lecture04反向传播
课程网址

Pytorch深度学习实践

部分课件内容：

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_pred-y)**2

print('Predicted(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.item()
        w.grad.zero_()
    print('Epoch:', epoch,'w:',w.item(), 'Loss:', l.item())

print('Predicted(after training)',4,forward(4).item())

pytorch的机制是动态计算图，
tensor里面既有data也有gradient