lecture04反向传播
课程网址

Pytorch深度学习实践

部分课件内容：

import torchx_data =[1.0,2.0,3.0]
y_data =[2.0,4.0,6.0]
w = torch.tensor([1.0])
w.requires_grad = Truedef forward(x):return x*wdef loss(x,y):y_pred = forward(x)return (y_pred-y)**2print('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