pytorch-tutorial，01-basics/pytorch_basics

生成向量

# Create tensors of shape (10, 3) and (10, 2).
x = torch.randn(10, 3)
y = torch.randn(10, 2)

构建网络结构

# Build a fully connected layer。线性，输入三个特征，输出两个特征
linear = nn.Linear(3, 2)

损失函数

# Build loss function and optimizer. uild loss function and optimizer. 均方损失函数，随机梯度下降法
criterion = nn.MSELoss()
optimizer = torch.optim.SGD(linear.parameters(), lr=0.01)

计算结果，比较误差

# Forward pass.
pred = linear(x)

# Compute loss.
loss = criterion(pred, y)

迭代

# Backward pass.
loss.backward()

optimizer.step()

算是完成了一个完整训练过程，后面再调整权值，重复训练即可。