Skip to content

Feature/lr milestones #37

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

Open
JonnaMat wants to merge 2 commits into
base: master
Choose a base branch
from
Open

Feature/lr milestones #37

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
7b3ab53
add parser arg to set lr milestone for training
JonnaMat Mar 30, 2023
78a87f1
remove print statement from testing
JonnaMat Mar 30, 2023
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
4 changes: 3 additions & 1 deletion trainer.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -55,6 +55,8 @@
parser.add_argument('--save-every', dest='save_every',
help='Saves checkpoints at every specified number of epochs',
type=int, default=10)
parser.add_argument('--lr-milestones', default=[100, 150], nargs='+',
help='list of epoch indices for multi step learning rate scheduler', type=int)
best_prec1 = 0


Expand Down Expand Up @@ -118,7 +120,7 @@ def main():
weight_decay=args.weight_decay)

lr_scheduler = torch.optim.lr_scheduler.MultiStepLR(optimizer,
milestones=[100, 150], last_epoch=args.start_epoch - 1)
milestones=args.lr_milestones, last_epoch=args.start_epoch - 1)

if args.arch in ['resnet1202', 'resnet110']:
# for resnet1202 original paper uses lr=0.01 for first 400 minibatches for warm-up
Expand Down