Object Detection

Warning

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

ConfusionMatrix¶

Confusion matrix for object detection tasks.

Attributes:

Name	Type	Description
`matrix`	`ndarray`	An 2D `np.ndarray` of shape `(len(classes) + 1, len(classes) + 1)` containing the number of `TP`, `FP`, `FN` and `TN` for each class.
`classes`	`List[str]`	Model class names.
`conf_threshold`	`float`	Detection confidence threshold between `0` and `1`. Detections with lower confidence will be excluded from the matrix.
`iou_threshold`	`float`	Detection IoU threshold between `0` and `1`. Detections with lower IoU will be classified as `FP`.

Source code in supervision/metrics/detection.py

@dataclass
class ConfusionMatrix:
    """
    Confusion matrix for object detection tasks.

    Attributes:
        matrix (np.ndarray): An 2D `np.ndarray` of shape
            `(len(classes) + 1, len(classes) + 1)`
            containing the number of `TP`, `FP`, `FN` and `TN` for each class.
        classes (List[str]): Model class names.
        conf_threshold (float): Detection confidence threshold between `0` and `1`.
            Detections with lower confidence will be excluded from the matrix.
        iou_threshold (float): Detection IoU threshold between `0` and `1`.
            Detections with lower IoU will be classified as `FP`.
    """

    matrix: np.ndarray
    classes: List[str]
    conf_threshold: float
    iou_threshold: float

    @classmethod
    def from_detections(
        cls,
        predictions: List[Detections],
        targets: List[Detections],
        classes: List[str],
        conf_threshold: float = 0.3,
        iou_threshold: float = 0.5,
    ) -> ConfusionMatrix:
        """
        Calculate confusion matrix based on predicted and ground-truth detections.

        Args:
            targets (List[Detections]): Detections objects from ground-truth.
            predictions (List[Detections]): Detections objects predicted by the model.
            classes (List[str]): Model class names.
            conf_threshold (float): Detection confidence threshold between `0` and `1`.
                Detections with lower confidence will be excluded.
            iou_threshold (float): Detection IoU threshold between `0` and `1`.
                Detections with lower IoU will be classified as `FP`.

        Returns:
            ConfusionMatrix: New instance of ConfusionMatrix.

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

            >>> targets = [
            ...     sv.Detections(...),
            ...     sv.Detections(...)
            ... ]

            >>> predictions = [
            ...     sv.Detections(...),
            ...     sv.Detections(...)
            ... ]

            >>> confusion_matrix = sv.ConfusionMatrix.from_detections(
            ...     predictions=predictions,
            ...     targets=target,
            ...     classes=['person', ...]
            ... )

            >>> confusion_matrix.matrix
            array([
                [0., 0., 0., 0.],
                [0., 1., 0., 1.],
                [0., 1., 1., 0.],
                [1., 1., 0., 0.]
            ])
            ```
        """

        prediction_tensors = []
        target_tensors = []
        for prediction, target in zip(predictions, targets):
            prediction_tensors.append(
                detections_to_tensor(prediction, with_confidence=True)
            )
            target_tensors.append(detections_to_tensor(target, with_confidence=False))
        return cls.from_tensors(
            predictions=prediction_tensors,
            targets=target_tensors,
            classes=classes,
            conf_threshold=conf_threshold,
            iou_threshold=iou_threshold,
        )

    @classmethod
    def from_tensors(
        cls,
        predictions: List[np.ndarray],
        targets: List[np.ndarray],
        classes: List[str],
        conf_threshold: float = 0.3,
        iou_threshold: float = 0.5,
    ) -> ConfusionMatrix:
        """
        Calculate confusion matrix based on predicted and ground-truth detections.

