• 课堂内容代码

# 逻辑斯蒂回归模型
import torch

x_data = torch.Tensor([[1.0], [2.0], [3.0]])
y_data = torch.Tensor([[0], [0], [1]])


# design model using class
class LogisticRegressionModel(torch.nn.Module):
    def __init__(self):
        super(LogisticRegressionModel, self).__init__()
        self.linear = torch.nn.Linear(1, 1)

    def forward(self, x):
        # 线性回归之后利用sigmoid函数使输出在[0,1]之间
        y_pred = torch.nn.functional.sigmoid(self.linear(x))
        # y_pred = torch.sigmoid(self.linear(x))
        # torch.sigmoid()是一个torch库中的函数，可以直接使用
        # torch.nn.Sigmoid()是torch.nn模块中的类，需要实例化为对象才能使用
        return y_pred


model = LogisticRegressionModel()

# 默认情况下，loss会基于element平均(reduction='mean')，如果reduction='sum'的话，loss会被累加。
criterion = torch.nn.BCELoss(reduction='sum')  # 二分类交叉熵损失
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()

print('w = ', model.linear.weight.item())
print('b = ', model.linear.bias.item())

x_test = torch.Tensor([[4.0]])
y_test = model(x_test)
print('y_pred = ', y_test.data)

• 结果