skip_clean no longer needs to be passed explicitly to parsers

Author: dtronmans

luxonis_ml/data/parsers/base_parser.py

@@ -151,6 +151,7 @@ def parse_split(
         @rtype: LuxonisDataset
         @return: C{LDF} with all the images and annotations parsed.
         """
+        self.skip_clean = kwargs.pop("skip_clean", False)
         added_images = self._parse_split(**kwargs)
         if split is not None:
             self.dataset.make_splits({split: added_images})
@@ -169,6 +170,7 @@ def parse_dir(self, dataset_dir: Path, **kwargs) -> BaseDataset:
         @rtype: LuxonisDataset
         @return: C{LDF} with all the images and annotations parsed.
         """
+        self.skip_clean = kwargs.pop("skip_clean", False)
         train, val, test = self.from_dir(dataset_dir, **kwargs)
 
         self.dataset.make_splits({"train": train, "val": val, "test": test})

luxonis_ml/data/parsers/coco_parser.py

@@ -127,7 +127,6 @@ def from_dir(
         use_keypoint_ann: bool = False,
         keypoint_ann_paths: dict[str, str] | None = None,
         split_val_to_test: bool = True,
-        skip_clean: bool = False,
     ) -> tuple[list[Path], list[Path], list[Path]]:
         dir_format, splits = COCOParser._detect_dataset_dir_format(dataset_dir)
         if dir_format is None:
@@ -162,7 +161,9 @@ def from_dir(
             else train_paths["annotation_path"]
         )
         cleaned_annotation_path = (
-            train_ann_path if skip_clean else clean_annotations(train_ann_path)
+            train_ann_path
+            if self.skip_clean
+            else clean_annotations(train_ann_path)
         )
         added_train_imgs = self._parse_split(
             image_dir=train_paths["image_dir"],
@@ -235,7 +236,6 @@ def from_split(
         self,
         image_dir: Path,
         annotation_path: Path,
-        skip_clean: bool = False,
     ) -> ParserOutput:
         """Parses annotations from COCO format to LDF. Annotations
         include classification, segmentation, object detection and
@@ -245,16 +245,13 @@ def from_split(
         @param image_dir: Path to directory with images
         @type annotation_path: Path
         @param annotation_path: Path to annotation json file
-        @type skip_clean: bool
-        @param skip_clean: If C{True}, skip automatic cleaning of known
-            dataset issues. Defaults to C{False}.
         @rtype: L{ParserOutput}
         @return: Annotation generator, list of classes names, skeleton
             dictionary for keypoints and list of added images.
         """
         annotation_path = (
             annotation_path
-            if skip_clean
+            if self.skip_clean
             else clean_annotations(annotation_path)
         )
 

luxonis_ml/data/parsers/fiftyone_classification_parser.py

@@ -114,9 +114,7 @@ def _extract_native_classes(labels_path: Path) -> dict[int, str]:
         classes = labels_data.get("classes", [])
         return dict(enumerate(classes))
 
-    def from_split(
-        self, split_path: Path, skip_clean: bool = False
-    ) -> ParserOutput:
+    def from_split(self, split_path: Path) -> ParserOutput:
         labels_path = split_path / "labels.json"
         data_path = split_path / "data"
 
@@ -125,7 +123,7 @@ def from_split(
         # and label indices, and set native classes
         is_flat_structure = split_path.name not in self.SPLIT_NAMES
         if is_flat_structure:
-            if not skip_clean:
+            if not self.skip_clean:
                 labels_path = clean_imagenet_annotations(labels_path)
             native_classes = self._extract_native_classes(labels_path)
             if native_classes: