Core

Warning

Dataset API is still fluid and may change. If you use Dataset API in your project until further notice, freeze the supervision version in your requirements.txt or setup.py.

DetectionDataset

Bases: BaseDataset

Dataclass containing information about object detection dataset.

Attributes:

Name	Type	Description
classes	List[str]	List containing dataset class names.
images	Dict[str, ndarray]	Dictionary mapping image name to image.
annotations	Dict[str, Detections]	Dictionary mapping image name to annotations.

Source code in supervision/dataset/core.py

@dataclass
class DetectionDataset(BaseDataset):
    """
    Dataclass containing information about object detection dataset.

    Attributes:
        classes (List[str]): List containing dataset class names.
        images (Dict[str, np.ndarray]): Dictionary mapping image name to image.
        annotations (Dict[str, Detections]): Dictionary mapping image name to annotations.
    """

    classes: List[str]
    images: Dict[str, np.ndarray]
    annotations: Dict[str, Detections]

    def __len__(self) -> int:
        """
        Return the number of images in the dataset.

        Returns:
            int: The number of images.
        """
        return len(self.images)

    def __iter__(self) -> Iterator[Tuple[str, np.ndarray, Detections]]:
        """
        Iterate over the images and annotations in the dataset.

        Yields:
            Iterator[Tuple[str, np.ndarray, Detections]]: An iterator that yields tuples containing the image name,
                                                          the image data, and its corresponding annotation.
        """
        for image_name, image in self.images.items():
            yield image_name, image, self.annotations.get(image_name, None)

    def __eq__(self, other):
        if not isinstance(other, DetectionDataset):
            return False

        if set(self.classes) != set(other.classes):
            return False

        for key in self.images:
            if not np.array_equal(self.images[key], other.images[key]):
                return False
            if not self.annotations[key] == other.annotations[key]:
                return False

        return True

    def split(
        self, split_ratio=0.8, random_state=None, shuffle: bool = True
    ) -> Tuple[DetectionDataset, DetectionDataset]:
        """
        Splits the dataset into two parts (training and testing) using the provided split_ratio.

        Args:
            split_ratio (float, optional): The ratio of the training set to the entire dataset.
            random_state (int, optional): The seed for the random number generator. This is used for reproducibility.
            shuffle (bool, optional): Whether to shuffle the data before splitting.

        Returns:
            Tuple[DetectionDataset, DetectionDataset]: A tuple containing the training and testing datasets.

        Example:
            ```python
            >>> import supervision as sv

            >>> ds = sv.DetectionDataset(...)
            >>> train_ds, test_ds = ds.split(split_ratio=0.7, random_state=42, shuffle=True)
            >>> len(train_ds), len(test_ds)
            (700, 300)
            ```
        """

        image_names = list(self.images.keys())
        train_names, test_names = train_test_split(
            data=image_names,
            train_ratio=split_ratio,
            random_state=random_state,
            shuffle=shuffle,
        )

        train_dataset = DetectionDataset(
            classes=self.classes,
            images={name: self.images[name] for name in train_names},
            annotations={name: self.annotations[name] for name in train_names},
        )
        test_dataset = DetectionDataset(
            classes=self.classes,
            images={name: self.images[name] for name in test_names},
            annotations={name: self.annotations[name] for name in test_names},
        )
        return train_dataset, test_dataset

    def as_pascal_voc(
        self,
        images_directory_path: Optional[str] = None,
        annotations_directory_path: Optional[str] = None,
        min_image_area_percentage: float = 0.0,
        max_image_area_percentage: float = 1.0,
        approximation_percentage: float = 0.0,
    ) -> None:
        """
        Exports the dataset to PASCAL VOC format. This method saves the images and their corresponding annotations in
        PASCAL VOC format.

        Args:
            images_directory_path (Optional[str]): The path to the directory where the images should be saved.
                If not provided, images will not be saved.
            annotations_directory_path (Optional[str]): The path to the directory where the annotations in
                PASCAL VOC format should be saved. If not provided, annotations will not be saved.
            min_image_area_percentage (float): The minimum percentage of detection area relative to
                the image area for a detection to be included. Argument is used only for segmentation datasets.
            max_image_area_percentage (float): The maximum percentage of detection area relative to
                the image area for a detection to be included. Argument is used only for segmentation datasets.
            approximation_percentage (float): The percentage of polygon points to be removed from the input polygon,
            in the range [0, 1). Argument is used only for segmentation datasets.
        """
        if images_directory_path:
            images_path = Path(images_directory_path)
            images_path.mkdir(parents=True, exist_ok=True)

        if annotations_directory_path:
            annotations_path = Path(annotations_directory_path)
            annotations_path.mkdir(parents=True, exist_ok=True)

        for image_name, image in self.images.items():
            detections = self.annotations[image_name]

            if images_directory_path:
                cv2.imwrite(str(images_path / image_name), image)

            if annotations_directory_path:
                annotation_name = Path(image_name).stem
                pascal_voc_xml = detections_to_pascal_voc(
                    detections=detections,
                    classes=self.classes,
                    filename=image_name,
                    image_shape=image.shape,
                    min_image_area_percentage=min_image_area_percentage,
                    max_image_area_percentage=max_image_area_percentage,
                    approximation_percentage=approximation_percentage,
                )

                with open(annotations_path / f"{annotation_name}.xml", "w") as f:
                    f.write(pascal_voc_xml)

    @classmethod
    def from_pascal_voc(
        cls, images_directory_path: str, annotations_directory_path: str
    ) -> DetectionDataset:
        """
        Creates a Dataset instance from PASCAL VOC formatted data.

        Args:
            images_directory_path (str): The path to the directory containing the images.
            annotations_directory_path (str): The path to the directory containing the PASCAL VOC XML annotations.

        Returns:
            DetectionDataset: A DetectionDataset instance containing the loaded images and annotations.

