Fix NMS box format comment from xyxy to xywh (#20376)

Signed-off-by: Glenn Jocher <glenn.jocher@ultralytics.com>
Co-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com>
This commit is contained in:
nikenake1 2025-04-27 17:07:17 +08:00 committed by GitHub
parent a496589758
commit 7b324694e9
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
2 changed files with 2 additions and 2 deletions

View file

@ -108,7 +108,7 @@ solutions = [
"streamlit>=1.29.0,<1.44.0", # for live inference on web browser, i.e `yolo streamlit-predict`
]
logging = [
"wandb", # https://docs.ultralytics.com/integrations/comet/
"wandb", # https://docs.ultralytics.com/integrations/weights-biases/
"tensorboard", # https://docs.ultralytics.com/integrations/tensorboard/
"mlflow", # https://docs.ultralytics.com/integrations/mlflow/
]

View file

@ -213,7 +213,7 @@ def non_max_suppression(
multi_label (bool): If True, each box may have multiple labels.
labels (List[List[Union[int, float, torch.Tensor]]]): A list of lists, where each inner
list contains the apriori labels for a given image. The list should be in the format
output by a dataloader, with each label being a tuple of (class_index, x1, y1, x2, y2).
output by a dataloader, with each label being a tuple of (class_index, x, y, w, h).
max_det (int): The maximum number of boxes to keep after NMS.
nc (int): The number of classes output by the model. Any indices after this will be considered masks.
max_time_img (float): The maximum time (seconds) for processing one image.