Made all the changes requested

Author: SakhinetiPraveena

app.py

@@ -6,7 +6,12 @@
 from detectionmetrics.datasets.detection import ImageDetectionDataset
 
 
-def build_coco_dataset(annotation_file: str, image_dir: str, coco_obj: Optional[COCO] = None) -> Tuple[pd.DataFrame, dict]:
+def build_coco_dataset(
+    annotation_file: str,
+    image_dir: str,
+    coco_obj: Optional[COCO] = None,
+    split: str = "train",
+) -> Tuple[pd.DataFrame, dict]:
     """Build dataset and ontology dictionaries from COCO dataset structure
 
     :param annotation_file: Path to the COCO-format JSON annotation file
@@ -15,41 +20,47 @@ def build_coco_dataset(annotation_file: str, image_dir: str, coco_obj: Optional[
     :type image_dir: str
     :param coco_obj: Optional pre-loaded COCO object to reuse
     :type coco_obj: COCO
+    :param split: Dataset split name (e.g., "train", "val", "test")
+    :type split: str
     :return: Dataset DataFrame and ontology dictionary
     :rtype: Tuple[pd.DataFrame, dict]
     """
     # Check that provided paths exist
-    assert os.path.isfile(annotation_file), f"Annotation file not found: {annotation_file}"
+    assert os.path.isfile(
+        annotation_file
+    ), f"Annotation file not found: {annotation_file}"
     assert os.path.isdir(image_dir), f"Image directory not found: {image_dir}"
 
     # Load COCO annotations (reuse if provided)
     if coco_obj is None:
         coco = COCO(annotation_file)
     else:
         coco = coco_obj
-    
+
     # Build ontology from COCO categories
     ontology = {}
     for cat in coco.loadCats(coco.getCatIds()):
         ontology[cat["name"]] = {
             "idx": cat["id"],
             # "name": cat["name"],
-            "rgb": [0, 0, 0]  # Placeholder; COCO doesn't define RGB colors
+            "rgb": [0, 0, 0],  # Placeholder; COCO doesn't define RGB colors
         }
 
     # Build dataset DataFrame from COCO image IDs
     rows = []
     for img_id in coco.getImgIds():
         img_info = coco.loadImgs(img_id)[0]
-        rows.append({
-            "image": img_info["file_name"],
-            "annotation": str(img_id),
-            "split": "train"  # Default split - could be enhanced to read from COCO
-        })
-    
+        rows.append(
+            {
+                "image": img_info["file_name"],
+                "annotation": str(img_id),
+                "split": split,  # Use provided split parameter
+            }
+        )
+
     dataset = pd.DataFrame(rows)
     dataset.attrs = {"ontology": ontology}
-    
+
     return dataset, ontology
 
 
@@ -61,26 +72,36 @@ class CocoDataset(ImageDetectionDataset):
     :type annotation_file: str
     :param image_dir: Path to the directory containing image files
     :type image_dir: str
+    :param split: Dataset split name (e.g., "train", "val", "test")
+    :type split: str
     """
-    def __init__(self, annotation_file: str, image_dir: str):
+
+    def __init__(self, annotation_file: str, image_dir: str, split: str = "train"):
         # Load COCO object once
         self.coco = COCO(annotation_file)
         self.image_dir = image_dir
-        
-        # Build dataset using the same COCO object
-        dataset, ontology = build_coco_dataset(annotation_file, image_dir, self.coco)
-        
+        self.split = split
+
+        # Build dataset using the same COCO object and split
+        dataset, ontology = build_coco_dataset(
+            annotation_file, image_dir, self.coco, split=split
+        )
+
         super().__init__(dataset=dataset, dataset_dir=image_dir, ontology=ontology)
 
-    def read_annotation(self, fname: str) -> Tuple[List[List[float]], List[int], List[int]]:
+    def read_annotation(
+        self, fname: str
+    ) -> Tuple[List[List[float]], List[int], List[int]]:
         """Return bounding boxes, labels, and category_ids for a given image ID.
 