        Args:
            predictions (List[np.ndarray]): Each element of the list describes a single
                image and has `shape = (M, 6)` where `M` is the number of detected
                objects. Each row is expected to be in
                `(x_min, y_min, x_max, y_max, class, conf)` format.
            targets (List[np.ndarray]): Each element of the list describes a single
                image and has `shape = (N, 5)` where `N` is the number of
                ground-truth objects. Each row is expected to be in
                `(x_min, y_min, x_max, y_max, class)` format.
            classes (List[str]): Model class names.
            conf_threshold (float): Detection confidence threshold between `0` and `1`.
                Detections with lower confidence will be excluded.
            iou_threshold (float): Detection iou  threshold between `0` and `1`.
                Detections with lower iou will be classified as `FP`.

        Returns:
            ConfusionMatrix: New instance of ConfusionMatrix.

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

            >>> targets = (
            ...     [
            ...         array(
            ...             [
            ...                 [0.0, 0.0, 3.0, 3.0, 1],
            ...                 [2.0, 2.0, 5.0, 5.0, 1],
            ...                 [6.0, 1.0, 8.0, 3.0, 2],
            ...             ]
            ...         ),
            ...         array([1.0, 1.0, 2.0, 2.0, 2]),
            ...     ]
            ... )

            >>> predictions = [
            ...     array(
            ...         [
            ...             [0.0, 0.0, 3.0, 3.0, 1, 0.9],
            ...             [0.1, 0.1, 3.0, 3.0, 0, 0.9],
            ...             [6.0, 1.0, 8.0, 3.0, 1, 0.8],
            ...             [1.0, 6.0, 2.0, 7.0, 1, 0.8],
            ...         ]
            ...     ),
            ...     array([[1.0, 1.0, 2.0, 2.0, 2, 0.8]])
            ... ]

            >>> confusion_matrix = sv.ConfusionMatrix.from_tensors(
            ...     predictions=predictions,
            ...     targets=targets,
            ...     classes=['person', ...]
            ... )

            >>> confusion_matrix.matrix
            array([
                [0., 0., 0., 0.],
                [0., 1., 0., 1.],
                [0., 1., 1., 0.],
                [1., 1., 0., 0.]
            ])
            ```
        """
        validate_input_tensors(predictions, targets)

        num_classes = len(classes)
        matrix = np.zeros((num_classes + 1, num_classes + 1))
        for true_batch, detection_batch in zip(targets, predictions):
            matrix += cls.evaluate_detection_batch(
                predictions=detection_batch,
                targets=true_batch,
                num_classes=num_classes,
                conf_threshold=conf_threshold,
                iou_threshold=iou_threshold,
            )
        return cls(
            matrix=matrix,
            classes=classes,
            conf_threshold=conf_threshold,
            iou_threshold=iou_threshold,
        )

    @staticmethod
    def evaluate_detection_batch(
        predictions: np.ndarray,
        targets: np.ndarray,
        num_classes: int,
        conf_threshold: float,
        iou_threshold: float,
    ) -> np.ndarray:
        """
        Calculate confusion matrix for a batch of detections for a single image.

        Args:
            predictions (np.ndarray): Batch prediction. Describes a single image and
                has `shape = (M, 6)` where `M` is the number of detected objects.
                Each row is expected to be in
                `(x_min, y_min, x_max, y_max, class, conf)` format.
            targets (np.ndarray): Batch target labels. Describes a single image and
                has `shape = (N, 5)` where `N` is the number of ground-truth objects.
                Each row is expected to be in
                `(x_min, y_min, x_max, y_max, class)` format.
            num_classes (int): Number of classes.
            conf_threshold (float): Detection confidence threshold between `0` and `1`.
                Detections with lower confidence will be excluded.
            iou_threshold (float): Detection iou  threshold between `0` and `1`.
                Detections with lower iou will be classified as `FP`.

