《PyTorch深度学习实践》06逻辑斯蒂回归

torchvision里面所存在的包

Logistic保证输出在0，1之间

又回归到分类。loss得变

BCELoss二分类的交叉熵损失函数

import torch
import matplotlib.pyplot as plt
import numpy as np


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 = torch.sigmoid(self.linear(x))
        return y_pred

model= LogisticRegressionModel()

criterion = torch.nn.BCELoss(size_average=False)  ##二分类交叉熵损失函数，可以使得0，0损失值小，1.1值小，1，0值大，0，1值大
optimizer = torch.optim.SGD(model.parameters(), lr=0.01)

for epoch in range(1000):
    y_pred = model(x_data)
    loss = criterion(y_pred, y_data)
    print(epoch,loss.item())
    optimizer.zero_grad()
    loss.backward()
    optimizer.step()


x= np.linspace(0, 10, 200)##numpy中在0到10中找200个点    ##一维向量
print("x",x)
x_t = torch.Tensor(x).view((200,1))   ##二维矩阵 200行1列
print("x_t",x_t)
y_t = model(x_t)
print("y_t",y_t)
y = y_t.data.numpy()
print("numpy--y_t",y_t)


plt.plot(x,y)
plt.xlabel("Hours")
plt.ylabel("概率结果")
plt.grid()
plt.show()