DeepLearing学习笔记-改善深层神经网络(第一周作业-3-梯度校验)

最新推荐文章于 2021-12-21 22:44:46 发布

JasonLiu1919

最新推荐文章于 2021-12-21 22:44:46 发布

阅读量1.9k

点赞数 3

分类专栏：深度学习文章标签：神经网络 deep-learning

本文链接：https://blog.csdn.net/ljp1919/article/details/78241599

版权

深度学习专栏收录该内容

55 篇文章 3 订阅

订阅专栏

1-背景：

在神经网络计算过程中，对后向传播的梯度进行校验，确保其计算无误。至于，前向传播，由于相对简单，所以，一般不会出错，在前向传播的基础上利用计算出来的代价 $J$ 我们可以进行后向梯度的校验。

公式原理如下：

\partial J \partial θ = lim ε \to 0 J ( θ + ε ) - J ( θ - ε ) 2 ε (1)

$\frac{\partial J}{\partial \theta} = \lim_{\varepsilon \to 0} \frac{J(\theta + \varepsilon) - J(\theta - \varepsilon)}{2 \varepsilon} \tag{1}$
在前向传播的基础上，我们可以获取到

J $J$ ，也就可以上公式1的计算，将计算的结果值和反向传播的梯度值按照一定的方式做比较即可。

2- 一维梯度校验

当 $J(\theta) = \theta x$ ，线性模型如下:
这里写图片描述
该模型的前向传播和后向传播的代码如下：

# GRADED FUNCTION: forward_propagation

def forward_propagation(x, theta):
    """
    Implement the linear forward propagation (compute J) presented in Figure 1 (J(theta) = theta * x)

    Arguments:
    x -- a real-valued input
    theta -- our parameter, a real number as well

    Returns:
    J -- the value of function J, computed using the formula J(theta) = theta * x
    """

    ### START CODE HERE ### (approx. 1 line)
    J = theta * x
    ### END CODE HERE ###

    return J

x, theta = 2, 4
J = forward_propagation(x, theta)
print ("J = " + str(J))

输出结果：
J = 8

由于 $J(\theta) = \theta x$ 所以 $dtheta = \frac { \partial J }{ \partial \theta} = x$

# GRADED FUNCTION: backward_propagation

def backward_propagation(x, theta):
    """
    Computes the derivative of J with respect to theta (see Figure 1).

    Arguments:
    x -- a real-valued input
    theta -- our parameter, a real number as well

    Returns:
    dtheta -- the gradient of the cost with respect to theta
    """

    ### START CODE HERE ### (approx. 1 line)
    dtheta = x
    ### END CODE HERE ###

    return dtheta

x, theta = 2, 4
dtheta = backward_propagation(x, theta)
print ("dtheta = " + str(dtheta))

输出结果：
dtheta = 2

2-1 一维梯度校验

步骤如下：

计算梯度近似值 “gradapprox”:
1. $\theta^{+} = \theta + \varepsilon$
2. $\theta^{-} = \theta - \varepsilon$
3. $J^{+} = J(\theta^{+})$
4. $J^{-} = J(\theta^{-})$
5. $gradapprox = \frac{J^{+} - J^{-}}{2 \varepsilon}$
进行反向传播，获取梯度值 “grad”
按照如下公式计算两者difference :
$d i f f e r e n c e = ∣ ∣ g r a d - g r a d a p p r o x ∣ ∣ 2 ∣ ∣ g r a d ∣ ∣ 2 + ∣ ∣ g r a d a p p r o x ∣ ∣ 2 (2)$ $difference = \frac {\mid\mid grad - gradapprox \mid\mid_2}{\mid\mid grad \mid\mid_2 + \mid\mid gradapprox \mid\mid_2} \tag{2}$

范数的计算可以用np.linalg.norm(...)
当difference 足够小(< $10^{-7}$ )，则可以视为梯度校验通过。

2-2 梯度校验代码：

# GRADED FUNCTION: gradient_check

def gradient_check(x, theta, epsilon = 1e-7):
    """
    Implement the backward propagation presented in Figure 1.

