pytorch学习之回归分类

引用库

import matplotlib.pyplot as plt
import torch
import torch.nn as nn
import torch.optim as optim
from torch.autograd import Variable
import numpy as np

数据导出

with open("G:\大四\pytorch学习\learning_pyTorch_with_SherlockLiao-master\Chapter_3\logistRegression/data.txt",'r') as f:
    # 读每行数据
    data_list = f.readlines()
    # 通过换行分割数据
    data_list = [i.split('\n')[0] for i in data_list]
    # 通过，分割数据![image.png](https://img.haomeiwen.com/i15573329/3e616f8ebe559e53.png?imageMogr2/auto-orient/strip%7CimageView2/2/w/1240)

    data_list = [i.split(',') for i in data_list]  
    # 获得数据中[0],[1],[2]的数据
    data = [(float(i[0]),float(i[1]),float(i[2])) for i in data_list]

数据展示

# 获得标记为0的点坐标
x0 = list(filter(lambda x:x[-1] == 0.0 ,data))
# 获得标记为1的点坐标
x1 = list(filter(lambda x:x[-1] == 1.0 ,data))

# 分别获得点坐标的x和y轴
plot_x0_0 = [i[0] for i in x0]
plot_x0_1 = [i[1] for i in x0]
plot_x1_0 = [i[0] for i in x1]
plot_x1_1 = [i[1] for i in x1]

# 显示
plt.plot(plot_x0_0,plot_x0_1,'ro',label='x_0',color="blue")
plt.plot(plot_x1_0,plot_x1_1,'ro',label='x_1')
plt.legend(loc='best')

image.png

获得数据

# 分别获得标注为0和1的数据的点坐标（x,y)
label0 = np.array([(float(row[0]), float(row[1])) for row in data if row[2] == 0])
label1 = np.array([(float(row[0]), float(row[1])) for row in data if row[2] == 1])

# 将点坐标合并连接起来
x = np.concatenate((label0,label1), axis = 0)
x_data = torch.from_numpy(x).float()

# 分别获得对应的标注（既0或者1，将其连接起来）
y = [[0] for i in range(label0.shape[0])]
y += [[1] for i in range(label1.shape[0])]
y_data = torch.FloatTensor(y)

设置模型

# 建立回归模型
class LogisticRegression(nn.Module):
    # 建立一层线程神经网络层和激活函数
    def __init__(self):
        super().__init__()
        self.lr = nn.Linear(2, 1)
        self.sm = nn.Sigmoid()
    
    # 前向传播，通过学习率和sigmod函数激活x    
    def forward(self,x):
        x = self.lr(x)
        x = self.sm(x)
        return x

# 建立模型对象    
logistic_model = LogisticRegression()
if torch.cuda.is_available():
    logistic_model.cuda()

设置损失函数和优化器

# 交叉熵损失函数
criterion = nn.BCELoss()
# 带动量的随机梯度下降优化器
optimizer = torch.optim.SGD(logistic_model.parameters(),lr=1e-3,momentum=0.9)

image.png

模型训练

# 训练50000次
for epoch in range(50000):
    # 将数据转换为tensor变量
    if torch.cuda.is_available():
        x = Variable(x_data).cuda()
        y = Variable(y_data).cuda()
    else:
        x = Variable(x_data)
        y = Variable(y_data)
    
    # 向前传播，计算输出及损失函数
    out = logistic_model(x)
    loss = criterion(out,y) 
    print_loss = loss.data[0]
    
    # 判断输出结果如果大于0.5就等于1，小于0.5就等于0
    mask = out.ge(0.5).float()
    correct = (mask==y).sum()
    acc = correct.data[0].item()/ x.size(0)
    
    # 反向传播
    optimizer.zero_grad()
    loss.backward()
    optimizer.step()
    if (epoch+1) %1000 ==0:
        print('*'*10)
        print('epoch {}'.format(epoch+1))
        print('loss is {:.4f}'.format(print_loss))
        print('acc is {:.4f}'.format(acc))
        

可视化分类结果

# 获得权值
weight = logistic_model.lr.weight[0]
w0, w1 = weight[0], weight[1]
b = logistic_model.lr.bias.data[0]

plt.plot(plot_x0_0,plot_x0_1,'ro',label='x_0',color="blue")
plt.plot(plot_x1_0,plot_x1_1,'ro',label='x_1')
plt.legend(loc = 'best')
plot_x = np.arange(30, 100, 0.1)
plot_y = (-w0.item() * plot_x - b.item()) / w1.item()
plt.plot(plot_x, plot_y)
plt.show()

image.png

总结

本实验是训练一个线性回归分类问题
目的是为了训练
    w0*x + w1*y + b =0

则
   y = (-w0*x-b)/w1