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

Jump to bottom

Pass LOCAL_RANK to torch_distributed_zero_first() #5114

Merged
merged 1 commit into from
Oct 10, 2021
Merged

Pass LOCAL_RANK to torch_distributed_zero_first() #5114

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
6 changes: 3 additions & 3 deletions train.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -99,7 +99,7 @@ def train(hyp, # path/to/hyp.yaml or hyp dictionary
plots = not evolve # create plots
cuda = device.type != 'cpu'
init_seeds(1 + RANK)
with torch_distributed_zero_first(RANK):
with torch_distributed_zero_first(LOCAL_RANK):
data_dict = data_dict or check_dataset(data) # check if None
train_path, val_path = data_dict['train'], data_dict['val']
nc = 1 if single_cls else int(data_dict['nc']) # number of classes
Expand All @@ -111,7 +111,7 @@ def train(hyp, # path/to/hyp.yaml or hyp dictionary
check_suffix(weights, '.pt') # check weights
pretrained = weights.endswith('.pt')
if pretrained:
with torch_distributed_zero_first(RANK):
with torch_distributed_zero_first(LOCAL_RANK):
weights = attempt_download(weights) # download if not found locally
ckpt = torch.load(weights, map_location=device) # load checkpoint
model = Model(cfg or ckpt['model'].yaml, ch=3, nc=nc, anchors=hyp.get('anchors')).to(device) # create
Expand Down Expand Up @@ -208,7 +208,7 @@ def train(hyp, # path/to/hyp.yaml or hyp dictionary

# Trainloader
train_loader, dataset = create_dataloader(train_path, imgsz, batch_size // WORLD_SIZE, gs, single_cls,
hyp=hyp, augment=True, cache=opt.cache, rect=opt.rect, rank=RANK,
hyp=hyp, augment=True, cache=opt.cache, rect=opt.rect, rank=LOCAL_RANK,
workers=workers, image_weights=opt.image_weights, quad=opt.quad,
prefix=colorstr('train: '))
mlc = int(np.concatenate(dataset.labels, 0)[:, 0].max()) # max label class
Expand Down