代码
import torch
import torch.nn.functional as F
import numpy as np
import matplotlib.pyplot as plt
x_data=torch.Tensor([[1.0],[2.0],[3.0]])
y_data=torch.Tensor([[0],[0],[1]])
class LogisticRegressionModel(torch.nn.Module):
def __init__(self):
super(LogisticRegressionModel,self).__init__()
self.linear=torch.nn.Linear(1,1)
def forward(self,x):
y_pred=F.sigmoid(self.linear(x))
return y_pred
model=LogisticRegressionModel()
criterion=torch.nn.BCELoss(size_average=False) #二元交叉熵损失
optimizer=torch.optim.SGD(model.parameters(),lr=0.01) #优化器是随机梯度下降
for epoch in range(1000):
y_pred=model(x_data)
loss=criterion(y_pred,y_data)
print(epoch,'loss=',loss.item())
optimizer.zero_grad() #权重归零
loss.backward() #自动求导
optimizer.step() #更新
p=torch.Tensor([[2.5]])
q=model(p)
print('Predict:hours=2.5 Probability of Pass:',q.data.item())
x=np.linspace(0,10,200)
#将x变换为200*1的向量
x_t=torch.Tensor(x).view((200,1)) #view相当于numpy里的reshape
y_t=model(x_t)
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()
运行结果