PyTorch实现—Logistic回归，loss和acc可视化

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

viz = visdom.Visdom(env='train')
loss_win = viz.line(np.arange(0.8))
acc_win = viz.line(np.arange(0.8))

#从data.txt读取数据
with open('data.txt','r') as f:
    data_list = f.readlines()
    data_list = [i.split('\n')[0] for i in data_list]
    data_list = [i.split(',') for i in data_list]
    data = [(float(i[0]),float(i[1]),float(i[2])) for i in data_list]
    x_data = np.array([(float(i[0]),float(i[1])) for i in data_list])
    y_data = np.array([[(float(i[2]))] for i in data_list])
    
x0 = list(filter(lambda x :x[-1] == 0.0,data))
x1 = list(filter(lambda x :x[-1] == 1.0,data))

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]

#plt.plot(plot_x0_0,plot_x0_1,'ro',label='x_0')
#plt.plot(plot_x1_0,plot_x1_1,'bo',label='x_0')
#plt.show()

#获取训练数据
x = torch.from_numpy(x_data).float()
#y = torch.from_numpy(y_data)
y = torch.FloatTensor(y_data)
#print(x.size())
#print(y)
#定义模型
class logisticRegression(nn.Module):
    def __init__(self):
        super().__init__()
        self.line = nn.Linear(2,1)
        self.smd = nn.Sigmoid()
        
    def forward(self,x):
        x = self.line(x)
        return self.smd(x) 
    
logistic_model = logisticRegression()

criterion = nn.BCELoss()
optimizer = torch.optim.SGD(logistic_model.parameters(),lr = 1e-3)

for epoch in range(80000):
    x = Variable(x)
    
    y = Variable(y)
    #print('****')
    #print(x)
    
    #==========forward=========
    out = logistic_model(x)
    
    loss = criterion(out,y)
    print_loss = loss.item()    
    #判断输出结果大于0.5就等于1，小于0.5就等于0
    #通过这个来计算模型分类的准确率
    mask = out.ge(0.5).float() 
    correct = (mask == y).sum()
    acc = correct.item()/x.size(0)
    #==========backward========
    optimizer.zero_grad()
    loss.backward()
    optimizer.step()
    
    if(epoch + 1) % 100 == 0:
        print('*'*10)
        print('epoch{}'.format(epoch+1))
        print('loss is {:.4f}'.format(print_loss))
        print('acc is {:.4f}'.format(acc))
        viz.line(Y=np.array([print_loss]), X=np.array([epoch+1]), update='append', opts={'title':'loss'}, win=loss_win)
        viz.line(Y=np.array([acc]), X=np.array([epoch+1]), update='append', opts={'title':'acc'}, win=acc_win)
        
weight = logistic_model.line.weight.data[0]
w0, w1 = weight[0], weight[1]
b = logistic_model.line.bias.data[0]
plt.plot(plot_x0_0,plot_x0_1,'ro',label='x_0')
plt.plot(plot_x1_0,plot_x1_1,'bo',label='x_0')
plt.legend(loc = 'best')
plot_x = torch.from_numpy(np.arange(30, 100, 0.1))
plot_y = (-w0 * plot_x - b) / w1
plt.plot(plot_x, plot_y)
plt.show()

 

 

本次实验分别测试训练60000次和80000的效果，以上loss和acc是训练60000之后的可视化数据图。训练80000次之后可视化效果更明显。