feat: add show_progress option to dataset loaders and savers

src/supervision/dataset/core.py

@@ -334,6 +334,7 @@ def as_pascal_voc(
         min_image_area_percentage: float = 0.0,
         max_image_area_percentage: float = 1.0,
         approximation_percentage: float = 0.0,
+        show_progress: bool = False,
     ) -> None:
         """
         Exports the dataset to PASCAL VOC format. This method saves the images
@@ -357,11 +358,13 @@ def as_pascal_voc(
             approximation_percentage: The percentage of
                 polygon points to be removed from the input polygon,
                 in the range [0, 1). Argument is used only for segmentation datasets.
+            show_progress: If `True`, display a progress bar while saving images.
         """
         if images_directory_path:
             save_dataset_images(
                 dataset=self,
                 images_directory_path=images_directory_path,
+                show_progress=show_progress,
             )
         if annotations_directory_path:
             Path(annotations_directory_path).mkdir(parents=True, exist_ok=True)
@@ -390,6 +393,7 @@ def from_pascal_voc(
         images_directory_path: str,
         annotations_directory_path: str,
         force_masks: bool = False,
+        show_progress: bool = False,
     ) -> DetectionDataset:
         """
         Creates a Dataset instance from PASCAL VOC formatted data.
@@ -400,6 +404,7 @@ def from_pascal_voc(
                 containing the PASCAL VOC XML annotations.
             force_masks: If True, forces masks to
                 be loaded for all annotations, regardless of whether they are present.
+            show_progress: If `True`, display a progress bar while loading images.
 
         Returns:
             A DetectionDataset instance containing
@@ -432,6 +437,7 @@ def from_pascal_voc(
             images_directory_path=images_directory_path,
             annotations_directory_path=annotations_directory_path,
             force_masks=force_masks,
+            show_progress=show_progress,
         )
 
         return DetectionDataset(
@@ -446,6 +452,7 @@ def from_yolo(
         data_yaml_path: str,
         force_masks: bool = False,
         is_obb: bool = False,
+        show_progress: bool = False,
     ) -> DetectionDataset:
         """
         Creates a Dataset instance from YOLO formatted data.
@@ -463,6 +470,7 @@ def from_yolo(
             is_obb: If True, loads the annotations in OBB format.
                 OBB annotations are defined as `[class_id, x, y, x, y, x, y, x, y]`,
                 where pairs of [x, y] are box corners.
+            show_progress: If `True`, display a progress bar while loading images.
 
         Returns:
             A DetectionDataset instance
@@ -496,6 +504,7 @@ def from_yolo(
             data_yaml_path=data_yaml_path,
             force_masks=force_masks,
             is_obb=is_obb,
+            show_progress=show_progress,
         )
         return DetectionDataset(
             classes=classes, images=image_paths, annotations=annotations
@@ -509,6 +518,7 @@ def as_yolo(
         min_image_area_percentage: float = 0.0,
         max_image_area_percentage: float = 1.0,
         approximation_percentage: float = 0.0,
+        show_progress: bool = False,
     ) -> None:
         """
         Exports the dataset to YOLO format. This method saves the
@@ -537,10 +547,13 @@ def as_yolo(
                 be removed from the input polygon, in the range [0, 1).
                 This is useful for simplifying the annotations.
                 Argument is used only for segmentation datasets.
+            show_progress: If `True`, display a progress bar while saving images.
         """
         if images_directory_path is not None:
             save_dataset_images(
-                dataset=self, images_directory_path=images_directory_path
+                dataset=self,
+                images_directory_path=images_directory_path,
+                show_progress=show_progress,
             )
         if annotations_directory_path is not None:
             save_yolo_annotations(
@@ -559,6 +572,7 @@ def from_coco(
         images_directory_path: str,
         annotations_path: str,
         force_masks: bool = False,
+        show_progress: bool = False,
     ) -> DetectionDataset:
         """
         Creates a Dataset instance from COCO formatted data.
@@ -570,6 +584,7 @@ def from_coco(
             force_masks: If True,
                 forces masks to be loaded for all annotations,
                 regardless of whether they are present.
+            show_progress: If `True`, display a progress bar while loading images.
         Returns:
             A DetectionDataset instance containing
                 the loaded images and annotations.
@@ -599,6 +614,7 @@ def from_coco(
             images_directory_path=images_directory_path,
             annotations_path=annotations_path,
             force_masks=force_masks,
+            show_progress=show_progress,
         )
         return DetectionDataset(classes=classes, images=images, annotations=annotations)
 
