pytorch实现模型不同层设置不同的学习率方式

class net(torch.nn.Module):
  def __init__(self):
    super(net, self).__init__()
    # backbone
    self.backbOne= ...
    # detect
    self....

base_params = list(map(id, net.backbone.parameters()))
logits_params = filter(lambda p: id(p) not in base_params, net.parameters())
params = [
  {"params": logits_params, "lr": config.lr},
  {"params": net.backbone.parameters(), "lr": config.backbone_lr},
]
optimizer = torch.optim.SGD(params, momentum=config.momentum, weight_decay=config.weight_decay)