PyTorch深度学习实践06

Logistic Regression

逻辑回归但是做分类

import os
import os
os.environ["KMP_DUPLICATE_LIB_OK"]="TRUE"
import torch
import matplotlib.pyplot as plt
import torch.nn.functional as F
import numpy as np

x_data=torch.Tensor([[1.0],[2.0],[3.0]])
y_data=torch.Tensor([[0],[0],[1]])#二分类问题


class LogisticRegressionModel(torch.nn.Module):
    def __init__(self):
        super(LogisticRegressionModel, self).__init__()
        self.linear=torch.nn.Linear(1,1)#初始话w和b 实现xw+b
    def forward(self,x):
        y_pred=F.sigmoid(self.linear(x))
        return y_pred

model =LogisticRegressionModel()

criterion=torch.nn.BCELoss(size_average=False)
optimizer=torch.optim.SGD(model.parameters(),lr=0.01)

for epoch in range(1000):
    y_pre=model(x_data)#计算y_pre
    loss=criterion(y_pre,y_data)#计算loss
    print(epoch,loss.item())

    optimizer.zero_grad()#在backward之前先清零
    loss.backward()#求loss对w的导数
    optimizer.step()#更新w

x=np.linspace(0,10,200)#x轴  在0-10小时 取200个点
x_t=torch.Tensor(x).view((200,1))#变成200行 1列的矩阵 view相当于numpy中的reshape
y_t=model(x_t)#得到预测值 y_temp
y=y_t.data.numpy()
plt.plot(x,y)
plt.plot([0,10],[0.5,0.5],c='r')
plt.xlabel=('Hours')
plt.ylabel=('Probability of pass')
plt.grid()
plt.show()