《吴恩达深度学习》第一课第四周任意层的神经网络实现及BUG处理

一、实现

1、吴恩达提供的工具函数

这几个函数这里只是展示一下，这是吴恩达写好的工具类，在实现的部分会导入；具体查看提供的附件

sigmoid

def sigmoid(Z):
    A = 1/(1+np.exp(-Z))
    cache = Z
    return A, cache

sigmoid求导

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

relu

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

relu求导

def relu_backward(dA, cache):
    Z = cache
    dZ = np.array(dA, copy=True)
    dZ[Z <= 0] = 0
    return dZ

2、实现代码

导包和配置

import numpy as np
import h5py
import matplotlib.pyplot as plt
from testCases_v2 import *
from dnn_utils_v2 import sigmoid, sigmoid_backward, relu, relu_backward

%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)

初始化参数

def initialize_parameters_deep(layer_dims):
    """
    Arguments:
    layer_dims -- python array (list) containing the
    dimensions of each layer in our network
    
    Returns:
    parameters -- python dictionary containing your
    parameters "W1", "b1", ..., "WL", "bL":
         Wl -- weight matrix of 
         shape (layer_dims[l], layer_dims[l-1])
         bl -- bias vector of shape (layer_dims[l], 1)
    """
    np.random.seed(3)
    parameters = {}
    L = len(layer_dims)
    for l in range(1, L):
        parameters['W%d' % l] = np.random.randn(layer_dims[l],
        layer_dims[l-1]) * 0.01
        parameters['b%d' % l] = np.zeros((layer_dims[l], 1))
    return parameters  

前向运算

def linear_forward(A, W, b):
    """
    Implement the linear part of a layer's forward propagation.

    Arguments:
    A -- activations from previous layer 
    (or input data): (size of previous layer, number of examples)
    W -- weights matrix: numpy array of shape 
    (size of current layer, size of previous layer)
    b -- bias vector, numpy array of shape 
    (size of the current layer, 1)

    Returns:
    Z -- the input of the activation function,
    also called pre-activation parameter 
    cache -- a python dictionary containing "A", "W" and "b" ;
    stored for computing the backward pass efficiently
    """
    Z = np.dot(W, A) + b
    cache = (A, W, b)
    return Z, cache

def linear_activation_forward(A_prev, W, b, activation):
    """
    Implement the forward propagation for the LINEAR->ACTIVATION layer

    Arguments:
    A_prev -- activations from previous layer
    (or input data): (size of previous layer, number of examples)
    W -- weights matrix: numpy array of shape
    (size of current layer, size of previous layer)
    b -- bias vector, numpy array of shape (size of the current layer, 1)
    activation -- the activation to be used in this layer,
    stored as a text string: "sigmoid" or "relu"

    Returns:
    A -- the output of the activation function,
    also called the post-activation value 
    cache -- a python dictionary containing "linear_cache"
    and "activation_cache";stored 
    for computing the backward pass efficiently
    """
    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)
    cache = (linear_cache, activation_cache)
    return A, cache

def L_model_forward(X, parameters):
    """
    Implement forward propagation for the 
    [LINEAR->RELU]*(L-1)->LINEAR->SIGMOID computation
    
    Arguments:
    X -- data, numpy array of shape 
    (input size, number of examples)
    parameters -- output of initialize_parameters_deep()
    
    Returns:
    AL -- last post-activation value
    caches -- list of caches containing:
    every cache of linear_relu_forward() 
    (there are L-1 of them, indexed from 0 to L-2)
    the cache of linear_sigmoid_forward() (there is one, indexed L-1)
    """

    caches = []
    A = X
    L = len(parameters) // 2  # number of layers in the neural network
    # Implement [LINEAR -> RELU]*(L-1). Add "cache" to the "caches" list.
    for l in range(1, L):
        A_prev = A 
        ### START CODE HERE ### (≈ 2 lines of code)
        A, linear_activation_cache = linear_activation_forward(A_prev,
        parameters['W%s' % l],  parameters['b%s' % l], activation = "relu")
        caches.append(linear_activation_cache)
        ### END CODE HERE ###
    # Implement LINEAR -> SIGMOID. Add "cache" to the "caches" list.
    ### START CODE HERE ### (≈ 2 lines of code)
    AL, linear_activation_cache = linear_activation_forward(A,
    parameters['W%s' % L],  parameters['b%s' % L], activation = "sigmoid")
    caches.append(linear_activation_cache)
    ### END CODE HERE ###
    return AL, caches

