Skip to content
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

Load weights on segmentation/train.py when using --resume and --test-only flags #3285

Merged
merged 2 commits into from
Jan 25, 2021
Merged

Load weights on segmentation/train.py when using --resume and --test-only flags #3285

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
3b7c1be
Load variables when --resume /path/to/checkpoint --test-only
datumbox Jan 24, 2021
b02857c
Merge branch 'master' into bugfix/segmentation_testonly
fmassa Jan 25, 2021
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
19 changes: 10 additions & 9 deletions references/segmentation/train.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -133,11 +133,6 @@ def main(args):
model = torch.nn.parallel.DistributedDataParallel(model, device_ids=[args.gpu])
model_without_ddp = model.module

if args.test_only:
confmat = evaluate(model, data_loader_test, device=device, num_classes=num_classes)
print(confmat)
return

params_to_optimize = [
{"params": [p for p in model_without_ddp.backbone.parameters() if p.requires_grad]},
{"params": [p for p in model_without_ddp.classifier.parameters() if p.requires_grad]},
Expand All @@ -155,10 +150,16 @@ def main(args):

if args.resume:
checkpoint = torch.load(args.resume, map_location='cpu')
model_without_ddp.load_state_dict(checkpoint['model'])
optimizer.load_state_dict(checkpoint['optimizer'])
lr_scheduler.load_state_dict(checkpoint['lr_scheduler'])
args.start_epoch = checkpoint['epoch'] + 1
model_without_ddp.load_state_dict(checkpoint['model'], strict=not args.test_only)
Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

strict=False required to avoid having to configure auxiliary classifiers

if not args.test_only:
optimizer.load_state_dict(checkpoint['optimizer'])
Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

We avoid loading the weights of other objects if in test-only mode. Similar to the above, this is done to avoid having to handle auxiliary classifiers.

lr_scheduler.load_state_dict(checkpoint['lr_scheduler'])
args.start_epoch = checkpoint['epoch'] + 1

if args.test_only:
confmat = evaluate(model, data_loader_test, device=device, num_classes=num_classes)
print(confmat)
return

start_time = time.time()
for epoch in range(args.start_epoch, args.epochs):
Expand Down