L1W4多层神经网络--深度学习笔记
2020-06-28 本文已影响0人
Sunooo
如何使用多层神经网络来进行预测？
在使用jupyter notebook做完两道编程题之后，实在厌倦了没有提示的环境下代码，也曾尝试过安装插件，但是效果不理想。
所以下载了pyCharm 2020版，30天的免费也足够当下用了。
多层神经网络的步骤与单层神经网络的思路和步骤大同小异，具体的就是公式不一样。
个人总结的构建神经网络的步骤
1.定义神经网络结构，确定输入项，输出项和隐藏层
2.构造初始化函数，得到初始W和b参数
3.构造正向传播函数，选择合适的激活函数，例如sigmoid, tanh 等
4.构造成本函数，计算损失J
5.构造反向传播函数，得到参数的梯度
6.构造优化函数，设置学习率，对参数进行更新
7.合成神经网络模型函数，输出结果为参数
8.构造预测函数，根据神经网络模型获得的参数机型预测分析，得到准确率
python编写代码的时候，一定要注意左侧对齐，例如for循环就是按照左侧对齐来判断for的作用域的，如果对齐错了，就会产生bug。
然后使用plt绘图的时候，要使用.show()才能输出图片。
在开始之前需要先准备测试数据文件和工具类
链接: https://pan.baidu.com/s/1tb-QT1AamPB8N4XMSVLPnQ 密码: m8pi
如果缺少相应库的话，也需要安装，如果做了前面两道题，应该都已经安装完毕了。
下面就上代码了
import numpy as np
from testCases import linear_forward_test_case, linear_activation_forward_test_case, L_model_forward_test_case, \
linear_backward_test_case, linear_activation_backward_test_case, update_parameters_test_case, L_model_backward_test_case
import h5py
import matplotlib.pyplot as plt
from dnn_utils import sigmoid, sigmoid_backward, relu, relu_backward
import lr_utils
np.random.seed(1)
# 初始化模型参数, 两层网络
def initialize_parameters(n_x, n_h, n_y):
print(n_h)
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))
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
# 初始化多层神经网络，L层, layers_dims 为包含网络中每个图层的节点数量的列表
def initialize_parameters_deep(layers_dims):
np.random.seed(3)
parameters = {}
L = len(layers_dims)
for l in range(1, L):
parameters["W" + str(l)] = np.random.randn(layers_dims[l], layers_dims[l - 1]) / np.sqrt(layers_dims[l - 1])
parameters["b" + str(l)] = np.zeros((layers_dims[l], 1))
assert (parameters["W" + str(l)].shape == (layers_dims[l], layers_dims[l - 1]))
assert (parameters["b" + str(l)].shape == (layers_dims[l], 1))
return parameters
# 线性正向传播
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
#正向传播+激活函数,包括sigmoid和relu两种激活函数
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)
return A, cache
#正向传播+L层+激活函数，L-1层都是relu，L层是sigmoid
def L_model_forward(X, parameters):
caches = []
A = X
L = len(parameters) // 2
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)
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]))
return AL, caches
#构造成本函数，计算损失
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
#线性反向传播
def linear_backward(dZ, cache):
A_prev, W, b = cache
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
#反向传播+激活函数，可选relu和sigmoid
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
#反向传播+L层+激活函数，L层的激活函数是sigmoid，其他L-1层的激活函数是relu
def L_model_backward(AL, Y, caches):
grads = {}
L = len(caches)
m = AL.shape[1]
Y = Y.reshape(AL.shape)
#用损失函数的导数求dAL
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,
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
#优化函数，设置学习率，对参数进行更新
def update_parameters(parameters, grads, learning_rate):
L = len(parameters) // 2
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
#搭建两层神经网络
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
parameters = initialize_parameters(n_x, n_h, n_y)
W1 = parameters["W1"]
b1 = parameters["b1"]
W2 = parameters["W2"]
b2 = parameters["b2"]
for i in range(0, num_iterations):
A1, cache1 = linear_activation_forward(X, W1, b1, "relu")
A2, cache2 = linear_activation_forward(A1, W2, b2, "sigmoid")
cost = compute_cost(A2, Y)
dA2 = -(np.divide(Y, A2) - np.divide(1 - Y, 1 - A2))
dA1, dW2, db2 = linear_activation_backward(dA2, cache2, "sigmoid")
dA0, dW1, db1 = linear_activation_backward(dA1, cache1, "relu")
grads["dW1"] = dW1
grads["db1"] = db1
grads["dW2"] = dW2
grads["db2"] = db2
parameters = update_parameters(parameters, grads, learning_rate)
W1 = parameters["W1"]
b1 = parameters["b1"]
W2 = parameters["W2"]
b2 = parameters["b2"]
if i % 100 == 0 :
costs.append(cost)
if print_cost:
print("第", i, "次迭代，成本值为: ", np.squeeze(cost))
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
'''
#测试两层神经网络
train_set_x_orig , train_set_y , test_set_x_orig , test_set_y , classes = lr_utils.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
n_x = 12288
n_h = 7
n_y = 1
layers_dims = (n_x,n_h,n_y)
print(train_x)
print(train_set_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)
'''
# 构建预测函数
def predict(X, Y, parameters):
m = X.shape[1]
n = len(parameters) // 2
p = np.zeros((1, m))
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
#测试两层神经网络
#predictions_train = predict(train_x, train_y, parameters)
#predictions_test = predict(test_x, test_y, parameters)
#搭建多层神经网络
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)
if i % 100 == 0:
costs.append(cost)
if print_cost:
print("第", i, "次迭代，成本值为：", np.squeeze(cost))
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
#测试多层神经网络
train_set_x_orig , train_set_y , test_set_x_orig , test_set_y , classes = lr_utils.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
layers_dims = [12288, 20, 7, 5, 1]
parameters = L_layer_model(train_x, train_y, layers_dims, num_iterations = 2500, print_cost = True,isPlot=False)
pred_train = predict(train_x, train_y, parameters)
pred_test = predict(test_x, test_y, parameters)
'''
L1W2的编程题，结果正确率为0.70
二层网络，结果正确率为0.72
多层网络，结果正确率为0.78
说明添加神经网络层数，可以提高预测的正确率
'''
#查看谁在L层被错误标记
def print_mislabeled_images(classes, X, Y, p):
a = p + Y
mislabeled_indices = np.asarray(np.where(a == 1))
plt.rcParams['figure.figsize'] = (40.0, 40.0)
num_images = len(mislabeled_indices[0])
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"))
plt.show()
return 0
print_mislabeled_images(classes, test_x, test_y, pred_test)
代码编写参考了以下两位博主的文章，在此感谢他们的无私奉献。
https://blog.csdn.net/u013733326/article/details/79767169
https://www.kesci.com/home/project/5dd798fbf41512002ceb38de