        Returns:
            np.ndarray: Confusion matrix based on a single image.
        """
        result_matrix = np.zeros((num_classes + 1, num_classes + 1))

        conf_idx = 5
        confidence = predictions[:, conf_idx]
        detection_batch_filtered = predictions[confidence > conf_threshold]

        class_id_idx = 4
        true_classes = np.array(targets[:, class_id_idx], dtype=np.int16)
        detection_classes = np.array(
            detection_batch_filtered[:, class_id_idx], dtype=np.int16
        )
        true_boxes = targets[:, :class_id_idx]
        detection_boxes = detection_batch_filtered[:, :class_id_idx]

        iou_batch = box_iou_batch(
            boxes_true=true_boxes, boxes_detection=detection_boxes
        )
        matched_idx = np.asarray(iou_batch > iou_threshold).nonzero()

        if matched_idx[0].shape[0]:
            matches = np.stack(
                (matched_idx[0], matched_idx[1], iou_batch[matched_idx]), axis=1
            )
            matches = ConfusionMatrix._drop_extra_matches(matches=matches)
        else:
            matches = np.zeros((0, 3))

        matched_true_idx, matched_detection_idx, _ = matches.transpose().astype(
            np.int16
        )

        for i, true_class_value in enumerate(true_classes):
            j = matched_true_idx == i
            if matches.shape[0] > 0 and sum(j) == 1:
                result_matrix[
                    true_class_value, detection_classes[matched_detection_idx[j]]
                ] += 1  # TP
            else:
                result_matrix[true_class_value, num_classes] += 1  # FN

        for i, detection_class_value in enumerate(detection_classes):
            if not any(matched_detection_idx == i):
                result_matrix[num_classes, detection_class_value] += 1  # FP

        return result_matrix

    @staticmethod
    def _drop_extra_matches(matches: np.ndarray) -> np.ndarray:
        """
        Deduplicate matches. If there are multiple matches for the same true or
        predicted box, only the one with the highest IoU is kept.
        """
        if matches.shape[0] > 0:
            matches = matches[matches[:, 2].argsort()[::-1]]
            matches = matches[np.unique(matches[:, 1], return_index=True)[1]]
            matches = matches[matches[:, 2].argsort()[::-1]]
            matches = matches[np.unique(matches[:, 0], return_index=True)[1]]
        return matches

    @classmethod
    def benchmark(
        cls,
        dataset: DetectionDataset,
        callback: Callable[[np.ndarray], Detections],
        conf_threshold: float = 0.3,
        iou_threshold: float = 0.5,
    ) -> ConfusionMatrix:
        """
        Calculate confusion matrix from dataset and callback function.

        Args:
            dataset (DetectionDataset): Object detection dataset used for evaluation.
            callback (Callable[[np.ndarray], Detections]): Function that takes an image
                as input and returns Detections object.
            conf_threshold (float): Detection confidence threshold between `0` and `1`.
                Detections with lower confidence will be excluded.
            iou_threshold (float): Detection IoU threshold between `0` and `1`.
                Detections with lower IoU will be classified as `FP`.

        Returns:
            ConfusionMatrix: New instance of ConfusionMatrix.

        Example:
            ```python
            >>> import supervision as sv
            >>> from ultralytics import YOLO

            >>> dataset = sv.DetectionDataset.from_yolo(...)

            >>> model = YOLO(...)
            >>> def callback(image: np.ndarray) -> sv.Detections:
            ...     result = model(image)[0]
            ...     return sv.Detections.from_ultralytics(result)

            >>> confusion_matrix = sv.ConfusionMatrix.benchmark(
            ...     dataset = dataset,
            ...     callback = callback
            ... )

            >>> confusion_matrix.matrix
            array([
                [0., 0., 0., 0.],
                [0., 1., 0., 1.],
                [0., 1., 1., 0.],
                [1., 1., 0., 0.]
            ])
            ```
        """
        predictions, targets = [], []
        for img_name, img in dataset.images.items():
            predictions_batch = callback(img)
            predictions.append(predictions_batch)
            targets_batch = dataset.annotations[img_name]
            targets.append(targets_batch)
        return cls.from_detections(
            predictions=predictions,
            targets=targets,
            classes=dataset.classes,
            conf_threshold=conf_threshold,
            iou_threshold=iou_threshold,
        )

    def plot(
        self,
        save_path: Optional[str] = None,
        title: Optional[str] = None,
        classes: Optional[List[str]] = None,
        normalize: bool = False,
        fig_size: Tuple[int, int] = (12, 10),
    ) -> matplotlib.figure.Figure:
        """
        Create confusion matrix plot and save it at selected location.