        Example:
            ```python
            >>> import roboflow
            >>> from roboflow import Roboflow
            >>> import supervision as sv

            >>> roboflow.login()

            >>> rf = Roboflow()

            >>> project = rf.workspace(WORKSPACE_ID).project(PROJECT_ID)
            >>> dataset = project.version(PROJECT_VERSION).download("voc")

            >>> ds = sv.DetectionDataset.from_yolo(
            ...     images_directory_path=f"{dataset.location}/train/images",
            ...     annotations_directory_path=f"{dataset.location}/train/labels"
            ... )

            >>> ds.classes
            ['dog', 'person']
            ```
        """
        image_paths = list_files_with_extensions(
            directory=images_directory_path, extensions=["jpg", "jpeg", "png"]
        )
        annotation_paths = list_files_with_extensions(
            directory=annotations_directory_path, extensions=["xml"]
        )

        raw_annotations: List[Tuple[str, Detections, List[str]]] = [
            load_pascal_voc_annotations(annotation_path=str(annotation_path))
            for annotation_path in annotation_paths
        ]

        classes = []
        for annotation in raw_annotations:
            classes.extend(annotation[2])
        classes = list(set(classes))

        for annotation in raw_annotations:
            class_id = [classes.index(class_name) for class_name in annotation[2]]
            annotation[1].class_id = np.array(class_id)

        images = {
            image_path.name: cv2.imread(str(image_path)) for image_path in image_paths
        }

        annotations = {
            image_name: detections for image_name, detections, _ in raw_annotations
        }
        return DetectionDataset(classes=classes, images=images, annotations=annotations)

    @classmethod
    def from_yolo(
        cls,
        images_directory_path: str,
        annotations_directory_path: str,
        data_yaml_path: str,
        force_masks: bool = False,
    ) -> DetectionDataset:
        """
        Creates a Dataset instance from YOLO formatted data.

        Args:
            images_directory_path (str): The path to the directory containing the images.
            annotations_directory_path (str): The path to the directory containing the YOLO annotation files.
            data_yaml_path (str): The path to the data YAML file containing class information.
            force_masks (bool, optional): If True, forces masks to be loaded for all annotations, regardless of whether they are present.

        Returns:
            DetectionDataset: A DetectionDataset instance containing the loaded images and annotations.

        Example:
            ```python
            >>> import roboflow
            >>> from roboflow import Roboflow
            >>> import supervision as sv

            >>> roboflow.login()

            >>> rf = Roboflow()

            >>> project = rf.workspace(WORKSPACE_ID).project(PROJECT_ID)
            >>> dataset = project.version(PROJECT_VERSION).download("yolov5")

            >>> ds = sv.DetectionDataset.from_yolo(
            ...     images_directory_path=f"{dataset.location}/train/images",
            ...     annotations_directory_path=f"{dataset.location}/train/labels",
            ...     data_yaml_path=f"{dataset.location}/data.yaml"
            ... )

            >>> ds.classes
            ['dog', 'person']
            ```
        """
        classes, images, annotations = load_yolo_annotations(
            images_directory_path=images_directory_path,
            annotations_directory_path=annotations_directory_path,
            data_yaml_path=data_yaml_path,
            force_masks=force_masks,
        )
        return DetectionDataset(classes=classes, images=images, annotations=annotations)

    def as_yolo(
        self,
        images_directory_path: Optional[str] = None,
        annotations_directory_path: Optional[str] = None,
        data_yaml_path: Optional[str] = None,
        min_image_area_percentage: float = 0.0,
        max_image_area_percentage: float = 1.0,
        approximation_percentage: float = 0.0,
    ) -> None:
        """
        Exports the dataset to YOLO format. This method saves the images and their corresponding
        annotations in YOLO format.

        Args:
            images_directory_path (Optional[str]): The path to the directory where the images should be saved.
                If not provided, images will not be saved.
            annotations_directory_path (Optional[str]): The path to the directory where the annotations in
                YOLO format should be saved. If not provided, annotations will not be saved.
            data_yaml_path (Optional[str]): The path where the data.yaml file should be saved.
                If not provided, the file will not be saved.
            min_image_area_percentage (float): The minimum percentage of detection area relative to
                the image area for a detection to be included. Argument is used only for segmentation datasets.
            max_image_area_percentage (float): The maximum percentage of detection area relative to
                the image area for a detection to be included. Argument is used only for segmentation datasets.
            approximation_percentage (float): The percentage of polygon points 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.
        """
        if images_directory_path is not None:
            save_dataset_images(
                images_directory_path=images_directory_path, images=self.images
            )
        if annotations_directory_path is not None:
            save_yolo_annotations(
                annotations_directory_path=annotations_directory_path,
                images=self.images,
                annotations=self.annotations,
                min_image_area_percentage=min_image_area_percentage,
                max_image_area_percentage=max_image_area_percentage,
                approximation_percentage=approximation_percentage,
            )
        if data_yaml_path is not None:
            save_data_yaml(data_yaml_path=data_yaml_path, classes=self.classes)

    @classmethod
    def from_coco(
        cls,
        images_directory_path: str,
        annotations_path: str,
        force_masks: bool = False,
    ) -> DetectionDataset:
        """
        Creates a Dataset instance from COCO formatted data.

        Args:
            images_directory_path (str): The path to the directory containing the images.
            annotations_path (str): The path to the json annotation files.
            force_masks (bool, optional): If True, forces masks to be loaded for all annotations, regardless of whether they are present.

        Returns:
            DetectionDataset: A DetectionDataset instance containing the loaded images and annotations.

        Example:
            ```python
            >>> import roboflow
            >>> from roboflow import Roboflow
            >>> import supervision as sv

            >>> roboflow.login()

            >>> rf = Roboflow()

            >>> project = rf.workspace(WORKSPACE_ID).project(PROJECT_ID)
            >>> dataset = project.version(PROJECT_VERSION).download("coco")

            >>> ds = sv.DetectionDataset.from_coco(
            ...     images_directory_path=f"{dataset.location}/train",
            ...     annotations_path=f"{dataset.location}/train/_annotations.coco.json",
            ... )

            >>> ds.classes
            ['dog', 'person']
            ```
        """
        classes, images, annotations = load_coco_annotations(
            images_directory_path=images_directory_path,
            annotations_path=annotations_path,
            force_masks=force_masks,
        )
        return DetectionDataset(classes=classes, images=images, annotations=annotations)

    def as_coco(
        self,
        images_directory_path: Optional[str] = None,
        annotations_path: Optional[str] = None,
        min_image_area_percentage: float = 0.0,
        max_image_area_percentage: float = 1.0,
        approximation_percentage: float = 0.0,
    ) -> None:
        """
        Exports the dataset to COCO format. This method saves the images and their corresponding
        annotations in COCO format.

