《PyTorch深度学习实践》P4反向传播

code:

import torch

x_data = [1.0, 2.0, 3.0]
y_data = [2.0, 4.0, 6.0]

w = torch.Tensor([1.0])
w.requires_grad = True # Ture：需要计算梯度

def forward(x):
    return x * w # 不是做简单乘法，而是在构建计算图

def loss(x, y):
    y_pred = forward(x)
    return (y_pred - y) ** 2
print('Predict(before training)', 4, forward(4))

for epoch in range(100):
    for x, y in zip(x_data, y_data):
        l = loss(x, y) # forward 计算loss
        l.backward() # 自动计算，把梯度存到w里面
        print('\tgrad:', x, y, w.grad.item())
        w.data = w.data - 0.01 * w.grad.data # 权重更新时不适用张量，因为不想再构建计算图，求梯度，只需要数值更新，即data

        w.grad.data.zero_() # 梯度清零
    print("process:", epoch, l.item())
print('Predict(after training)', 4, forward(4))

效果：