Skip to content

refactor: replace LambdaLR with PolynomialLR in segmentation training script #6405

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 1 commit into from
Aug 12, 2022
Merged

refactor: replace LambdaLR with PolynomialLR in segmentation training script #6405

Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
5 changes: 3 additions & 2 deletions references/segmentation/train.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -10,6 +10,7 @@
import utils
from coco_utils import get_coco
from torch import nn
from torch.optim.lr_scheduler import PolynomialLR
from torchvision.transforms import functional as F, InterpolationMode


Expand Down Expand Up @@ -184,8 +185,8 @@ def main(args):
scaler = torch.cuda.amp.GradScaler() if args.amp else None

iters_per_epoch = len(data_loader)
main_lr_scheduler = torch.optim.lr_scheduler.LambdaLR(
optimizer, lambda x: (1 - x / (iters_per_epoch * (args.epochs - args.lr_warmup_epochs))) ** 0.9
main_lr_scheduler = PolynomialLR(
optimizer, total_steps=iters_per_epoch * (args.epochs - args.lr_warmup_epochs), power=0.9
)

if args.lr_warmup_epochs > 0:
Expand Down