        Args:
            images_directory_path (Optional[str]): The path to the directory where the images should be saved.
                If not provided, images will not be saved.
            annotations_path (Optional[str]): The path to COCO annotation file.
            min_image_area_percentage (float): The minimum percentage of detection area relative to
                the image area for a detection to be included. Argument is used only for segmentation datasets.
            max_image_area_percentage (float): The maximum percentage of detection area relative to
                the image area for a detection to be included. Argument is used only for segmentation datasets.
            approximation_percentage (float): The percentage of polygon points 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.
        """
        if images_directory_path is not None:
            save_dataset_images(
                images_directory_path=images_directory_path, images=self.images
            )
        if annotations_path is not None:
            save_coco_annotations(
                annotation_path=annotations_path,
                images=self.images,
                annotations=self.annotations,
                classes=self.classes,
                min_image_area_percentage=min_image_area_percentage,
                max_image_area_percentage=max_image_area_percentage,
                approximation_percentage=approximation_percentage,
            )

    @classmethod
    def merge(cls, dataset_list: List[DetectionDataset]) -> DetectionDataset:
        """
        Merge a list of `DetectionDataset` objects into a single `DetectionDataset` object.

        This method takes a list of `DetectionDataset` objects and combines their respective fields (`classes`, `images`,
        `annotations`) into a single `DetectionDataset` object.

        Args:
            dataset_list (List[DetectionDataset]): A list of `DetectionDataset` objects to merge.

        Returns:
            (DetectionDataset): A single `DetectionDataset` object containing the merged data from the input list.

        Example:
            ```python
            >>> import supervision as sv

            >>> ds_1 = sv.DetectionDataset(...)
            >>> len(ds_1)
            100
            >>> ds_1.classes
            ['dog', 'person']

            >>> ds_2 = sv.DetectionDataset(...)
            >>> len(ds_2)
            200
            >>> ds_2.classes
            ['cat']

            >>> ds_merged = sv.DetectionDataset.merge([ds_1, ds_2])
            >>> len(ds_merged)
            300
            >>> ds_merged.classes
            ['cat', 'dog', 'person']
            ```
        """
        merged_images, merged_annotations = {}, {}
        class_lists = [dataset.classes for dataset in dataset_list]
        merged_classes = merge_class_lists(class_lists=class_lists)

        for dataset in dataset_list:
            class_index_mapping = build_class_index_mapping(
                source_classes=dataset.classes, target_classes=merged_classes
            )
            for image_name, image, detections in dataset:
                if image_name in merged_annotations:
                    raise ValueError(
                        f"Image name {image_name} is not unique across datasets."
                    )

                merged_images[image_name] = image
                merged_annotations[image_name] = map_detections_class_id(
                    source_to_target_mapping=class_index_mapping,
                    detections=detections,
                )

        return cls(
            classes=merged_classes, images=merged_images, annotations=merged_annotations
        )

__iter__()

Iterate over the images and annotations in the dataset.

Yields:

Type	Description
str	Iterator[Tuple[str, np.ndarray, Detections]]: An iterator that yields tuples containing the image name, the image data, and its corresponding annotation.

Source code in supervision/dataset/core.py

def __iter__(self) -> Iterator[Tuple[str, np.ndarray, Detections]]:
    """
    Iterate over the images and annotations in the dataset.

    Yields:
        Iterator[Tuple[str, np.ndarray, Detections]]: An iterator that yields tuples containing the image name,
                                                      the image data, and its corresponding annotation.
    """
    for image_name, image in self.images.items():
        yield image_name, image, self.annotations.get(image_name, None)

__len__()

Return the number of images in the dataset.

Returns:

Name	Type	Description
int	int	The number of images.

Source code in supervision/dataset/core.py

def __len__(self) -> int:
    """
    Return the number of images in the dataset.

    Returns:
        int: The number of images.
    """
    return len(self.images)

as_coco(images_directory_path=None, annotations_path=None, min_image_area_percentage=0.0, max_image_area_percentage=1.0, approximation_percentage=0.0)

Exports the dataset to COCO format. This method saves the images and their corresponding annotations in COCO format.

Parameters:

Name	Type	Description	Default
images_directory_path	Optional[str]	The path to the directory where the images should be saved. If not provided, images will not be saved.	None
annotations_path	Optional[str]	The path to COCO annotation file.	None
min_image_area_percentage	float	The minimum percentage of detection area relative to the image area for a detection to be included. Argument is used only for segmentation datasets.	0.0
max_image_area_percentage	float	The maximum percentage of detection area relative to the image area for a detection to be included. Argument is used only for segmentation datasets.	1.0
approximation_percentage	float	The percentage of polygon points 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.	0.0

Source code in supervision/dataset/core.py

def as_coco(
    self,
    images_directory_path: Optional[str] = None,
    annotations_path: Optional[str] = None,
    min_image_area_percentage: float = 0.0,
    max_image_area_percentage: float = 1.0,
    approximation_percentage: float = 0.0,
) -> None:
    """
    Exports the dataset to COCO format. This method saves the images and their corresponding
    annotations in COCO format.

