Skip to content

callbacl fix #4

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
Matvezy merged 1 commit into from
Mar 20, 2025
Merged

callbacl fix #4

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
25 changes: 23 additions & 2 deletions rfdetr/util/misc.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -415,9 +415,30 @@ def is_main_process():
return get_rank() == 0


def save_on_master(*args, **kwargs):
def save_on_master(obj, f, *args, **kwargs):
"""
Safely save objects, removing any callbacks that can't be pickled
"""
if is_main_process():
torch.save(*args, **kwargs)
try:
if isinstance(obj, dict):
obj_copy = {}
for k, v in obj.items():
if k == 'args' and hasattr(v, '__dict__'):
args_dict = copy.copy(v.__dict__)
if 'callbacks' in args_dict:
del args_dict['callbacks']
obj_copy[k] = argparse.Namespace(**args_dict)
elif k != 'callbacks':
obj_copy[k] = v
obj = obj_copy

torch.save(obj, f, *args, **kwargs)
except Exception as e:
print(f"Error in safe_save_on_master: {e}")
if isinstance(obj, dict) and 'model' in obj:
print("Falling back to saving only model state_dict")
torch.save({'model': obj['model']}, f, *args, **kwargs)


def init_distributed_mode(args):
Expand Down