n_h, n_y):
    np.random.seed(1)
    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))
    # 使用断言确保我的数据格式是正确的
    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

# 初始化参数，深层
def initialize_parameters_deep(layer_dims):
    np.random.seed(3)
    parameters = {}
    L = len(layer_dims)  # 网络层数
    # 这里须明确矩阵维度
    for l in range(1, L):
        parameters['W' + str(l)] = np.random.randn(layer_dims[l], layer_dims[l - 1]) / np.sqrt(layer_dims[l - 1])
        parameters['b' + str(l)] = np.zeros((layer_dims[l], 1))
        # 确保我要的数据的格式是正确的
        assert (parameters['W' + str(l)].shape == (layer_dims[l], layer_dims[l - 1]))
        assert (parameters['b' + str(l)].shape == (layer_dims[l], 1))

    return parameters

#前向传播，分三步走
#第一步，实现前向传播，只有linear
def linear_forward(A, W, b):
    Z = np.dot(W, A) + b
    assert (Z.shape == (W.shape[0], A.shape[1]))
    cache = (A, W, b)
    return Z, cache
# 第二步，前向传播+激活函数
def linear_activation_forward(A_prev, W, b, activation):
    if activation == "sigmoid":
        Z, linear_cache = linear_forward(A_prev, W, b)
        A, activation_cache = sigmoid(Z)

    elif activation == "relu":
        Z, linear_cache = linear_forward(A_prev, W, b)
        A, activation_cache = relu(Z)

    assert (A.shape == (W.shape[0], A_prev.shape[1]))
    cache = (linear_cache, activation_cache)
    # 最后cache里面包含A_prev W b Z
    return A, cache

# 第三步，实现整个网络的前向传播
def L_model_forward(X, parameters):
    caches = []
    A = X
    L = len(parameters) // 2  # 神经网络的层数

    # L-1次linear-relu
    for l in range(1, L):
        A_prev = A
        A, cache = linear_activation_forward(A_prev, parameters['W' + str(l)], parameters['b' + str(l)],
                                             activation="relu")
        caches.append(cache)  # A_prev W b Z
    # L层的linear+sigmoid
    AL, cache = linear_activation_forward(A, parameters['W' + str(L)], parameters['b' + str(L)], activation="sigmoid")
    caches.append(cache)
    assert (AL.shape == (1, X.shape[1]))
    # 最后caches里面包含了每一层的A_prev W b Z
    return AL, caches

# 计算损失
def compute_cost(AL, Y):
    # 获得样本数量
    m = Y.shape[1]
    cost = -1 / m * np.sum(Y * np.log(AL) + (1 - Y) * np.log(1 - AL), axis=1, keepdims=True)
    cost = np.squeeze(cost)
    return cost

# 向后传播,分三步走
# 线性部分向后传播
def linear_backward(dZ, cache):
    #输入dZ，输出dW，db，dA_prev
    # z=np.dot(W,A)+b
    A_prev, W, b = cache
    # 样本数量
    m = A_prev.shape[1]
    dW = 1 / m * np.dot(dZ, A_prev.T)
    db = 1 / m * np.sum(dZ, axis=1, keepdims=True)
    dA_prev = np.dot(W.T, dZ)
    assert (dA_prev.shape == A_prev.shape)
    assert (dW.shape == W.shape)
    assert (db.shape == b.shape)
    return dA_prev, dW, db

# 线性部分+激活函数的向后传播
def linear_activation_backward(dA, cache, activation):
    linear_cache, activation_cache = cache
    # A_prev W  b    Z
    if activation == "relu":
        dZ = relu_backward(dA, activation_cache)
        dA_prev, dW, db = linear_backward(dZ, linear_cache)
    elif activation == "sigmoid":
        dZ = sigmoid_backward(dA, activation_cache)
        dA_prev, dW, db = linear_backward(dZ, linear_cache)
    return dA_prev, dW, db