计算损失

def compute_cost(AL, Y):
    m = Y.shape[1]
    # Compute loss from aL and y.
    ### START CODE HERE ### (≈ 1 lines of code)
    cost = -1./ m * (np.dot(np.log(AL), Y.T) 
                     + np.dot(np.log(1-AL), (1-Y).T))
    ### END CODE HERE ###
    cost = np.squeeze(cost)      
    return cost

后向运算

def linear_backward(dZ, cache):
    """
    Implement the linear portion of backward propagation for
     a single layer (layer l)

    Arguments:
    dZ -- Gradient of the cost with respect 
    to the linear output (of current layer l)
    cache -- tuple of values (A_prev, W, b) 
    coming from the forward propagation in the current layer

    Returns:
    dA_prev -- Gradient of the cost with respect 
    to the activation (of the previous layer l-1), same shape as A_prev
    dW -- Gradient of the cost with respect to W 
    (current layer l), same shape as W
    db -- Gradient of the cost with respect to b 
    (current layer l), same shape as b
    """
    A_prev, W, b = cache
    m = A_prev.shape[1]
    
    dA_prev = np.dot(W.T, dZ)
    dW = 1./ m * np.dot(dZ, A_prev.T)
    db = 1./m * np.sum(dZ, axis=1, keepdims=True)
    ### END CODE HERE ###
    return dA_prev, dW, db

def linear_activation_backward(dA, cache, activation):
    """
    Implement the backward propagation for 
    the LINEAR->ACTIVATION layer.
    
    Arguments:
    dA -- post-activation gradient for current layer l 
    cache -- tuple of values (linear_cache, activation_cache) 
    we store for computing backward propagation efficiently
    activation -- the activation to be used in this layer, 
    stored as a text string: "sigmoid" or "relu"
    
    Returns:
    dA_prev -- Gradient of the cost with respect to the activation 
    (of the previous layer l-1), same shape as A_prev
    dW -- Gradient of the cost with respect to W (current layer l), 
    same shape as W
    db -- Gradient of the cost with respect to b (current layer l), 
    same shape as b
    """
    linear_cache, activation_cache = cache
    
    if activation == "relu":
        ### START CODE HERE ### (≈ 2 lines of code)
        dZ = sigmoid_backward(dA, activation_cache)
        dA_prev, dW, db = linear_backward(dZ, linear_cache)
        ### END CODE HERE ###
        
    elif activation == "sigmoid":
        ### START CODE HERE ### (≈ 2 lines of code)
        dZ = relu_backward(dA, activation_cache)
        dA_prev, dW, db = linear_backward(dZ, linear_cache)
        ### END CODE HERE ###
    
    return dA_prev, dW, db

def L_model_backward(AL, Y, caches):
    """
    Implement the backward propagation for the 
    [LINEAR->RELU] * (L-1) -> LINEAR -> SIGMOID group
    
    Arguments:
    AL -- probability vector, output of the forward 
    propagation (L_model_forward())
    Y -- true "label" vector (containing 0 if non-cat, 1 if cat)
    caches -- list of caches containing:
        every cache of linear_activation_forward() with "relu" 
        (it's caches[l], for l in range(L-1) i.e l = 0...L-2)
        the cache of linear_activation_forward() with 
        "sigmoid" (it's caches[L-1])
    
    Returns:
    grads -- A dictionary with the gradients
             grads["dA" + str(l)] = ...
             grads["dW" + str(l)] = ...
             grads["db" + str(l)] = ...
    """
    grads = {}
    L = len(caches) # the number of layers
    m = AL.shape[1]
    Y = Y.reshape(AL.shape) # after this line, Y is the same shape as AL
    