@@ -609,6 +625,7 @@ def as_coco(
         min_image_area_percentage: float = 0.0,
         max_image_area_percentage: float = 1.0,
         approximation_percentage: float = 0.0,
+        show_progress: bool = False,
     ) -> None:
         """
         Exports the dataset to COCO format. This method saves the
@@ -645,10 +662,13 @@ def as_coco(
                 to be removed from the input polygon,
                 in the range [0, 1). This is useful for simplifying the annotations.
                 Argument is used only for segmentation datasets.
+            show_progress: If `True`, display a progress bar while saving images.
         """
         if images_directory_path is not None:
             save_dataset_images(
-                dataset=self, images_directory_path=images_directory_path
+                dataset=self,
+                images_directory_path=images_directory_path,
+                show_progress=show_progress,
             )
         if annotations_path is not None:
             save_coco_annotations(

src/supervision/dataset/formats/coco.py

@@ -6,6 +6,7 @@
 
 import numpy as np
 import numpy.typing as npt
+from tqdm.auto import tqdm
 
 from supervision.dataset.utils import (
     approximate_mask_with_polygons,
@@ -254,6 +255,7 @@ def load_coco_annotations(
     annotations_path: str,
     force_masks: bool = False,
     use_iscrowd: bool = True,
+    show_progress: bool = False,
 ) -> tuple[list[str], list[str], dict[str, Detections]]:
     """
     Load COCO annotations and convert them to `Detections`.
@@ -267,9 +269,21 @@ def load_coco_annotations(
         annotations_path: Path to COCO JSON annotations.
         force_masks: If `True`, always attempt to load masks.
         use_iscrowd: If `True`, include `iscrowd` and `area` in detection data.
+        show_progress: If `True`, display a progress bar while loading images.
 
     Returns:
         A tuple of `(classes, image_paths, annotations)`.
+
+    Examples:
+        ```python
+        import supervision as sv
+
+        ds = sv.DetectionDataset.from_coco(
+            images_directory_path="images/train",
+            annotations_path="images/train/_annotations.coco.json",
+            show_progress=True,
+        )
+        ```
     """
     coco_data = read_json_file(file_path=annotations_path)
     classes = coco_categories_to_classes(coco_categories=coco_data["categories"])
@@ -286,32 +300,38 @@ def load_coco_annotations(
     images = []
     annotations = {}
 
-    for coco_image in coco_images:
-        image_name, image_width, image_height = (
-            coco_image["file_name"],
-            coco_image["width"],
-            coco_image["height"],
-        )
-        image_annotations = coco_annotations_groups.get(coco_image["id"], [])
-        image_path = os.path.join(images_directory_path, image_name)
+    with tqdm(
+        total=len(coco_images),
+        desc="Loading COCO annotations",
+        disable=not show_progress,
+    ) as progress_bar:
+        for coco_image in coco_images:
+            image_name, image_width, image_height = (
+                coco_image["file_name"],
+                coco_image["width"],
+                coco_image["height"],
+            )
+            image_annotations = coco_annotations_groups.get(coco_image["id"], [])
+            image_path = os.path.join(images_directory_path, image_name)
 
-        with_masks = force_masks or any(
-            _with_seg_mask(annotation) for annotation in image_annotations
-        )
-        annotation = coco_annotations_to_detections(
-            image_annotations=image_annotations,
-            resolution_wh=(image_width, image_height),
-            with_masks=with_masks,
-            use_iscrowd=use_iscrowd,
-        )
+            with_masks = force_masks or any(
+                _with_seg_mask(annotation) for annotation in image_annotations
+            )
+            annotation = coco_annotations_to_detections(
+                image_annotations=image_annotations,
+                resolution_wh=(image_width, image_height),
+                with_masks=with_masks,
+                use_iscrowd=use_iscrowd,
+            )
 
