PyTorch 深度学习实践 第6讲 逻辑斯蒂回归

相较于之前只改了两个地方：

1. y值加上sigmoid
2. 损失函数改为交叉熵

import torch

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)
criterion = torch.nn.BCELoss(reduction='sum')
optimizer = torch.optim.SGD(model.parameters(), lr = 0.01)

for epoch in range(100000):
    y_pred = model(x_data)
    loss = criterion(y_pred, y_data)
    print("epoch:", epoch, "loss:", loss.item())
    
    optimizer.zero_grad()
    loss.backward()
    optimizer.step()
    
print("w:", model.linear.weight.item(), "b:", model.linear.bias.item())
    
print("when x = 4.0, y =", model(torch.tensor([[4.0]])).item())

画图

import matplotlib.pyplot as plt
import numpy as np

# x设置0到10，分成200个点
x = np.linspace(0, 10, 200)
# 此语句将生成200行1列的矩阵x
x_t = torch.Tensor(x).view((200, 1))
y_t = model(x_t)
y = y_t.data.numpy()
plt.plot(x, y)
plt.xlabel('Hours')
plt.ylabel('Probabilty of Pass')
plt.grid()
plt.show()