    Args:
        images_directory_path (Optional[str]): The path to the directory where the images should be saved.
            If not provided, images will not be saved.
        annotations_path (Optional[str]): The path to COCO annotation file.
        min_image_area_percentage (float): The minimum percentage of detection area relative to
            the image area for a detection to be included. Argument is used only for segmentation datasets.
        max_image_area_percentage (float): The maximum percentage of detection area relative to
            the image area for a detection to be included. Argument is used only for segmentation datasets.
        approximation_percentage (float): The percentage of polygon points 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.
    """
    if images_directory_path is not None:
        save_dataset_images(
            images_directory_path=images_directory_path, images=self.images
        )
    if annotations_path is not None:
        save_coco_annotations(
            annotation_path=annotations_path,
            images=self.images,
            annotations=self.annotations,
            classes=self.classes,
            min_image_area_percentage=min_image_area_percentage,
            max_image_area_percentage=max_image_area_percentage,
            approximation_percentage=approximation_percentage,
        )

as_pascal_voc(images_directory_path=None, annotations_directory_path=None, min_image_area_percentage=0.0, max_image_area_percentage=1.0, approximation_percentage=0.0)

Exports the dataset to PASCAL VOC format. This method saves the images and their corresponding annotations in PASCAL VOC format.

Parameters:

Name	Type	Description	Default
images_directory_path	Optional[str]	The path to the directory where the images should be saved. If not provided, images will not be saved.	None
annotations_directory_path	Optional[str]	The path to the directory where the annotations in PASCAL VOC format should be saved. If not provided, annotations will not be saved.	None
min_image_area_percentage	float	The minimum percentage of detection area relative to the image area for a detection to be included. Argument is used only for segmentation datasets.	0.0
max_image_area_percentage	float	The maximum percentage of detection area relative to the image area for a detection to be included. Argument is used only for segmentation datasets.	1.0
approximation_percentage	float	The percentage of polygon points to be removed from the input polygon,	0.0

Source code in supervision/dataset/core.py

def as_pascal_voc(
    self,
    images_directory_path: Optional[str] = None,
    annotations_directory_path: Optional[str] = None,
    min_image_area_percentage: float = 0.0,
    max_image_area_percentage: float = 1.0,
    approximation_percentage: float = 0.0,
) -> None:
    """
    Exports the dataset to PASCAL VOC format. This method saves the images and their corresponding annotations in
    PASCAL VOC format.

    Args:
        images_directory_path (Optional[str]): The path to the directory where the images should be saved.
            If not provided, images will not be saved.
        annotations_directory_path (Optional[str]): The path to the directory where the annotations in
            PASCAL VOC format should be saved. If not provided, annotations will not be saved.
        min_image_area_percentage (float): The minimum percentage of detection area relative to
            the image area for a detection to be included. Argument is used only for segmentation datasets.
        max_image_area_percentage (float): The maximum percentage of detection area relative to
            the image area for a detection to be included. Argument is used only for segmentation datasets.
        approximation_percentage (float): The percentage of polygon points to be removed from the input polygon,
        in the range [0, 1). Argument is used only for segmentation datasets.
    """
    if images_directory_path:
        images_path = Path(images_directory_path)
        images_path.mkdir(parents=True, exist_ok=True)

    if annotations_directory_path:
        annotations_path = Path(annotations_directory_path)
        annotations_path.mkdir(parents=True, exist_ok=True)

    for image_name, image in self.images.items():
        detections = self.annotations[image_name]

        if images_directory_path:
            cv2.imwrite(str(images_path / image_name), image)

        if annotations_directory_path:
            annotation_name = Path(image_name).stem
            pascal_voc_xml = detections_to_pascal_voc(
                detections=detections,
                classes=self.classes,
                filename=image_name,
                image_shape=image.shape,
                min_image_area_percentage=min_image_area_percentage,
                max_image_area_percentage=max_image_area_percentage,
                approximation_percentage=approximation_percentage,
            )

            with open(annotations_path / f"{annotation_name}.xml", "w") as f:
                f.write(pascal_voc_xml)

as_yolo(images_directory_path=None, annotations_directory_path=None, data_yaml_path=None, min_image_area_percentage=0.0, max_image_area_percentage=1.0, approximation_percentage=0.0)

Exports the dataset to YOLO format. This method saves the images and their corresponding annotations in YOLO format.

Parameters:

Name	Type	Description	Default
images_directory_path	Optional[str]	The path to the directory where the images should be saved. If not provided, images will not be saved.	None
annotations_directory_path	Optional[str]	The path to the directory where the annotations in YOLO format should be saved. If not provided, annotations will not be saved.	None
data_yaml_path	Optional[str]	The path where the data.yaml file should be saved. If not provided, the file will not be saved.	None
min_image_area_percentage	float	The minimum percentage of detection area relative to the image area for a detection to be included. Argument is used only for segmentation datasets.	0.0
max_image_area_percentage	float	The maximum percentage of detection area relative to the image area for a detection to be included. Argument is used only for segmentation datasets.	1.0
approximation_percentage	float	The percentage of polygon points 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.	0.0

Source code in supervision/dataset/core.py

def as_yolo(
    self,
    images_directory_path: Optional[str] = None,
    annotations_directory_path: Optional[str] = None,
    data_yaml_path: Optional[str] = None,
    min_image_area_percentage: float = 0.0,
    max_image_area_percentage: float = 1.0,
    approximation_percentage: float = 0.0,
) -> None:
    """
    Exports the dataset to YOLO format. This method saves the images and their corresponding
    annotations in YOLO format.

    Args:
        images_directory_path (Optional[str]): The path to the directory where the images should be saved.
            If not provided, images will not be saved.
        annotations_directory_path (Optional[str]): The path to the directory where the annotations in
            YOLO format should be saved. If not provided, annotations will not be saved.
        data_yaml_path (Optional[str]): The path where the data.yaml file should be saved.
            If not provided, the file will not be saved.
        min_image_area_percentage (float): The minimum percentage of detection area relative to
            the image area for a detection to be included. Argument is used only for segmentation datasets.
        max_image_area_percentage (float): The maximum percentage of detection area relative to
            the image area for a detection to be included. Argument is used only for segmentation datasets.
        approximation_percentage (float): The percentage of polygon points 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.
    """
    if images_directory_path is not None:
        save_dataset_images(
            images_directory_path=images_directory_path, images=self.images
        )
    if annotations_directory_path is not None:
        save_yolo_annotations(
            annotations_directory_path=annotations_directory_path,
            images=self.images,
            annotations=self.annotations,
            min_image_area_percentage=min_image_area_percentage,
            max_image_area_percentage=max_image_area_percentage,
            approximation_percentage=approximation_percentage,
        )
    if data_yaml_path is not None:
        save_data_yaml(data_yaml_path=data_yaml_path, classes=self.classes)

from_coco(images_directory_path, annotations_path, force_masks=False) classmethod

Creates a Dataset instance from COCO formatted data.