-        annotation = map_detections_class_id(
-            source_to_target_mapping=class_index_mapping,
-            detections=annotation,
-        )
+            annotation = map_detections_class_id(
+                source_to_target_mapping=class_index_mapping,
+                detections=annotation,
+            )
 
-        images.append(image_path)
-        annotations[image_path] = annotation
+            images.append(image_path)
+            annotations[image_path] = annotation
+            progress_bar.update(1)
 
     return classes, images, annotations
 

src/supervision/dataset/formats/pascal_voc.py

@@ -9,6 +9,7 @@
 import numpy.typing as npt
 from defusedxml.ElementTree import parse, tostring
 from defusedxml.minidom import parseString
+from tqdm.auto import tqdm
 
 from supervision.dataset.utils import approximate_mask_with_polygons
 from supervision.detection.core import Detections
@@ -149,6 +150,7 @@ def load_pascal_voc_annotations(
     images_directory_path: str,
     annotations_directory_path: str,
     force_masks: bool = False,
+    show_progress: bool = False,
 ) -> tuple[list[str], list[str], dict[str, Detections]]:
     """
     Loads PASCAL VOC XML annotations and returns the image name,
@@ -160,11 +162,23 @@ def load_pascal_voc_annotations(
             PASCAL VOC annotation files.
         force_masks: If True, forces masks to be loaded for all
             annotations, regardless of whether they are present.
+        show_progress: If `True`, display a progress bar while loading images.
 
     Returns:
         A tuple with a list
             of class names, a list of paths to images, and a dictionary with image
             paths as keys and corresponding Detections instances as values.
+
+    Examples:
+        ```python
+        import supervision as sv
+
+        ds = sv.DetectionDataset.from_pascal_voc(
+            images_directory_path="images/train",
+            annotations_directory_path="images/train/labels",
+            show_progress=True,
+        )
+        ```
     """
 
     image_paths = [
@@ -177,24 +191,33 @@ def load_pascal_voc_annotations(
     classes: list[str] = []
     annotations = {}
 
-    for image_path in image_paths:
-        image_stem = Path(image_path).stem
-        annotation_path = os.path.join(annotations_directory_path, f"{image_stem}.xml")
-        if not os.path.exists(annotation_path):
-            annotations[image_path] = Detections.empty()
-            continue
-
-        tree = parse(annotation_path)
-        root = tree.getroot()
-
-        image = cv2.imread(image_path)
-        if image is None:
-            raise ValueError(f"Could not read image from path: {image_path}")
-        resolution_wh = (image.shape[1], image.shape[0])
-        annotation, classes = detections_from_xml_obj(
-            root, classes, resolution_wh, force_masks
-        )
-        annotations[image_path] = annotation
+    with tqdm(
+        total=len(image_paths),
+        desc="Loading Pascal VOC annotations",
+        disable=not show_progress,
+    ) as progress_bar:
+        for image_path in image_paths:
+            image_stem = Path(image_path).stem
+            annotation_path = os.path.join(
+                annotations_directory_path, f"{image_stem}.xml"
+            )
+            if not os.path.exists(annotation_path):
+                annotations[image_path] = Detections.empty()
+                progress_bar.update(1)
+                continue
+
+            tree = parse(annotation_path)
+            root = tree.getroot()
+
+            image = cv2.imread(image_path)
+            if image is None:
+                raise ValueError(f"Could not read image from path: {image_path}")
+            resolution_wh = (image.shape[1], image.shape[0])
+            annotation, classes = detections_from_xml_obj(
+                root, classes, resolution_wh, force_masks
+            )
+            annotations[image_path] = annotation
+            progress_bar.update(1)
 
     return classes, image_paths, annotations