第二周编程作业

第一步：安装包

numpy

matplotliv

h5py

scipy

pillow

常用公式：

#查看有什么包
conda list

#导入数据
import h5py

#训练数据
train_data=h5py.File('D:\\Learning\\WED\\train_catvnoncat.h5','r')
test_data=h5py.File('D:\\Learning\\WED\\test_catvnoncat.h5','r')

#查看关键字
for key in train_data.keys():
    print(key)
#输出
#list_classes ：是猫/不是猫 
#train_set_x ：输入的图片
#train_set_y ：输入图片的分类：是或者不是

#查看train_data中train_set_x的维度
train_data['train_set_x'].shape
#输出
#(209, 64, 64, 3)：209张图片，图片的三个通道（64，64，3）

#查看train_data中train_set_y的维度
train_data['train_set_y'].shape
#输出
#(209,):209个是不是猫的标签

#取出训练集和测试集
#[:]表示取出数据集train_data中特征值train_set_x的所有行所有列
train_data_org = train_data['train_set_x'][:]
train_labels_org = train_data['train_set_y'][:]
test_data_org = test_data['test_set_x'][:]
test_labels_org = test_data['test_set_y'][:]

#查看图片
import matplotlib.pyplot as plt
%matplotlib inline

#显示图片
plt.imshow(train_data_org[148])

#取出训练集和测试集
train_data_org = train_data['train_set_x'][:]
train_labels_org = train_data['train_set_y'][:]
test_data_org = test_data['test_set_x'][:]
test_labels_org = test_data['test_set_y'][:]

#查看图片
import matplotlib.pyplot as plt
%matplotlib inline

#显示图片
plt.imshow(train_data_org[130])

#数据维度的处理
m_train = train_data_org.shape[0]
m_test = test_data_org.shape[0]
train_data_tran = train_data_org.reshape(m_train,-1).T
test_data_tran = test_data_org.reshape(m_test,-1).T

print(train_data_tran.shape,test_data_tran.shape)

#导入numpy作矩阵处理
import numpy as np
train_labels_tran = train_labels_org[np.newaxis,:]
test_labels_tran = test_labels_org[np.newaxis,:]

#标准化数据到0-1范围内
train_data_sta = train_data_tran / 255
test_data_sta = test_data_tran / 255

#定义sigmoid函数
def sigmoid(z):
    a = 1 / (1 + np.exp(-z))
    return a

#初始化参数
n_dim = train_data_sta.shape[0]
w = np.zeros((n_dim,1))
b = 0

#定义前向传播函数，代价函数以及梯度下降
def propagate(w,b,X,y):

    #前向传播函数
    Z = np.dot(w.T,X) + b
    A = sigmoid(Z)
    
    #代价函数
    m = X.shape[1]
    J = -1 / m * np.sum(y * np.log(A) + (1-y) * np.log(1 - A))
    
    #梯度下降
    dw = 1 / m * np.dot(X,(A - y).T)
    db = 1 / m * np.sum(A - y)
    
    #dw和db放到字典
    grands = {'dw':dw,'db':db}
    
    return grands,J

#优化部分
def optimize(w,b,X,y,alpha,n_iters):
    costs = []
    for i in range(n_iters):
        grands,J =  propagate(w,b,X,y)
        dw = grands['dw']
        db = grands['db']
        
        w = w - alpha * dw
        b = b=alpha * db
        
        if i % 100 == 0:
            costs.append(J)
            print('n_iters is ',i,'costs is ',J)
    grands = {'dw':dw,'db':db}
    params = {'w':w,'b':b}
    
    return grands,params,costs

#预测部分
def predict(w,b,X_test):
    Z = np.dot(w.T,X_test) + b
    A = sigmoid(Z)
    
    m = X_test.shape[1]
    y_pred = np.zeros((1,m))
    
    for i in range(m):
        if A[:,i] > 0.5:
            y_pred[:,i] = 1
        else:
             y_pred[:,i] = 0
    return  y_pred

#模型整合
def model(w,b,X_train,y_train,X_test,y_test,alpha,n_iters):
    grands,params,costs = optimize(w,b,X_train,y_train,alpha,n_iters)
    w = params['w']
    b = params['b']
    y_pred_train = predict(w,b,X_train)
    y_pred_test = predict(w,b,X_test)
    
    print('the train acc is',np.mean( y_pred_train == y_train)*100,'%')
    print('the test acc is',np.mean( y_pred_test == y_test)*100,'%')
    
    b={
        
        'w' : w,
        'b' : b,
        'y_pred_train' : y_pred_train,
        'y_pred_test' : y_pred_test,
        'alpha' : alpha
    }
    
    return b

b = model(w,b,train_data_sta,train_labels_tran,test_data_sta,test_labels_tran,alpha = 0.005,n_iters = 2000)