YoloDataset Contains Misleading Variable Names

[jonasdieker]

Description

I am confused about the following method:

YOLO/yolo/tools/data_loader.py

Lines 60 to 70 in cdd9a11

	def filter_data(self, dataset_path: Path, phase_name: str) -> list:
	"""
	Filters and collects dataset information by pairing images with their corresponding labels.
	Parameters:
	images_path (Path): Path to the directory containing image files.
	labels_path (str): Path to the directory containing label files.
	Returns:
	list: A list of tuples, each containing the path to an image file and its associated segmentation as a tensor.
	"""

My impression is that this is a general dataset, yet it seems to only load segmentations and no bboxes, judging from the docstring and variable names.
However, the following method, which does the actual loading seems to talk about bboxes again, even though the argument is clearly called seg_data_one_img:

YOLO/yolo/tools/data_loader.py

Lines 110 to 112 in cdd9a11

	def load_valid_labels(self, label_path: str, seg_data_one_img: list) -> Union[Tensor, None]:
	"""
	Loads and validates bounding box data is [0, 1] from a label file.

[nkinnaird]

I think it's just a language/translation thing, and it does load bboxes as you say (and maybe can load segmentation masks with the right config, but I haven't tested that or looked into it).