神经网络——优化器

1.优化器介绍：

优化器集中在torch.optim中。

• Constructing it

optimizer = optim.SGD(model.parameters(), lr=0.01, momentum=0.9)
optimizer = optim.Adam([var1, var2], lr=0.0001)

• Taking an optimization step

for input, target in dataset:
    optimizer.zero_grad()
    output = model(input)
    loss = loss_fn(output, target)
    loss.backward()
    optimizer