Skip to content

Modified misleading num_classes Warnings #261

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
wants to merge 4 commits into
base: develop
Choose a base branch
from
Open

Modified misleading num_classes Warnings #261

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
afec066
Modify num_classes Warnings
panagiotamoraiti Jul 15, 2025
468ab29
Modify num_classes - subtract 1
panagiotamoraiti Jul 15, 2025
8de3983
Modify num_classes - don't subtract 1 - label ids should start from 0
panagiotamoraiti Jul 15, 2025
58c20e4
Merge branch 'develop' into develop
panagiotamoraiti Oct 3, 2025
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
3 changes: 3 additions & 0 deletions rfdetr/detr.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -139,6 +139,9 @@ def train_from_config(self, config: TrainConfig, **kwargs):
raise ValueError(f"Invalid dataset file: {config.dataset_file}")

if self.model_config.num_classes != num_classes:
logger.warning(
f"Reinitializing your detection head with {num_classes} classes."
)
self.model.reinitialize_detection_head(num_classes)

train_config = config.dict()
Expand Down
3 changes: 3 additions & 0 deletions rfdetr/main.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -100,6 +100,9 @@ def __init__(self, **kwargs):

checkpoint_num_classes = checkpoint['model']['class_embed.bias'].shape[0]
if checkpoint_num_classes != args.num_classes + 1:
logger.warning(
f"Reinitializing detection head with {checkpoint_num_classes} classes"
)
self.reinitialize_detection_head(checkpoint_num_classes)
# add support to exclude_keys
# e.g., when load object365 pretrain, do not load `class_embed.[weight, bias]`
Expand Down