    # Initializing the backpropagation
    ### START CODE HERE ### (1 line of code)
    grads['dA'+str(L)] = - (np.divide(Y, AL) - np.divide(1 - Y, 1 - AL))
    ### END CODE HERE ###
   
    layer = L
    grads['dA'+str(layer-1)], grads['dW'+str(layer)],grads['db'+str(layer)]
    = linear_activation_backward(grads['dA'+str(layer)], caches[layer-1],
    activation = "sigmoid")
    for l in reversed(range(L - 1)):
        layer = l + 1
        grads['dA'+str(layer-1)],
        grads['dW'+str(layer)],grads['db'+str(layer)] 
        = linear_activation_backward(grads['dA'+str(layer)], 
        caches[layer-1], activation = "relu")
    return grads

更新参数

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 L_model_backward
    
    Returns:
    parameters -- python dictionary containing your updated parameters 
                  parameters["W" + str(l)] = ... 
                  parameters["b" + str(l)] = ...
    """
    
    L = len(parameters) // 2 # number of layers in the neural network
    for l in range(1, L+1):
        parameters['W'+str(l)] = parameters['W'+str(l)] 
        - learning_rate * grads['dW'+str(l)]
        parameters['b'+str(l)] = parameters['b'+str(l)] 
        - learning_rate * grads['db'+str(l)]
    return parameters

组装模型

def L_layer_model(X, Y, layers_dims, learning_rate = 0.0075,
 num_iterations = 3000, print_cost=False):#lr was 0.009
    """
    Implements a L-layer neural network: 
    [LINEAR->RELU]*(L-1)->LINEAR->SIGMOID.
    
    Arguments:
    X -- data, numpy array of shape 
    (number of examples, num_px * num_px * 3)
    Y -- true "label" vector (containing 0 if cat, 1 if non-cat),
     of shape (1, number of examples)
    layers_dims -- list containing the input size and each
     layer size, of length (number of layers + 1).
    learning_rate -- learning rate of the gradient descent update rule
    num_iterations -- number of iterations of the optimization loop
    print_cost -- if True, it prints the cost every 100 steps
    
    Returns:
    parameters -- parameters learnt by the model.
    They can then be used to predict.
    """

    np.random.seed(1)
    costs = []
    
    # Parameters initialization.
    ### START CODE HERE ###
    parameters = initialize_parameters_deep(layers_dims)
    ### END CODE HERE ###
    
    # Loop (gradient descent)
    for i in range(0, num_iterations):

        # Forward propagation: [LINEAR -> RELU]*(L-1) -> LINEAR -> SIGMOID.
        ### START CODE HERE ### (≈ 1 line of code)
        AL, caches = L_model_forward(X, parameters)
        ### END CODE HERE ###
        
        # Compute cost.
        ### START CODE HERE ### (≈ 1 line of code)
        cost = compute_cost(AL, Y)
        ### END CODE HERE ###
    
        # Backward propagation.
        ### START CODE HERE ### (≈ 1 line of code)
        grads = L_model_backward(AL, Y, caches)
        ### END CODE HERE ###
 
        # Update parameters.
        ### START CODE HERE ### (≈ 1 line of code)
        parameters = update_parameters(parameters, grads, learning_rate)
        ### END CODE HERE ###
                
        # Print the cost every 100 training example
        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)
            
    # plot the 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

3、问题及思考

除了L层的后向运算的测试用例外，其余各个环节及最后的结果都是正确的。
我的代码的运行结果和测试用例的对比如下图所示：

可以看到运行结果是完全对不上的！
所以网上找了很多答案，他们的代码与我的代码的不同之处都在L层的反向传播处：
（1）来源

(2)来源

就这两个答案来看，他们的写法在我看来是错误的；但是他们能对上答案，而对不上；我改成了它们的样子也对不上~所以对不上答案的问题可能在于我的测试用例？我也没有去看他们的测试用例和我的是否一样！反正就是这一个测试用例过不去，后面的全对。证明我的实现是没有问题的。
然后要说为什么它们的代码在我看来是不正确的，我的代码如下

很明显，1处的公式得到的就是输出层（L）的激活值的导数，而2和3每次求导，都应该得到前一层的激活值的导数与当前层的W和b的导数！如下图所示