Skip to content

Update optimizer param group strategy #7376

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 2 commits into from
Apr 11, 2022
Merged

Update optimizer param group strategy #7376

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
be3c3a7
Update optimizer param group strategy
glenn-jocher Apr 11, 2022
83059a4
fix init
glenn-jocher Apr 11, 2022
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
22 changes: 11 additions & 11 deletions train.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -150,27 +150,27 @@ def train(hyp, opt, device, callbacks): # hyp is path/to/hyp.yaml or hyp dictio
hyp['weight_decay'] *= batch_size * accumulate / nbs # scale weight_decay
LOGGER.info(f"Scaled weight_decay = {hyp['weight_decay']}")

g0, g1, g2 = [], [], [] # optimizer parameter groups
g = [], [], [] # optimizer parameter groups
for v in model.modules():
if hasattr(v, 'bias') and isinstance(v.bias, nn.Parameter): # bias
g2.append(v.bias)
g[2].append(v.bias)
if isinstance(v, nn.BatchNorm2d): # weight (no decay)
g0.append(v.weight)
g[1].append(v.weight)
elif hasattr(v, 'weight') and isinstance(v.weight, nn.Parameter): # weight (with decay)
g1.append(v.weight)
g[0].append(v.weight)

if opt.optimizer == 'Adam':
optimizer = Adam(g0, lr=hyp['lr0'], betas=(hyp['momentum'], 0.999)) # adjust beta1 to momentum
optimizer = Adam(g[2], lr=hyp['lr0'], betas=(hyp['momentum'], 0.999)) # adjust beta1 to momentum
elif opt.optimizer == 'AdamW':
optimizer = AdamW(g0, lr=hyp['lr0'], betas=(hyp['momentum'], 0.999)) # adjust beta1 to momentum
optimizer = AdamW(g[2], lr=hyp['lr0'], betas=(hyp['momentum'], 0.999)) # adjust beta1 to momentum
else:
optimizer = SGD(g0, lr=hyp['lr0'], momentum=hyp['momentum'], nesterov=True)
optimizer = SGD(g[2], lr=hyp['lr0'], momentum=hyp['momentum'], nesterov=True)

optimizer.add_param_group({'params': g1, 'weight_decay': hyp['weight_decay']}) # add g1 with weight_decay
optimizer.add_param_group({'params': g2}) # add g2 (biases)
optimizer.add_param_group({'params': g[0], 'weight_decay': hyp['weight_decay']}) # add g0 with weight_decay
optimizer.add_param_group({'params': g[1]}) # add g1 (BatchNorm2d weights)
LOGGER.info(f"{colorstr('optimizer:')} {type(optimizer).__name__} with parameter groups "
f"{len(g0)} weight (no decay), {len(g1)} weight, {len(g2)} bias")
del g0, g1, g2
f"{len(g[1])} weight (no decay), {len(g[0])} weight, {len(g[2])} bias")
del g

# Scheduler
if opt.cos_lr:
Expand Down