deep learning 专项课程一 代码（深层网络构建）

对于构造一个多层神经网络，有以下步骤

对于二层的神经网络整体流程函数如下：

def initialize_parameters(n_x, n_h, n_y):
...
return parameters
def linear_activation_forward(A_prev, W, b, activation):
...
return A, cache
def compute_cost(AL, Y):
...
return cost
def linear_activation_backward(dA, cache, activation):
...
return dA_prev, dW, db
def update_parameters(parameters, grads, learning_rate):
...
return parameters

多层的神经网络定义流程如下：

def initialize_parameters_deep(layer_dims):
...
return parameters
def L_model_forward(X, parameters):
...
return AL, caches
def compute_cost(AL, Y):
...
return cost
def L_model_backward(AL, Y, caches):
...
return grads
def update_parameters(parameters, grads, learning_rate):
...
return parameters

主要核心代码如下：

def initialize_parameters_deep(layer_dims):    
    np.random.seed(3)
    parameters = {}
    L = len(layer_dims)            
    for l in range(1, L):
        parameters['W' + str(l)] = np.random.randn(layer_dims[l], layer_dims[l-1])*0.01
        parameters['b' + str(l)] = np.zeros((layer_dims[l], 1))     
        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

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

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) //activation_cache包含Z,A是算出的结果
    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)
    return A, cache

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)],"relu")
        caches.append(cache)
    AL, cache = linear_activation_forward(A, parameters["W"+str(L)], parameters["b"+str(L)], "sigmoid")
    caches.append(cache)
    assert(AL.shape == (1,X.shape[1]))      
    return AL, caches

def compute_cost(AL, Y):
    m = Y.shape[1]
    cost = -np.sum(np.multiply(np.log(AL),Y)+np.multiply(np.log(1-AL),1-Y))/m
    cost = np.squeeze(cost) 
    assert(cost.shape == ())
    return cost

def linear_backward(dZ, cache):
    A_prev, W, b = cache
    m = A_prev.shape[1]
    dW = np.dot(dZ,A_prev.T)/m
    db = np.sum(dZ,axis=1,keepdims=True)/m
    dA_prev = np.dot(W.T,dZ)
    return dA_prev, dW, db

def linear_activation_backward(dA, cache, activation):
    linear_cache, activation_cache = cache
    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

def L_model_backward(AL, Y, caches):
    grads = {}
    L = len(caches) # the number of layers
    m = AL.shape[1]
    Y = Y.reshape(AL.shape)
    dAL = - (np.divide(Y, AL) - np.divide(1 - Y, 1 - AL))
    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")
  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,"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):    
    L = len(parameters) // 2
    for i in range(1,L):
        parameters["W"+str(i)]=parameters["W"+str(i)]-learning_rate*grads["dW"+str(i)]
        parameters["b"+str(i)]=parameters["b"+str(i)]-learning_rate*grads["db"+str(i)]
    return parameters