24.11.2 pytorch-刘二大人

逻辑回归（logistical）

import torch
import torch.nn.functional as F

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

# 定义逻辑回归模型
class LogisticRegressionModel(torch.nn.Module):
    def __init__(self):  # 修正 _init_ 为 __init__
        super(LogisticRegressionModel, self).__init__()
        self.linear = torch.nn.Linear(1, 1)

    def forward(self, x):
        y_pred = torch.sigmoid(self.linear(x))  # 使用 torch.sigmoid 而非 F.sigmoid
        return y_pred

# 创建模型实例
model = LogisticRegressionModel()

# 定义损失函数和优化器
criterion = torch.nn.BCELoss(reduction='sum')  # 更新参数，size_average=False 改为 reduction='sum'
optimizer = torch.optim.SGD(model.parameters(), lr=0.01)

# 训练模型
for epoch in range(1000):
    # 前向传播
    y_pred = model(x_data)
    loss = criterion(y_pred, y_data)
    print(epoch, loss.item())

    # 后向传播和优化
    optimizer.zero_grad()
    loss.backward()
    optimizer.step()

回归=> y∈R 分类=> y∈{离散型}