        Args:
            save_path (Optional[str]): Path to save the plot. If not provided,
                plot will be displayed.
            title (Optional[str]): Title of the plot.
            classes (Optional[List[str]]): List of classes to be displayed on the plot.
                If not provided, all classes will be displayed.
            normalize (bool): If True, normalize the confusion matrix.
            fig_size (Tuple[int, int]): Size of the plot.

        Returns:
            matplotlib.figure.Figure: Confusion matrix plot.
        """

        array = self.matrix.copy()

        if normalize:
            eps = 1e-8
            array = array / (array.sum(0).reshape(1, -1) + eps)

        array[array < 0.005] = np.nan

        fig, ax = plt.subplots(figsize=fig_size, tight_layout=True, facecolor="white")

        class_names = classes if classes is not None else self.classes
        use_labels_for_ticks = class_names is not None and (0 < len(class_names) < 99)
        if use_labels_for_ticks:
            x_tick_labels = class_names + ["FN"]
            y_tick_labels = class_names + ["FP"]
            num_ticks = len(x_tick_labels)
        else:
            x_tick_labels = None
            y_tick_labels = None
            num_ticks = len(array)
        im = ax.imshow(array, cmap="Blues")

        cbar = ax.figure.colorbar(im, ax=ax)
        cbar.mappable.set_clim(vmin=0, vmax=np.nanmax(array))

        if x_tick_labels is None:
            tick_interval = 2
        else:
            tick_interval = 1
        ax.set_xticks(np.arange(0, num_ticks, tick_interval), labels=x_tick_labels)
        ax.set_yticks(np.arange(0, num_ticks, tick_interval), labels=y_tick_labels)

        plt.setp(ax.get_xticklabels(), rotation=90, ha="right", rotation_mode="default")

        labelsize = 10 if num_ticks < 50 else 8
        ax.tick_params(axis="both", which="both", labelsize=labelsize)

        if num_ticks < 30:
            for i in range(array.shape[0]):
                for j in range(array.shape[1]):
                    n_preds = array[i, j]
                    if not np.isnan(n_preds):
                        ax.text(
                            j,
                            i,
                            f"{n_preds:.2f}" if normalize else f"{n_preds:.0f}",
                            ha="center",
                            va="center",
                            color="black"
                            if n_preds < 0.5 * np.nanmax(array)
                            else "white",
                        )

        if title:
            ax.set_title(title, fontsize=20)

        ax.set_xlabel("Predicted")
        ax.set_ylabel("True")
        ax.set_facecolor("white")
        if save_path:
            fig.savefig(
                save_path, dpi=250, facecolor=fig.get_facecolor(), transparent=True
            )
        return fig

`benchmark(dataset, callback, conf_threshold=0.3, iou_threshold=0.5)` `classmethod` ¶

Calculate confusion matrix from dataset and callback function.

Parameters:

Name	Type	Description	Default
`dataset`	`DetectionDataset`	Object detection dataset used for evaluation.	required
`callback`	`Callable[[ndarray], Detections]`	Function that takes an image as input and returns Detections object.	required
`conf_threshold`	`float`	Detection confidence threshold between `0` and `1`. Detections with lower confidence will be excluded.	`0.3`
`iou_threshold`	`float`	Detection IoU threshold between `0` and `1`. Detections with lower IoU will be classified as `FP`.	`0.5`

Returns:

Name	Type	Description
`ConfusionMatrix`	`ConfusionMatrix`	New instance of ConfusionMatrix.

Example

>>> import supervision as sv
>>> from ultralytics import YOLO

>>> dataset = sv.DetectionDataset.from_yolo(...)

