标签：some als one set highlight for back weight div
1. requires_grad = False
Set all parameters in the current model frozen:
for p in self.parameters():
p.requires_grad = False
Filter some specific layers by name to be frozen:
for n, m in self.named_modules():
if ‘stc‘ not in n:
for p in m.parameters():
p.requires_grad = False
else:
for p in m.parameters():
p.requires_grad = True
2. Filter out unfrozen parameters, pass it to the optimizer
if args.freeze_backbone_update:
optimizer = torch.optim.SGD(filter(lambda para: para.requires_grad, org_model.parameters()),
args.lr,
momentum=args.momentum,
weight_decay=args.weight_decay)
else:
optimizer = torch.optim.SGD(org_model.parameters(),
args.lr,
momentum=args.momentum,
weight_decay=args.weight_decay)
Freeze partial parameters while training
标签：some als one set highlight for back weight div
原文地址：https://www.cnblogs.com/hizhaolei/p/10624196.html
