《PyTorch深度学习实践》06 用PyTorch实现Logistic回归

1. 说明

本系列博客记录B站课程《PyTorch深度学习实践》的实践代码课程链接请点我

2. Pytorch写代码的一般逻辑

3. 代码

# ---------------------------
# @Time     : 2022/4/12 18:17
# @Author   : lcq
# @File     : Logistic_Regression.py
# @Function : PyTorch实现Logistic回归
# ---------------------------

import torch

# x,y是矩阵，3行1列 也就是说总共有3个样本，每个样本只有1个特征
x = torch.tensor([[1.0], [2.0], [3.0]])
y = torch.tensor([[0.0], [0.0], [1.0]])

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


# Step1: 创建模型
model = LogisticRegressionModel()

# Step2: 创建损失函数和优化器
Loss = torch.nn.BCELoss(size_average=True, reduction=True)
optimizer = torch.optim.SGD(params=model.parameters(), lr=0.01)


# Step3: 训练
for epoch in range(100):
    y_pred = model.forward(x)
    loss = Loss(y_pred, y)
    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)