import torch
x_data = torch.Tensor([[1.0], [2.0], [3.0]])
y_data = torch.Tensor([[2.0], [4.0], [6.0]])
#x_data和y_data为三行一列的矩阵,即总共有三个数据,每个数据只有一个特征
class LinearModel(torch.nn.Module):
def __init__(self):
super(LinearModel,self).__init__()
self.linear = torch.nn.Linear(1,1)
#(1,1)指输入x和输出y的特征维度,此处数据集中x、y的特征都是一维的
#该线性层需要学习的参数是w和b,获取w、b的方式是linear.weight和linear.bias
def forward(self,x):
y_pred = self.linear(x)
return y_pred
model = LinearModel()
# criterion = torch.nn.MSELoss(reduction='sum')
criterion = torch.nn.MSELoss(size_average=False)
optimizer = torch.optim.SGD(model.parameters(),lr=0.01)
for epoch in range(100):
y_pred = model(x_data) #forward:predict
loss = criterion(y_pred,y_data) #forward:loss
print(epoch,loss.item())
optimizer.zero_grad() #将梯度置为零
loss.backward() #backward:autograd,自动计算梯度
optimizer.step() #update参数,即更新w、b的值
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)
12-29
4089
![](https://csdnimg.cn/release/blogv2/dist/pc/img/readCountWhite.png)
03-23
3035
![](https://csdnimg.cn/release/blogv2/dist/pc/img/readCountWhite.png)
“相关推荐”对你有帮助么?
-
非常没帮助
-
没帮助
-
一般
-
有帮助
-
非常有帮助
提交