    Arguments:
    x -- a real-valued input
    theta -- our parameter, a real number as well
    epsilon -- tiny shift to the input to compute approximated gradient with formula(1)

    Returns:
    difference -- difference (2) between the approximated gradient and the backward propagation gradient
    """

    # Compute gradapprox using left side of formula (1). epsilon is small enough, you don't need to worry about the limit.
    ### START CODE HERE ### (approx. 5 lines)
    thetaplus = theta + epsilon                              # Step 1
    thetaminus = theta - epsilon                             # Step 2
    J_plus = forward_propagation(x, thetaplus)                                  # Step 3
    J_minus = forward_propagation(x, thetaminus)                                # Step 4
    gradapprox = (J_plus-J_minus)/(2*epsilon)                              # Step 5
    ### END CODE HERE ###

    # Check if gradapprox is close enough to the output of backward_propagation()
    ### START CODE HERE ### (approx. 1 line)
    grad = backward_propagation(x, theta)
    ### END CODE HERE ###

    ### START CODE HERE ### (approx. 1 line)
    numerator = np.linalg.norm(grad - gradapprox)                               # Step 1'
    denominator = np.linalg.norm(grad)+np.linalg.norm(gradapprox)               # Step 2'
    difference = numerator/denominator                              # Step 3'
    ### END CODE HERE ###

    if difference < 1e-7:
        print ("The gradient is correct!")
    else:
        print ("The gradient is wrong!")

    return difference

测试：

x, theta = 2, 4
difference = gradient_check(x, theta)
print("difference = " + str(difference))

运行结果如下：

The gradient is correct!
difference = 2.91933588329e-10

difference 明显小于阈值 $10^{-7}$ ，校验通过。

3- N微梯度校验

本文采用3层神经网络做说明，模型：LINEAR -> RELU -> LINEAR -> RELU -> LINEAR -> SIGMOID
这里写图片描述

3-1 前向传播和后向传播：

前向传播代码：

def forward_propagation_n(X, Y, parameters):
    """
    Implements the forward propagation (and computes the cost) presented in Figure 3.

    Arguments:
    X -- training set for m examples
    Y -- labels for m examples 
    parameters -- python dictionary containing your parameters "W1", "b1", "W2", "b2", "W3", "b3":
                    W1 -- weight matrix of shape (5, 4)
                    b1 -- bias vector of shape (5, 1)
                    W2 -- weight matrix of shape (3, 5)
                    b2 -- bias vector of shape (3, 1)
                    W3 -- weight matrix of shape (1, 3)
                    b3 -- bias vector of shape (1, 1)

    Returns:
    cost -- the cost function (logistic cost for one example)
    """

    # retrieve parameters
    m = X.shape[1]
    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)

    # Cost
    logprobs = np.multiply(-np.log(A3),Y) + np.multiply(-np.log(1 - A3), 1 - Y)
    cost = 1./m * np.sum(logprobs)

    cache = (Z1, A1, W1, b1, Z2, A2, W2, b2, Z3, A3, W3, b3)

    return cost, cache

这里的后向传播，故意在dW2和db1这里写错：

def backward_propagation_n(X, Y, cache):
    """
    Implement the backward propagation presented in figure 2.

    Arguments:
    X -- input datapoint, of shape (input size, 1)
    Y -- true "label"
    cache -- cache output from forward_propagation_n()

    Returns:
    gradients -- A dictionary with the gradients of the cost 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 = A3 - Y
    dW3 = 1./m * np.dot(dZ3, A2.T)
    db3 = 1./m * np.sum(dZ3, axis=1, keepdims = True)

    dA2 = np.dot(W3.T, dZ3)
    dZ2 = np.multiply(dA2, np.int64(A2 > 0))
    dW2 = 1./m * np.dot(dZ2, A1.T)#不用乘以2
    db2 = 1./m * np.sum(dZ2, axis=1, keepdims = True)

    dA1 = np.dot(W2.T, dZ2)
    dZ1 = np.multiply(dA1, np.int64(A1 > 0))
    dW1 = 1./m * np.dot(dZ1, X.T)
    db1 = 1./m * np.sum(dZ1, axis=1, keepdims = True)#分子是1，不是4

    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

3-2 梯度校验

对每个参数执行如下操作:

计算J_plus[i]:
1. $\theta^{+}$ = np.copy(parameters_values)
2. $\theta^{+}_i$ = $\theta^{+}_i + \varepsilon$
3. 采用forward_propagation_n(x, y, vector_to_dictionary( $\theta^{+}$ ))计算 $J^{+}_i$
对于 $\theta^{-}$ 同理计算 J_minus[i]
计算 $gradapprox[i] = \frac{J^{+}_i - J^{-}_i}{2 \varepsilon}$

gradapprox中的 gradapprox[i] 对应的是参数parameter_values[i]的梯度近似值。gradapprox 向量和后向传播的梯度的相似按照如下公式估算.:

d i f f e r e n c e = ∥ g r a d - g r a d a p p r o x ∥ 2 ∥ g r a d ∥ 2 + ∥ g r a d a p p r o x ∥ 2 (3)

$difference = \frac {\| grad - gradapprox \|_2}{\| grad \|_2 + \| gradapprox \|_2 } \tag{3}$

3-2 梯度校验

# GRADED FUNCTION: gradient_check_n

def gradient_check_n(parameters, gradients, X, Y, epsilon = 1e-7):
    """
    Checks if backward_propagation_n computes correctly the gradient of the cost output by forward_propagation_n

