笔记-b站刘二大人《pytorch深度学习实践》-第四讲

第四讲-反向传播

y=x*w

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

def forward(x):
    return x * w

def loss(x,y):
    y_pred = forward(x)
    return (y-y_pred)** 2

print('predict (before training)',4,forward(4).item())

for epoch in range(100):
    for x,y in zip(x_data,y_data):
        l=loss(x,y)
        l.backward()
        print('\tgrad:',x,y,w.grad.item())
        w.data = w.data - 0.01 *w.grad.data

        w.grad.data.zero_()   #后向传播会计算grad，因此更新完后要重新置零
    print('progress:',epoch,l.item())
print('predict(after training)',4,forward(4).item())

y=w1*x^2+w2*x+b

import torch

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

w1 = torch.tensor([1.0])
w2 = torch.tensor([1.0])
b = torch.tensor([-2.0])
w1.requires_grad = True
w2.requires_grad = True
b.requires_grad = True

def forward(x):
    return x* x * w1 + w2 * x + b

def loss(x,y):
    y_pred = forward(x)
    return (y-y_pred) ** 2

print('predict (before training)',4,forward(4).item())

for epoch in range(100):
    for x,y in zip(x_data,y_data):
        l=loss(x,y)
        l.backward()
        print('\tgrad:',x,y,w1.grad.item(),w2.grad.item())
        w1.data = w1.data - 0.01 * w1.grad.data
        w2.data = w2.data - 0.01 * w2.grad.data
        b.data = b.data - 0.05 * b.grad.data

        w1.grad.data.zero_()   #后向传播会计算grad，因此更新完后要重新置零
        w2.grad.data.zero_()
        b.grad.data.zero_()
    print('progress:',epoch,l.item())
print('predict(after training)',4,forward(4).item())