时间戳

首页 > 解决方案 > 跟踪神经网络中的缓存

python - 跟踪神经网络中的缓存

问题描述

我尝试实现基于 Coursera 深度学习课程的 L 层神经网络模型，但在将缓存添加到缓存列表时遇到问题。

caches = list.append(cache)

该课程建议使用 list.append() 函数。其余代码如下：

def L_model_forward(X, parameters):
    """
    Implement forward propagation 

    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_activation_forward() (there are L-1 of them, indexed from 0 to 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, cache = linear_activation_forward(A_prev, parameters['W' + str(l)], parameters['b' + str(l)], activation = "relu")
        caches = list.append(cache)
        ### END CODE HERE ###

    # Implement LINEAR -> SIGMOID. Add "cache" to the "caches" list.
    ### START CODE HERE ### (≈ 2 lines of code)
    AL, cache =  linear_activation_forward(A, parameters['W' + str(L)], parameters['b' + str(L)], activation = "sigmoid")
    caches = list.append(cache)    
    ### END CODE HERE ###

    assert(AL.shape == (1,X.shape[1]))

    return AL, caches

当我运行代码时，这是错误：

TypeError：描述符“附加”需要一个“列表”对象但收到一个“元组”

标签： pythonneural-network

解决方案

您不能使用 追加到列表中caches = list.append(cache)。它必须由caches.append(cache)and 附加，然后在caches将元组缓存添加到列表中之前使用cache=list(cache)，然后在缓存列表中使用caches.append(cache).

您的代码将如下所示：-

def L_model_forward(X, parameters):

    caches = []
    A = X
    L = len(parameters) // 2   # number of layers in the neural network
    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(list(cache))


    AL, cache =  linear_activation_forward(A, parameters['W' + str(L)], parameters['b' + str(L)], activation = "sigmoid")
    caches.append(list(cache))    

    assert(AL.shape == (1,X.shape[1]))

    return AL, caches

推荐阅读