         :param fname: str (image_id in string form)
         :return: Tuple of (boxes, labels, category_ids)
         """
         # Extract image ID (fname might be a path or ID string)
         try:
-            image_id = int(os.path.basename(fname))  # handles both '123' and '/path/to/123'
+            image_id = int(
+                os.path.basename(fname)
+            )  # handles both '123' and '/path/to/123'
         except ValueError:
             raise ValueError(f"Invalid annotation ID: {fname}")
 
@@ -99,4 +120,3 @@ def read_annotation(self, fname: str) -> Tuple[List[List[float]], List[int], Lis
             category_ids.append(ann["category_id"])
 
         return boxes, labels, category_ids
-

detectionmetrics/datasets/coco.py

@@ -13,6 +13,7 @@
 import detectionmetrics.utils.io as uio
 import detectionmetrics.utils.conversion as uc
 
+
 class DetectionDataset(PerceptionDataset):
     """Abstract perception detection dataset class."""
 
@@ -23,7 +24,7 @@ def read_annotation(self, fname: str):
         :param fname: Annotation file name
         """
         raise NotImplementedError
-    
+
     def get_label_count(self, splits: Optional[List[str]] = None):
         """Count detection labels per class for given splits.
 
@@ -40,7 +41,9 @@ def get_label_count(self, splits: Optional[List[str]] = None):
         for annotation_file in tqdm(df["annotation"], desc="Counting labels"):
             annots = self.read_annotation(annotation_file)
             for annot in annots:
-                class_idx = annot["category_id"]  #Should override the key category_id if needed in specific dataset class
+                class_idx = annot[
+                    "category_id"
+                ]  # Should override the key category_id if needed in specific dataset class
                 label_count[class_idx] += 1
 
         return label_count
@@ -58,7 +61,7 @@ def make_fname_global(self):
             self.dataset["annotation"] = self.dataset["annotation"].apply(
                 lambda x: os.path.join(self.dataset_dir, x) if x is not None else None
             )
-            self.dataset_dir = None  
+            self.dataset_dir = None
 
     def read_annotation(self, fname: str):
         """Read detection annotation from a file.
@@ -75,7 +78,13 @@ def read_annotation(self, fname: str):
 class LiDARDetectionDataset(DetectionDataset):
     """LiDAR detection dataset class."""
 
-    def __init__(self, dataset: pd.DataFrame, dataset_dir: str, ontology: dict, is_kitti_format: bool = True):
+    def __init__(
+        self,
+        dataset: pd.DataFrame,
+        dataset_dir: str,
+        ontology: dict,
+        is_kitti_format: bool = True,
+    ):
         super().__init__(dataset, dataset_dir, ontology)
         self.is_kitti_format = is_kitti_format
 
@@ -98,4 +107,4 @@ def read_annotation(self, fname: str):
         :return: Parsed annotations (e.g., list of dicts)
         """
         # TODO Implement format specific parsing
-        raise NotImplementedError("Implement LiDAR detection annotation reading")
+        raise NotImplementedError("Implement LiDAR detection annotation reading")

detectionmetrics/datasets/detection.py

@@ -57,7 +57,10 @@ def append(self, new_dataset: Self):
                     self.ontology[class_name]["idx"]
                     == new_dataset.ontology[class_name]["idx"]
                 ), "Ontologies don't match"
-                if "rgb" in self.ontology[class_name] and "rgb" in new_dataset.ontology[class_name]:
+                if (
+                    "rgb" in self.ontology[class_name]
+                    and "rgb" in new_dataset.ontology[class_name]
+                ):
                     assert (
                         self.ontology[class_name]["rgb"]
                         == new_dataset.ontology[class_name]["rgb"]

detectionmetrics/datasets/perception.py

@@ -73,7 +73,9 @@ def build_dataset(
     return dataset, ontology
 
 
-class Rellis3DImageSegmentationDataset(dm_segmentation_dataset.ImageSegmentationDataset):
+class Rellis3DImageSegmentationDataset(
+    dm_segmentation_dataset.ImageSegmentationDataset
+):
     """Specific class for Rellis3D-styled image segmentation datasets. All data can
     be downloaded from the official repo (https://github.com/unmannedlab/RELLIS-3D):
     images   -> https://drive.google.com/file/d/1F3Leu0H_m6aPVpZITragfreO_SGtL2yV
@@ -105,7 +107,9 @@ def __init__(self, dataset_dir: str, split_dir: str, ontology_fname: str):
         super().__init__(dataset, dataset_dir, ontology)
 