Parameters:

Name	Type	Description	Default
images_directory_path	str	The path to the directory containing the images.	required
annotations_path	str	The path to the json annotation files.	required
force_masks	bool	If True, forces masks to be loaded for all annotations, regardless of whether they are present.	False

Returns:

Name	Type	Description
DetectionDataset	DetectionDataset	A DetectionDataset instance containing the loaded images and annotations.

Example

>>> import roboflow
>>> from roboflow import Roboflow
>>> import supervision as sv

>>> roboflow.login()

>>> rf = Roboflow()

>>> project = rf.workspace(WORKSPACE_ID).project(PROJECT_ID)
>>> dataset = project.version(PROJECT_VERSION).download("coco")

>>> ds = sv.DetectionDataset.from_coco(
...     images_directory_path=f"{dataset.location}/train",
...     annotations_path=f"{dataset.location}/train/_annotations.coco.json",
... )

>>> ds.classes
['dog', 'person']

Source code in supervision/dataset/core.py

@classmethod
def from_coco(
    cls,
    images_directory_path: str,
    annotations_path: str,
    force_masks: bool = False,
) -> DetectionDataset:
    """
    Creates a Dataset instance from COCO formatted data.

    Args:
        images_directory_path (str): The path to the directory containing the images.
        annotations_path (str): The path to the json annotation files.
        force_masks (bool, optional): If True, forces masks to be loaded for all annotations, regardless of whether they are present.

    Returns:
        DetectionDataset: A DetectionDataset instance containing the loaded images and annotations.

    Example:
        ```python
        >>> import roboflow
        >>> from roboflow import Roboflow
        >>> import supervision as sv

        >>> roboflow.login()

        >>> rf = Roboflow()

        >>> project = rf.workspace(WORKSPACE_ID).project(PROJECT_ID)
        >>> dataset = project.version(PROJECT_VERSION).download("coco")

        >>> ds = sv.DetectionDataset.from_coco(
        ...     images_directory_path=f"{dataset.location}/train",
        ...     annotations_path=f"{dataset.location}/train/_annotations.coco.json",
        ... )

        >>> ds.classes
        ['dog', 'person']
        ```
    """
    classes, images, annotations = load_coco_annotations(
        images_directory_path=images_directory_path,
        annotations_path=annotations_path,
        force_masks=force_masks,
    )
    return DetectionDataset(classes=classes, images=images, annotations=annotations)

from_pascal_voc(images_directory_path, annotations_directory_path) classmethod

Creates a Dataset instance from PASCAL VOC formatted data.

Parameters:

Name	Type	Description	Default
images_directory_path	str	The path to the directory containing the images.	required
annotations_directory_path	str	The path to the directory containing the PASCAL VOC XML annotations.	required

Returns:

Name	Type	Description
DetectionDataset	DetectionDataset	A DetectionDataset instance containing the loaded images and annotations.

Example

>>> import roboflow
>>> from roboflow import Roboflow
>>> import supervision as sv

>>> roboflow.login()

>>> rf = Roboflow()

>>> project = rf.workspace(WORKSPACE_ID).project(PROJECT_ID)
>>> dataset = project.version(PROJECT_VERSION).download("voc")

>>> ds = sv.DetectionDataset.from_yolo(
...     images_directory_path=f"{dataset.location}/train/images",
...     annotations_directory_path=f"{dataset.location}/train/labels"
... )

>>> ds.classes
['dog', 'person']

Source code in supervision/dataset/core.py

@classmethod
def from_pascal_voc(
    cls, images_directory_path: str, annotations_directory_path: str
) -> DetectionDataset:
    """
    Creates a Dataset instance from PASCAL VOC formatted data.

    Args:
        images_directory_path (str): The path to the directory containing the images.
        annotations_directory_path (str): The path to the directory containing the PASCAL VOC XML annotations.

    Returns:
        DetectionDataset: A DetectionDataset instance containing the loaded images and annotations.

    Example:
        ```python
        >>> import roboflow
        >>> from roboflow import Roboflow
        >>> import supervision as sv

        >>> roboflow.login()

        >>> rf = Roboflow()

        >>> project = rf.workspace(WORKSPACE_ID).project(PROJECT_ID)
        >>> dataset = project.version(PROJECT_VERSION).download("voc")

        >>> ds = sv.DetectionDataset.from_yolo(
        ...     images_directory_path=f"{dataset.location}/train/images",
        ...     annotations_directory_path=f"{dataset.location}/train/labels"
        ... )

        >>> ds.classes
        ['dog', 'person']
        ```
    """
    image_paths = list_files_with_extensions(
        directory=images_directory_path, extensions=["jpg", "jpeg", "png"]
    )
    annotation_paths = list_files_with_extensions(
        directory=annotations_directory_path, extensions=["xml"]
    )

    raw_annotations: List[Tuple[str, Detections, List[str]]] = [
        load_pascal_voc_annotations(annotation_path=str(annotation_path))
        for annotation_path in annotation_paths
    ]

    classes = []
    for annotation in raw_annotations:
        classes.extend(annotation[2])
    classes = list(set(classes))

    for annotation in raw_annotations:
        class_id = [classes.index(class_name) for class_name in annotation[2]]
        annotation[1].class_id = np.array(class_id)

    images = {
        image_path.name: cv2.imread(str(image_path)) for image_path in image_paths
    }

    annotations = {
        image_name: detections for image_name, detections, _ in raw_annotations
    }
    return DetectionDataset(classes=classes, images=images, annotations=annotations)

from_yolo(images_directory_path, annotations_directory_path, data_yaml_path, force_masks=False) classmethod

Creates a Dataset instance from YOLO formatted data.

