smart_optimizer() revert to weight with decay (#9817)

If a parameter does not fall into any other category

Signed-off-by: Glenn Jocher <glenn.jocher@ultralytics.com>

Signed-off-by: Glenn Jocher <glenn.jocher@ultralytics.com>
This commit is contained in:
Glenn Jocher 2022-10-16 20:51:32 +02:00 committed by GitHub
parent df80e7c723
commit e42c89d4ef
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23

View File

@ -319,12 +319,13 @@ def smart_optimizer(model, name='Adam', lr=0.001, momentum=0.9, decay=1e-5):
g = [], [], [] # optimizer parameter groups
bn = tuple(v for k, v in nn.__dict__.items() if 'Norm' in k) # normalization layers, i.e. BatchNorm2d()
for v in model.modules():
if hasattr(v, 'bias') and isinstance(v.bias, nn.Parameter): # bias (no decay)
g[2].append(v.bias)
if isinstance(v, bn): # weight (no decay)
g[1].append(v.weight)
elif hasattr(v, 'weight') and isinstance(v.weight, nn.Parameter): # weight (with decay)
g[0].append(v.weight)
for p_name, p in v.named_parameters(recurse=0):
if p_name == 'bias': # bias (no decay)
g[2].append(p)
elif p_name == 'weight' and isinstance(v, bn): # weight (no decay)
g[1].append(p)
else:
g[0].append(p) # weight (with decay)
if name == 'Adam':
optimizer = torch.optim.Adam(g[2], lr=lr, betas=(momentum, 0.999)) # adjust beta1 to momentum