# 整个网络向后传播
def L_model_backward(AL, Y, caches):
    grads = {}
    # 层数
    L = len(caches)
    # 样本数量
    m = AL.shape[1]
    # Y大小是 (1，m)
    Y = Y.reshape(AL.shape)
    # 初始化反向传播
    dAL = - (np.divide(Y, AL) - np.divide(1 - Y, 1 - AL))
    # L层反向传播
    current_cache = caches[L - 1]
    grads["dA" + str(L)], grads["dW" + str(L)], grads["db" + str(L)] = linear_activation_backward(dAL, current_cache,
                                                                                                   activation="sigmoid")
    # L-1层反向传播
    for l in reversed(range(L - 1)):
        current_cache = caches[l]
        dA_prev_temp, dW_temp, db_temp = linear_activation_backward(grads["dA" + str(l + 2)], current_cache,
                                                                    activation="relu")
        grads["dA" + str(l + 1)] = dA_prev_temp
        grads["dW" + str(l + 1)] = dW_temp
        grads["db" + str(l + 1)] = db_temp
    return grads

def update_parameters(parameters, grads, learning_rate):
    # 神经网络的层数
    L = len(parameters)// 2
    # 更新每个参数，使用 for 循环
    for l in range(L):
        parameters["W" + str(l + 1)] = parameters["W" + str(l + 1)] - learning_rate * grads["dW" + str(l + 1)]
        parameters["b" + str(l + 1)] = parameters["b" + str(l + 1)] - learning_rate * grads["db" + str(l + 1)]
    return parameters


# 搭建两层神经网路
def two_layer_model(X, Y, layers_dims, learning_rate=0.0075, num_iterations=3000, print_cost=False, isPlot=True):
    np.random.seed(1)
    grads = {}
    costs = []
    (n_x, n_h, n_y) = layers_dims
    # 初始化参数
    parameters = initialize_parameters(n_x, n_h, n_y)
    W1 = parameters["W1"]
    b1 = parameters["b1"]
    W2 = parameters["W2"]
    b2 = parameters["b2"]
    # 开始进行迭代
    for i in range(0, num_iterations):
        # 前向传播
        A1, cache1 = linear_activation_forward(X, W1, b1, "relu")
        A2, cache2 = linear_activation_forward(A1, W2, b2, "sigmoid")
        # 计算成本
        cost = compute_cost(A2, Y)
        # 后向传播
        ## 初始化后向传播
        dA2 = - (np.divide(Y, A2) - np.divide(1 - Y, 1 - A2))
        ## 向后传播，输入：“dA2，cache2，cache1”。 输出：“dA1，dW2，db2;还有dA0（未使用），dW1，db1”。
        dA1, dW2, db2 = linear_activation_backward(dA2, cache2, "sigmoid")
        dA0, dW1, db1 = linear_activation_backward(dA1, cache1, "relu")

        ## 向后传播完成后的数据保存到grads
        grads["dW1"] = dW1
        grads["db1"] = db1
        grads["dW2"] = dW2
        grads["db2"] = db2

        # 更新参数
        parameters = update_parameters(parameters, grads, learning_rate)
        W1 = parameters["W1"]
        b1 = parameters["b1"]
        W2 = parameters["W2"]
        b2 = parameters["b2"]

        # 打印成本值，如果print_cost=False则忽略
        if i % 100 == 0:
            # 记录成本
            costs.append(cost)
            # 是否打印成本值
            if print_cost:
                print("第", i, "次迭代，成本值为：", np.squeeze(cost))
    # 迭代完成，根据条件绘制图
    if isPlot:
        plt.plot(np.squeeze(costs))
        plt.ylabel('cost')
        plt.xlabel('iterations (per tens)')
        plt.title("Learning rate =" + str(learning_rate))
        plt.show()
    # 返回 parameters
    return parameters

# 搭建L层深度神经网络
def L_layer_model(X, Y, layers_dims, learning_rate=0.0075, num_iterations=3000, print_cost=False, isPlot=True):
    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 = compute_cost(AL, Y)
        grads = L_model_backward(AL, Y, caches)
        parameters = update_parameters(parameters, grads, learning_rate)
        # 打印成本值，如果 print_cost=False 则忽略
        if i % 100 == 0:
            # 记录成本
            costs.append(cost)
            # 是否打印成本值
            if print_cost:
                print("第", i, "次迭代，成本值为：", np.squeeze(cost))
    # 迭代完成，根据条件绘制图
    if isPlot:
        plt.plot(np.squeeze(costs))
        plt.ylabel('cost')
        plt.xlabel('iterations (per tens)')
        plt.title("Learning rate =" + str(learning_rate))
        plt.show()
    return parameters