Parameters:

Name	Type	Description	Default
images_directory_path	str	The path to the directory containing the images.	required
annotations_directory_path	str	The path to the directory containing the YOLO annotation files.	required
data_yaml_path	str	The path to the data YAML file containing class information.	required
force_masks	bool	If True, forces masks to be loaded for all annotations, regardless of whether they are present.	False

Returns:

Name	Type	Description
DetectionDataset	DetectionDataset	A DetectionDataset instance containing the loaded images and annotations.

Example

>>> import roboflow
>>> from roboflow import Roboflow
>>> import supervision as sv

>>> roboflow.login()

>>> rf = Roboflow()

>>> project = rf.workspace(WORKSPACE_ID).project(PROJECT_ID)
>>> dataset = project.version(PROJECT_VERSION).download("yolov5")

>>> ds = sv.DetectionDataset.from_yolo(
...     images_directory_path=f"{dataset.location}/train/images",
...     annotations_directory_path=f"{dataset.location}/train/labels",
...     data_yaml_path=f"{dataset.location}/data.yaml"
... )

>>> ds.classes
['dog', 'person']

Source code in supervision/dataset/core.py

@classmethod
def from_yolo(
    cls,
    images_directory_path: str,
    annotations_directory_path: str,
    data_yaml_path: str,
    force_masks: bool = False,
) -> DetectionDataset:
    """
    Creates a Dataset instance from YOLO formatted data.

    Args:
        images_directory_path (str): The path to the directory containing the images.
        annotations_directory_path (str): The path to the directory containing the YOLO annotation files.
        data_yaml_path (str): The path to the data YAML file containing class information.
        force_masks (bool, optional): If True, forces masks to be loaded for all annotations, regardless of whether they are present.

    Returns:
        DetectionDataset: A DetectionDataset instance containing the loaded images and annotations.

    Example:
        ```python
        >>> import roboflow
        >>> from roboflow import Roboflow
        >>> import supervision as sv

        >>> roboflow.login()

        >>> rf = Roboflow()

        >>> project = rf.workspace(WORKSPACE_ID).project(PROJECT_ID)
        >>> dataset = project.version(PROJECT_VERSION).download("yolov5")

        >>> ds = sv.DetectionDataset.from_yolo(
        ...     images_directory_path=f"{dataset.location}/train/images",
        ...     annotations_directory_path=f"{dataset.location}/train/labels",
        ...     data_yaml_path=f"{dataset.location}/data.yaml"
        ... )

        >>> ds.classes
        ['dog', 'person']
        ```
    """
    classes, images, annotations = load_yolo_annotations(
        images_directory_path=images_directory_path,
        annotations_directory_path=annotations_directory_path,
        data_yaml_path=data_yaml_path,
        force_masks=force_masks,
    )
    return DetectionDataset(classes=classes, images=images, annotations=annotations)

merge(dataset_list) classmethod

Merge a list of DetectionDataset objects into a single DetectionDataset object.

This method takes a list of DetectionDataset objects and combines their respective fields (classes, images, annotations) into a single DetectionDataset object.

Parameters:

Name	Type	Description	Default
dataset_list	List[DetectionDataset]	A list of DetectionDataset objects to merge.	required

Returns:

Type	Description
DetectionDataset	A single DetectionDataset object containing the merged data from the input list.

Example

>>> import supervision as sv

>>> ds_1 = sv.DetectionDataset(...)
>>> len(ds_1)
100
>>> ds_1.classes
['dog', 'person']

>>> ds_2 = sv.DetectionDataset(...)
>>> len(ds_2)
200
>>> ds_2.classes
['cat']

>>> ds_merged = sv.DetectionDataset.merge([ds_1, ds_2])
>>> len(ds_merged)
300
>>> ds_merged.classes
['cat', 'dog', 'person']

Source code in supervision/dataset/core.py

@classmethod
def merge(cls, dataset_list: List[DetectionDataset]) -> DetectionDataset:
    """
    Merge a list of `DetectionDataset` objects into a single `DetectionDataset` object.

    This method takes a list of `DetectionDataset` objects and combines their respective fields (`classes`, `images`,
    `annotations`) into a single `DetectionDataset` object.

    Args:
        dataset_list (List[DetectionDataset]): A list of `DetectionDataset` objects to merge.

    Returns:
        (DetectionDataset): A single `DetectionDataset` object containing the merged data from the input list.

    Example:
        ```python
        >>> import supervision as sv

        >>> ds_1 = sv.DetectionDataset(...)
        >>> len(ds_1)
        100
        >>> ds_1.classes
        ['dog', 'person']

        >>> ds_2 = sv.DetectionDataset(...)
        >>> len(ds_2)
        200
        >>> ds_2.classes
        ['cat']

        >>> ds_merged = sv.DetectionDataset.merge([ds_1, ds_2])
        >>> len(ds_merged)
        300
        >>> ds_merged.classes
        ['cat', 'dog', 'person']
        ```
    """
    merged_images, merged_annotations = {}, {}
    class_lists = [dataset.classes for dataset in dataset_list]
    merged_classes = merge_class_lists(class_lists=class_lists)

    for dataset in dataset_list:
        class_index_mapping = build_class_index_mapping(
            source_classes=dataset.classes, target_classes=merged_classes
        )
        for image_name, image, detections in dataset:
            if image_name in merged_annotations:
                raise ValueError(
                    f"Image name {image_name} is not unique across datasets."
                )

            merged_images[image_name] = image
            merged_annotations[image_name] = map_detections_class_id(
                source_to_target_mapping=class_index_mapping,
                detections=detections,
            )

    return cls(
        classes=merged_classes, images=merged_images, annotations=merged_annotations
    )

split(split_ratio=0.8, random_state=None, shuffle=True)

Splits the dataset into two parts (training and testing) using the provided split_ratio.