 
-class Rellis3DLiDARSegmentationDataset(dm_segmentation_dataset.LiDARSegmentationDataset):
+class Rellis3DLiDARSegmentationDataset(
+    dm_segmentation_dataset.LiDARSegmentationDataset
+):
     """Specific class for Rellis3D-styled LiDAR segmentation datasets. All data can
     be downloaded from the official repo (https://github.com/unmannedlab/RELLIS-3D):
     points   -> https://drive.google.com/file/d/1lDSVRf_kZrD0zHHMsKJ0V1GN9QATR4wH

detectionmetrics/datasets/rellis3d.py

@@ -13,6 +13,7 @@
 import detectionmetrics.utils.io as uio
 import detectionmetrics.utils.conversion as uc
 
+
 class SegmentationDataset(PerceptionDataset):
     """Abstract perception dataset class."""
 
@@ -383,4 +384,3 @@ def read_label(fname: str) -> Tuple[np.ndarray, np.ndarray]:
         semantic_label = label & 0xFFFF
         instance_label = label >> 16
         return semantic_label.astype(np.int32), instance_label.astype(np.int32)
-

detectionmetrics/datasets/segmentation.py

@@ -123,7 +123,9 @@ def build_dataset(dataset_dir: str, split_fnames: dict) -> Tuple[dict, dict]:
     return dataset, ontology
 
 
-class WildscenesImageSegmentationDataset(dm_segmentation_dataset.ImageSegmentationDataset):
+class WildscenesImageSegmentationDataset(
+    dm_segmentation_dataset.ImageSegmentationDataset
+):
     """Specific class for Wildscenes-styled image segmentation datasets. All data can
     be downloaded from the official repo (https://github.com/unmannedlab/RELLIS-3D):
     dataset  -> https://data.csiro.au/collection/csiro:61541

detectionmetrics/datasets/wildscenes.py

@@ -12,6 +12,7 @@
 import detectionmetrics.utils.conversion as uc
 import detectionmetrics.utils.io as uio
 
+
 class DetectionModel(PerceptionModel):
     """Parent detection model class
 
@@ -38,9 +39,7 @@ def __init__(
         super().__init__(model, model_type, model_cfg, ontology_fname, model_fname)
 
     @abstractmethod
-    def inference(
-        self, data: Union[np.ndarray, Image.Image]
-    ) -> List[dict]:
+    def inference(self, data: Union[np.ndarray, Image.Image]) -> List[dict]:
         """Perform inference for a single input (image or point cloud)
 
         :param data: Input image or LiDAR point cloud
@@ -76,6 +75,7 @@ def eval(
         """
         raise NotImplementedError
 
+
 class ImageDetectionModel(DetectionModel):
     """Parent image detection model class
 
@@ -138,6 +138,7 @@ def eval(
         """
         raise NotImplementedError
 
+
 class LiDARDetectionModel(DetectionModel):
     """Parent LiDAR detection model class
 
@@ -198,4 +199,4 @@ def eval(
         :return: DataFrame containing evaluation metrics
         :rtype: pd.DataFrame
         """
-        raise NotImplementedError
+        raise NotImplementedError

detectionmetrics/models/detection.py

@@ -12,6 +12,7 @@
 import detectionmetrics.utils.conversion as uc
 import detectionmetrics.utils.io as uio
 
+
 class SegmentationModel(PerceptionModel):
     """Parent segmentation model class
 
@@ -201,4 +202,3 @@ def eval(
         :rtype: pd.DataFrame
         """
         raise NotImplementedError
-