pytorch动态学习率

两种方法：

1. 手动改

for g in optim.param_groups:
    g['lr'] = 0.001

2. LambdaLR

torch.optim.lr_scheduler import LambdaLR
optimizer = torch.optim.SGD(model.parameters(), lr=0.1, momentum=0.9)
# Assuming optimizer has two groups.
lambda_group1 = lambda epoch: epoch // 30
lambda_group2 = lambda epoch: 0.95 ** epoch
scheduler = LambdaLR(optimizer, lr_lambda=[lambda1, lambda2])
for epoch in range(100):
    train(...)
    validate(...)
    scheduler.step()

具体可以参考：
stackoverflow