Parameters:

Name	Type	Description	Default
split_ratio	float	The ratio of the training set to the entire dataset.	0.8
random_state	int	The seed for the random number generator. This is used for reproducibility.	None
shuffle	bool	Whether to shuffle the data before splitting.	True

Returns:

Type	Description
Tuple[DetectionDataset, DetectionDataset]	Tuple[DetectionDataset, DetectionDataset]: A tuple containing the training and testing datasets.

Example

>>> import supervision as sv

>>> ds = sv.DetectionDataset(...)
>>> train_ds, test_ds = ds.split(split_ratio=0.7, random_state=42, shuffle=True)
>>> len(train_ds), len(test_ds)
(700, 300)

Source code in supervision/dataset/core.py

def split(
    self, split_ratio=0.8, random_state=None, shuffle: bool = True
) -> Tuple[DetectionDataset, DetectionDataset]:
    """
    Splits the dataset into two parts (training and testing) using the provided split_ratio.

    Args:
        split_ratio (float, optional): The ratio of the training set to the entire dataset.
        random_state (int, optional): The seed for the random number generator. This is used for reproducibility.
        shuffle (bool, optional): Whether to shuffle the data before splitting.

    Returns:
        Tuple[DetectionDataset, DetectionDataset]: A tuple containing the training and testing datasets.

    Example:
        ```python
        >>> import supervision as sv

        >>> ds = sv.DetectionDataset(...)
        >>> train_ds, test_ds = ds.split(split_ratio=0.7, random_state=42, shuffle=True)
        >>> len(train_ds), len(test_ds)
        (700, 300)
        ```
    """

    image_names = list(self.images.keys())
    train_names, test_names = train_test_split(
        data=image_names,
        train_ratio=split_ratio,
        random_state=random_state,
        shuffle=shuffle,
    )

    train_dataset = DetectionDataset(
        classes=self.classes,
        images={name: self.images[name] for name in train_names},
        annotations={name: self.annotations[name] for name in train_names},
    )
    test_dataset = DetectionDataset(
        classes=self.classes,
        images={name: self.images[name] for name in test_names},
        annotations={name: self.annotations[name] for name in test_names},
    )
    return train_dataset, test_dataset

ClassificationDataset

Bases: BaseDataset

Dataclass containing information about a classification dataset.

Attributes:

Name	Type	Description
classes	List[str]	List containing dataset class names.
images	Dict[str, ndarray]	Dictionary mapping image name to image.
annotations	Dict[str, Detections]	Dictionary mapping image name to annotations.

Source code in supervision/dataset/core.py

@dataclass
class ClassificationDataset(BaseDataset):
    """
    Dataclass containing information about a classification dataset.

    Attributes:
        classes (List[str]): List containing dataset class names.
        images (Dict[str, np.ndarray]): Dictionary mapping image name to image.
        annotations (Dict[str, Detections]): Dictionary mapping image name to annotations.
    """

    classes: List[str]
    images: Dict[str, np.ndarray]
    annotations: Dict[str, Classifications]

    def __len__(self) -> int:
        return len(self.images)

    def split(
        self, split_ratio=0.8, random_state=None, shuffle: bool = True
    ) -> Tuple[ClassificationDataset, ClassificationDataset]:
        """
        Splits the dataset into two parts (training and testing) using the provided split_ratio.

        Args:
            split_ratio (float, optional): The ratio of the training set to the entire dataset.
            random_state (int, optional): The seed for the random number generator. This is used for reproducibility.
            shuffle (bool, optional): Whether to shuffle the data before splitting.

        Returns:
            Tuple[ClassificationDataset, ClassificationDataset]: A tuple containing the training and testing datasets.

        Example:
            ```python
            >>> import supervision as sv

            >>> cd = sv.ClassificationDataset(...)
            >>> train_cd, test_cd = cd.split(split_ratio=0.7, random_state=42, shuffle=True)
            >>> len(train_cd), len(test_cd)
            (700, 300)
            ```
        """
        image_names = list(self.images.keys())
        train_names, test_names = train_test_split(
            data=image_names,
            train_ratio=split_ratio,
            random_state=random_state,
            shuffle=shuffle,
        )

        train_dataset = ClassificationDataset(
            classes=self.classes,
            images={name: self.images[name] for name in train_names},
            annotations={name: self.annotations[name] for name in train_names},
        )
        test_dataset = ClassificationDataset(
            classes=self.classes,
            images={name: self.images[name] for name in test_names},
            annotations={name: self.annotations[name] for name in test_names},
        )
        return train_dataset, test_dataset

    def as_folder_structure(self, root_directory_path: str) -> None:
        """
        Saves the dataset as a multi-class folder structure.

        Args:
            root_directory_path (str): The path to the directory where the dataset will be saved.
        """
        os.makedirs(root_directory_path, exist_ok=True)

        for class_name in self.classes:
            os.makedirs(os.path.join(root_directory_path, class_name), exist_ok=True)

        for image_name in self.images:
            classification = self.annotations[image_name]
            image = self.images[image_name]
            class_id = (
                classification.class_id[0]
                if classification.confidence is None
                else classification.get_top_k(1)[0][0]
            )
            class_name = self.classes[class_id]
            image_path = os.path.join(root_directory_path, class_name, image_name)
            cv2.imwrite(image_path, image)

    @classmethod
    def from_folder_structure(cls, root_directory_path: str) -> ClassificationDataset:
        """
        Load data from a multiclass folder structure into a ClassificationDataset.

        Args:
            root_directory_path (str): The path to the dataset directory.

        Returns:
            ClassificationDataset: The dataset.

