pytorch学习2之逻辑回归

X_data = torch.Tensor([[1.0],[2.0],[3.0]])
Y_data = torch.Tensor([[0],[0],[1]])

#构建模型
class LogisticRegressionModel(torch.nn.Module):
    def __init__(self):
        super(LogisticRegressionModel,self).__init__()     #继承Module的父类
        self.linear = torch.nn.Linear(1,1)     
    
    def forward(self , x):
        y_pred = torch.sigmoid(self.linear(x))
        return y_pred
model = LogisticRegressionModel()
#构建损失函数
criterion = torch.nn.BCELoss(reduction='sum')
#构建优化器
optimizer = torch.optim.SGD(model.parameters(),lr = 0.01)
#训练模型
for epoch in range(1000): 
    y_pred = model(X_data)
    loss = criterion(y_pred, Y_data)
    print(epoch , loss.item())
    
    #梯度归零
    optimizer.zero_grad()
    loss.backward()
    #更新
    optimizer.step()
    

训练结果：

994 1.08380126953125
995 1.0832830667495728
996 1.0827655792236328
997 1.0822484493255615
998 1.0817