# 预测
def predict(X, y, parameters):

    m = X.shape[1]
    n = len(parameters) // 2  # 神经网络的层数
    p = np.zeros((1, m))
    # 根据参数前向传播
    probas, caches = L_model_forward(X, parameters)
    for i in range(0, probas.shape[1]):
        if probas[0, i] > 0.5:
            p[0, i] = 1
        else:
            p[0, i] = 0
    print("准确度为: " + str(float(np.sum((p == y)) / m)))
    return p


# 加载数据集
def load_dataset():
    # 本地路径
    train_dataset = h5py.File('C:/Users/Dell/Desktop/datasets/train_catvnoncat.h5', "r")
    train_set_x_orig = np.array(train_dataset["train_set_x"][:])  # 209张 64*64*3的图像
    train_set_y_orig = np.array(train_dataset["train_set_y"][:])  # 0/1

    test_dataset = h5py.File('C:/Users/Dell/Desktop/datasets/test_catvnoncat.h5', "r")
    test_set_x_orig = np.array(test_dataset["test_set_x"][:])  # 50张   64*64*3的图像
    test_set_y_orig = np.array(test_dataset["test_set_y"][:])  # 0/1

    classes = np.array(test_dataset["list_classes"][:])  # non-cat / cat

    train_set_y_orig = train_set_y_orig.reshape((1, train_set_y_orig.shape[0]))
    test_set_y_orig = test_set_y_orig.reshape((1, test_set_y_orig.shape[0]))

    return train_set_x_orig, train_set_y_orig, test_set_x_orig, test_set_y_orig, classes

train_set_x_orig , train_set_y , test_set_x_orig , test_set_y , classes=load_dataset()
train_x_flatten = train_set_x_orig.reshape(train_set_x_orig.shape[0], -1).T
test_x_flatten = test_set_x_orig.reshape(test_set_x_orig.shape[0], -1).T
train_x = train_x_flatten / 255
train_y = train_set_y
test_x = test_x_flatten / 255
test_y = test_set_y

'''
# 正式训练2层神经网络并预测
n_x = 12288
n_h = 7
n_y = 1
layers_dims = (n_x,n_h,n_y)
parameters = two_layer_model(train_x, train_set_y, layers_dims = (n_x, n_h, n_y), num_iterations = 2500, print_cost=True,isPlot=True)
predictions_train = predict(train_x, train_y, parameters) # 训练集
predictions_test = predict(test_x, test_y, parameters)    # 测试集
'''
# 正式训练L层深度神经网络并预测
layers_dims = [12288, 20, 7, 5, 1] #  5-layer model
parameters = L_layer_model(train_x, train_y, layers_dims, num_iterations = 2500, print_cost = True,isPlot=True)
pred_train = predict(train_x, train_y, parameters) #训练集
pred_test = predict(test_x, test_y, parameters) #测试集

# 打印预测错误的图像，分析原因
def print_mislabeled_images(classes, X, y, p):
    a = p + y   # (1,m)
    # 返回a==1的元素索引
    mislabeled_indices = np.asarray(np.where(a == 1))
    # print(mislabeled_indices)
    # [[ 0  0  0  0  0  0  0  0  0  0  0]
    #  [ 5  6 13 19 28 29 34 44 45 46 48]]
    # 第一个一维数组返回的是a==1的行索引
    # 第二个一维数组返回的是a==1的列索引
    plt.rcParams['figure.figsize'] = (40.0, 40.0)  # 设置 plot 的默认大小
    # 预测错图片的总数
    num_images = len(mislabeled_indices[0])  # 11
    # 显示预测错误的图片
    for i in range(num_images):
        index = mislabeled_indices[1][i]
        plt.subplot(2, num_images, i + 1)
        plt.imshow(X[:, index].reshape(64, 64, 3), interpolation='nearest')
        plt.axis('off')
        plt.title(
            "Prediction: " + classes[int(p[0, index])].decode("utf-8") + " \n Class: " + classes[y[0, index]].decode(
                "utf-8"))
    pylab.show()
print_mislabeled_images(classes, test_x, test_y, pred_test)