        Example:
            ```python
            >>> import roboflow
            >>> from roboflow import Roboflow
            >>> import supervision as sv

            >>> roboflow.login()

            >>> rf = Roboflow()

            >>> project = rf.workspace(WORKSPACE_ID).project(PROJECT_ID)
            >>> dataset = project.version(PROJECT_VERSION).download("folder")

            >>> cd = sv.ClassificationDataset.from_folder_structure(
            ...     root_directory_path=f"{dataset.location}/train"
            ... )
            ```
        """
        classes = os.listdir(root_directory_path)
        classes = sorted(set(classes))

        images = {}
        annotations = {}

        for class_name in classes:
            class_id = classes.index(class_name)

            for image in os.listdir(os.path.join(root_directory_path, class_name)):
                image_dir = os.path.join(root_directory_path, class_name, image)
                images[image] = cv2.imread(image_dir)
                annotations[image] = Classifications(
                    class_id=np.array([class_id]),
                )

        return cls(
            classes=classes,
            images=images,
            annotations=annotations,
        )

as_folder_structure(root_directory_path)

Saves the dataset as a multi-class folder structure.

Parameters:

Name	Type	Description	Default
root_directory_path	str	The path to the directory where the dataset will be saved.	required

Source code in supervision/dataset/core.py

def as_folder_structure(self, root_directory_path: str) -> None:
    """
    Saves the dataset as a multi-class folder structure.

    Args:
        root_directory_path (str): The path to the directory where the dataset will be saved.
    """
    os.makedirs(root_directory_path, exist_ok=True)

    for class_name in self.classes:
        os.makedirs(os.path.join(root_directory_path, class_name), exist_ok=True)

    for image_name in self.images:
        classification = self.annotations[image_name]
        image = self.images[image_name]
        class_id = (
            classification.class_id[0]
            if classification.confidence is None
            else classification.get_top_k(1)[0][0]
        )
        class_name = self.classes[class_id]
        image_path = os.path.join(root_directory_path, class_name, image_name)
        cv2.imwrite(image_path, image)

from_folder_structure(root_directory_path) classmethod

Load data from a multiclass folder structure into a ClassificationDataset.

Parameters:

Name	Type	Description	Default
root_directory_path	str	The path to the dataset directory.	required

Returns:

Name	Type	Description
ClassificationDataset	ClassificationDataset	The dataset.

Example

>>> import roboflow
>>> from roboflow import Roboflow
>>> import supervision as sv

>>> roboflow.login()

>>> rf = Roboflow()

>>> project = rf.workspace(WORKSPACE_ID).project(PROJECT_ID)
>>> dataset = project.version(PROJECT_VERSION).download("folder")

>>> cd = sv.ClassificationDataset.from_folder_structure(
...     root_directory_path=f"{dataset.location}/train"
... )

Source code in supervision/dataset/core.py

@classmethod
def from_folder_structure(cls, root_directory_path: str) -> ClassificationDataset:
    """
    Load data from a multiclass folder structure into a ClassificationDataset.

    Args:
        root_directory_path (str): The path to the dataset directory.

    Returns:
        ClassificationDataset: The dataset.

    Example:
        ```python
        >>> import roboflow
        >>> from roboflow import Roboflow
        >>> import supervision as sv

        >>> roboflow.login()

        >>> rf = Roboflow()

        >>> project = rf.workspace(WORKSPACE_ID).project(PROJECT_ID)
        >>> dataset = project.version(PROJECT_VERSION).download("folder")

        >>> cd = sv.ClassificationDataset.from_folder_structure(
        ...     root_directory_path=f"{dataset.location}/train"
        ... )
        ```
    """
    classes = os.listdir(root_directory_path)
    classes = sorted(set(classes))

    images = {}
    annotations = {}

    for class_name in classes:
        class_id = classes.index(class_name)

        for image in os.listdir(os.path.join(root_directory_path, class_name)):
            image_dir = os.path.join(root_directory_path, class_name, image)
            images[image] = cv2.imread(image_dir)
            annotations[image] = Classifications(
                class_id=np.array([class_id]),
            )

    return cls(
        classes=classes,
        images=images,
        annotations=annotations,
    )

split(split_ratio=0.8, random_state=None, shuffle=True)

Splits the dataset into two parts (training and testing) using the provided split_ratio.

Parameters:

Name	Type	Description	Default
split_ratio	float	The ratio of the training set to the entire dataset.	0.8
random_state	int	The seed for the random number generator. This is used for reproducibility.	None
shuffle	bool	Whether to shuffle the data before splitting.	True

Returns:

Type	Description
Tuple[ClassificationDataset, ClassificationDataset]	Tuple[ClassificationDataset, ClassificationDataset]: A tuple containing the training and testing datasets.

Example

>>> import supervision as sv

>>> cd = sv.ClassificationDataset(...)
>>> train_cd, test_cd = cd.split(split_ratio=0.7, random_state=42, shuffle=True)
>>> len(train_cd), len(test_cd)
(700, 300)

Source code in supervision/dataset/core.py

def split(
    self, split_ratio=0.8, random_state=None, shuffle: bool = True
) -> Tuple[ClassificationDataset, ClassificationDataset]:
    """
    Splits the dataset into two parts (training and testing) using the provided split_ratio.

    Args:
        split_ratio (float, optional): The ratio of the training set to the entire dataset.
        random_state (int, optional): The seed for the random number generator. This is used for reproducibility.
        shuffle (bool, optional): Whether to shuffle the data before splitting.

    Returns:
        Tuple[ClassificationDataset, ClassificationDataset]: A tuple containing the training and testing datasets.

    Example:
        ```python
        >>> import supervision as sv

        >>> cd = sv.ClassificationDataset(...)
        >>> train_cd, test_cd = cd.split(split_ratio=0.7, random_state=42, shuffle=True)
        >>> len(train_cd), len(test_cd)
        (700, 300)
        ```
    """
    image_names = list(self.images.keys())
    train_names, test_names = train_test_split(
        data=image_names,
        train_ratio=split_ratio,
        random_state=random_state,
        shuffle=shuffle,
    )

    train_dataset = ClassificationDataset(
        classes=self.classes,
        images={name: self.images[name] for name in train_names},
        annotations={name: self.annotations[name] for name in train_names},
    )
    test_dataset = ClassificationDataset(
        classes=self.classes,
        images={name: self.images[name] for name in test_names},
        annotations={name: self.annotations[name] for name in test_names},
    )
    return train_dataset, test_dataset