    Arguments:
    parameters -- python dictionary containing your parameters "W1", "b1", "W2", "b2", "W3", "b3":
    grad -- output of backward_propagation_n, contains gradients of the cost with respect to the parameters. 
    x -- input datapoint, of shape (input size, 1)
    y -- true "label"
    epsilon -- tiny shift to the input to compute approximated gradient with formula(1)

    Returns:
    difference -- difference (2) between the approximated gradient and the backward propagation gradient
    """

    # Set-up variables
    parameters_values, _ = dictionary_to_vector(parameters)
    grad = gradients_to_vector(gradients)#将字典转为向量形式
    num_parameters = parameters_values.shape[0]#参数个数
    J_plus = np.zeros((num_parameters, 1))
    J_minus = np.zeros((num_parameters, 1))
    gradapprox = np.zeros((num_parameters, 1))

    # Compute gradapprox
    for i in range(num_parameters):

        # Compute J_plus[i]. Inputs: "parameters_values, epsilon". Output = "J_plus[i]".
        # "_" is used because the function you have to outputs two parameters but we only care about the first one
        ### START CODE HERE ### (approx. 3 lines)
        thetaplus = np.copy(parameters_values)                                      # Step 1
        thetaplus[i][0] = thetaplus[i][0]+epsilon                                # Step 2
        J_plus[i], _ = forward_propagation_n(X, Y, vector_to_dictionary(thetaplus))                                   # Step 3
        ### END CODE HERE ###

        # Compute J_minus[i]. Inputs: "parameters_values, epsilon". Output = "J_minus[i]".
        ### START CODE HERE ### (approx. 3 lines)
        thetaminus = np.copy(parameters_values)                                     # Step 1
        thetaminus[i][0] = thetaminus[i][0]-epsilon                               # Step 2        
        J_minus[i], _ =  forward_propagation_n(X, Y, vector_to_dictionary(thetaminus))                                  # Step 3
        ### END CODE HERE ###

        # Compute gradapprox[i]
        ### START CODE HERE ### (approx. 1 line)
        gradapprox[i] = (J_plus[i]-J_minus[i])/(2*epsilon)
        ### END CODE HERE ###

    # Compare gradapprox to backward propagation gradients by computing difference.
    ### START CODE HERE ### (approx. 1 line)
    numerator = np.linalg.norm(grad-gradapprox)                                            # Step 1'
    denominator = np.linalg.norm(grad)+np.linalg.norm(gradapprox)                                         # Step 2'
    difference = numerator/denominator                                          # Step 3'
    ### END CODE HERE ###
    #注意这里epsilon值的问题，如果是1e-6是可以的，使得梯度校验通过，epsilon值越小，反而和导数越不一致
    if difference > 1e-7:
        print ("\033[93m" + "There is a mistake in the backward propagation! difference = " + str(difference) + "\033[0m")
    else:
        print ("\033[92m" + "Your backward propagation works perfectly fine! difference = " + str(difference) + "\033[0m")

    return difference

测试代码：

X, Y, parameters = gradient_check_n_test_case()
cost, cache = forward_propagation_n(X, Y, parameters)
gradients = backward_propagation_n(X, Y, cache)
difference = gradient_check_n(parameters, gradients, X, Y)

测试结果：
There is a mistake in the backward propagation! difference = 0.285093156654
明显存在梯度计算问题。将反向梯度计算的dW2和db1进行修改，重新运行：
There is a mistake in the backward propagation! difference = 1.18855520355e-07
虽然现实出现问题，但是different值已经很接近阈值了，此时，我们单独修改计算双边梯度之后的epsilon=1e-6,不修改判断的阈值。
输出：
Your backward propagation works perfectly fine! difference = 8.26588225515e-09
所以，要注意看difference值是否和阈值相距很大。本文为何就差那么一些，导致需要修改epsilon，可能是由于代价函数在局部存在毛刺，导致估算值和后向梯度计算结果，存在超于阈值的偏差。另外，relu的导数在0处有歧义，也可能导致此处的不够准确。

JasonLiu1919

关注

3
点赞
踩
4

收藏

觉得还不错? 一键收藏
1
评论
DeepLearing学习笔记-改善深层神经网络(第一周作业-3-梯度校验)

1-背景：在神经网络计算过程中，对后向传播的梯度进行校验，确保其计算无误。至于，前向传播，由于相对简单，所以，一般不会出错，在前向传播的基础上利用计算出来的代价JJ我们可以进行后向梯度的校验。公式原理如下： ∂J∂θ=limε→0J(θ+ε)−J(θ−ε)2ε(1) \frac{\partial J}{\partial \theta} = \lim_{\varepsilon \to 0} \fra
复制链接

扫一扫

专栏目录