pytorch余弦退火，learning rate 衰减

lr_scheduler = optim.lr_scheduler.CosineAnnealingLR(optimizer, T_max=5,eta_min=4e-08)

lr_scheduler.step()

官网:https://pytorch.org/docs/0.3.1/optim.html#torch.optim.lr_scheduler.CosineAnnealingLR

Example:

scheduler = optim.lr_scheduler.CosineAnnealingLR(optimizer, T_max=5,eta_min=4e-08)
for epoch in range(100):
scheduler.step()
train(…)
validate(…)

来源：CSDN

作者：orzchenyuming

链接：https://blog.csdn.net/qq_29936933/article/details/82755940