Skip to content

imagenet: add rank indicator to progress summary when distributed #551

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
hartb wants to merge 1 commit into
base: main
Choose a base branch
from
Open

imagenet: add rank indicator to progress summary when distributed #551

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
13 changes: 11 additions & 2 deletions imagenet/main.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -263,7 +263,7 @@ def train(train_loader, model, criterion, optimizer, epoch, args):
top1 = AverageMeter('Acc@1', ':6.2f')
top5 = AverageMeter('Acc@5', ':6.2f')
progress = ProgressMeter(len(train_loader), batch_time, data_time, losses, top1,
top5, prefix="Epoch: [{}]".format(epoch))
top5, prefix="Epoch: [{}]{}".format(epoch, rank_indicator(args)))

# switch to train mode
model.train()
Expand Down Expand Up @@ -306,7 +306,7 @@ def validate(val_loader, model, criterion, args):
top1 = AverageMeter('Acc@1', ':6.2f')
top5 = AverageMeter('Acc@5', ':6.2f')
progress = ProgressMeter(len(val_loader), batch_time, losses, top1, top5,
prefix='Test: ')
prefix='Test{}: '.format(rank_indicator(args)))

# switch to evaluate mode
model.eval()
Expand Down Expand Up @@ -348,6 +348,15 @@ def save_checkpoint(state, is_best, filename='checkpoint.pth.tar'):
shutil.copyfile(filename, 'model_best.pth.tar')


def rank_indicator(args):
if args.distributed:
digits = len(str(args.world_size))
indicator = '[{rank:{width}}]'.format(rank=args.rank, width=digits)
else:
indicator = ''
return indicator


class AverageMeter(object):
"""Computes and stores the average and current value"""
def __init__(self, name, fmt=':f'):
Expand Down