链接：https://pan.baidu.com/s/1ypHuubawEcuJyAxyRMErYg 提取码：a9av
这次的作业是建立一个2分类的神经网络
源代码：
import numpy as np
import matplotlib.pyplot as plt
from testCases import *
import sklearn
import sklearn.datasets
import sklearn.linear_model
from planar_utils import plot_decision_boundary, sigmoid, load_planar_dataset, load_extra_datasets
np.random.seed(1) #设置一个固定的随机种子，保证接下来的随机数是一致的。
X,Y=load_planar_dataset()#加载数据集
plt.scatter(X[0,:],X[1,:],c=np.squeeze(Y),s=40, cmap=plt.cm.Spectral)#绘制图像
# plt.show()
shape_X=X.shape
shape_Y=Y.shape
m=Y.shape[1]
# 构建神经网络的一般方法是：
# 1. 定义神经网络结构（输入单元的数量，隐藏单元的数量等）。
# 2. 初始化模型的参数
# 3. 循环：
# 实施前向传播
# 计算损失
# 实现向后传播
# 更新参数（梯度下降）
def layer_sizes(X,Y):
"""
:param X: 输入数据
:param Y:标签
:return:输入层，隐藏层，输出层
"""
n_x=X.shape[0]
n_h=4
n_y=Y.shape[0]
return n_x,n_h,n_y
def initialize_parameters(n_x,n_h,n_y):
np.random.seed(2)
W1=np.random.randn(n_h,n_x)*0.01
b1=np.zeros(shape=(n_h,1))
W2=np.random.randn(n_y,n_h)*0.01
b2=np.zeros(shape=(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,
'W2':W2,
'b1':b1,
'b2':b2
}
return parameters
def forward_propagation(X,parameters):
W1 = parameters['W1']
b1 = parameters['b1']
W2 = parameters['W2']
b2 = parameters['b2']
Z1=np.dot(W1,X)+b1
A1=np.tanh(Z1)
Z2=np.dot(W2,A1)+b2
A2=sigmoid(Z2)
assert (A2.shape==(1,X.shape[1]))
cache={
'Z1':Z1,
'Z2':Z2,
'A1':A1,
'A2':A2
}
return A2,cache
def compute_cost(A2,Y,):
m=Y.shape[1]
logprobs=Y*np.log(A2)+(1-Y)*np.log(1-A2)
cost=-np.sum(logprobs)/m
cost=float(np.squeeze(cost))
assert (isinstance(cost,float))
return cost
def backward_propagation(parameters,cache,X,Y):
A1=cache['A1']
A2=cache['A2']
m=Y.shape[1]
W2=parameters['W2']
dZ2=A2-Y
dW2=np.dot(dZ2,A1.T)/m
db2=np.sum(dZ2,axis=1,keepdims=True)/m
dZ1=np.multiply(np.dot(W2.T,dZ2),1 - np.power(A1, 2))
dW1=np.dot(dZ1,X.T)/m
db1=np.sum(dZ1,axis=1,keepdims=True)/m
grads={
'dW1':dW1,
'dW2':dW2,
'db1':db1,
'db2':db2
}
return grads
def update_parameters(parameters,grads,learning_rate=1.2):
W1=parameters['W1']
W2=parameters['W2']
b1=parameters['b1']
b2=parameters['b2']
dW1=grads['dW1']
dW2=grads['dW2']
db1=grads['db1']
db2=grads['db2']
W1=W1-learning_rate*dW1
b1=learning_rate*db1
W2=W2-learning_rate*dW2
b2=b2-learning_rate*db2
parameters={
'W1':W1,
'W2':W2,
'b1':b1,
'b2':b2
}
return parameters
def nn_model(X,Y,n_h,num_iterations,print_cost=False):
np.random.seed(3)
n_x=layer_sizes(X,Y)[0]
n_y=layer_sizes(X,Y)[2]
parameters=initialize_parameters(n_x,n_h,n_y)
for i in range(num_iterations):
A2,cache=forward_propagation(X,parameters)
cost=compute_cost(A2,Y)
grads=backward_propagation(parameters,cache,X,Y)
parameters=update_parameters(parameters,grads,learning_rate=0.5)
if print_cost:
if i00==0:
print("第",i,"次循环，成本为："+str(cost))
return parameters
def predict(parameters,X):
A2 , cache = forward_propagation(X,parameters)
predictions = np.round(A2)
return predictions
parameters = nn_model(X, Y, n_h = 4, num_iterations=10000, print_cost=True)
#绘制边界
plot_decision_boundary(lambda x: predict(parameters, x.T), X, Y)
plt.title("Decision Boundary for hidden layer size " + str(4))
predictions = predict(parameters, X)
print ('准确率: %d' % float((np.dot(Y, predictions.T) + np.dot(1 - Y, 1 - predictions.T)) / float(Y.size) * 100) + '%')
参考：https://blog.csdn.net/u013733326/article/details/79827273