>>> model = YOLO(...)
>>> def callback(image: np.ndarray) -> sv.Detections:
...     result = model(image)[0]
...     return sv.Detections.from_ultralytics(result)

>>> confusion_matrix = sv.ConfusionMatrix.benchmark(
...     dataset = dataset,
...     callback = callback
... )

>>> confusion_matrix.matrix
array([
    [0., 0., 0., 0.],
    [0., 1., 0., 1.],
    [0., 1., 1., 0.],
    [1., 1., 0., 0.]
])

Source code in supervision/metrics/detection.py

@classmethod
def benchmark(
    cls,
    dataset: DetectionDataset,
    callback: Callable[[np.ndarray], Detections],
    conf_threshold: float = 0.3,
    iou_threshold: float = 0.5,
) -> ConfusionMatrix:
    """
    Calculate confusion matrix from dataset and callback function.

    Args:
        dataset (DetectionDataset): Object detection dataset used for evaluation.
        callback (Callable[[np.ndarray], Detections]): Function that takes an image
            as input and returns Detections object.
        conf_threshold (float): Detection confidence threshold between `0` and `1`.
            Detections with lower confidence will be excluded.
        iou_threshold (float): Detection IoU threshold between `0` and `1`.
            Detections with lower IoU will be classified as `FP`.

    Returns:
        ConfusionMatrix: New instance of ConfusionMatrix.

    Example:
        ```python
        >>> import supervision as sv
        >>> from ultralytics import YOLO

        >>> dataset = sv.DetectionDataset.from_yolo(...)

        >>> model = YOLO(...)
        >>> def callback(image: np.ndarray) -> sv.Detections:
        ...     result = model(image)[0]
        ...     return sv.Detections.from_ultralytics(result)

        >>> confusion_matrix = sv.ConfusionMatrix.benchmark(
        ...     dataset = dataset,
        ...     callback = callback
        ... )

        >>> confusion_matrix.matrix
        array([
            [0., 0., 0., 0.],
            [0., 1., 0., 1.],
            [0., 1., 1., 0.],
            [1., 1., 0., 0.]
        ])
        ```
    """
    predictions, targets = [], []
    for img_name, img in dataset.images.items():
        predictions_batch = callback(img)
        predictions.append(predictions_batch)
        targets_batch = dataset.annotations[img_name]
        targets.append(targets_batch)
    return cls.from_detections(
        predictions=predictions,
        targets=targets,
        classes=dataset.classes,
        conf_threshold=conf_threshold,
        iou_threshold=iou_threshold,
    )

`evaluate_detection_batch(predictions, targets, num_classes, conf_threshold, iou_threshold)` `staticmethod` ¶

Calculate confusion matrix for a batch of detections for a single image.

Parameters:

Name	Type	Description	Default
`predictions`	`ndarray`	Batch prediction. Describes a single image and has `shape = (M, 6)` where `M` is the number of detected objects. Each row is expected to be in `(x_min, y_min, x_max, y_max, class, conf)` format.	required
`targets`	`ndarray`	Batch target labels. Describes a single image and has `shape = (N, 5)` where `N` is the number of ground-truth objects. Each row is expected to be in `(x_min, y_min, x_max, y_max, class)` format.	required
`num_classes`	`int`	Number of classes.	required
`conf_threshold`	`float`	Detection confidence threshold between `0` and `1`. Detections with lower confidence will be excluded.	required
`iou_threshold`	`float`	Detection iou threshold between `0` and `1`. Detections with lower iou will be classified as `FP`.	required

Returns:

Type	Description
`ndarray`	np.ndarray: Confusion matrix based on a single image.

Source code in supervision/metrics/detection.py

@staticmethod
def evaluate_detection_batch(
    predictions: np.ndarray,
    targets: np.ndarray,
    num_classes: int,
    conf_threshold: float,
    iou_threshold: float,
) -> np.ndarray:
    """
    Calculate confusion matrix for a batch of detections for a single image.

    Args:
        predictions (np.ndarray): Batch prediction. Describes a single image and
            has `shape = (M, 6)` where `M` is the number of detected objects.
            Each row is expected to be in
            `(x_min, y_min, x_max, y_max, class, conf)` format.
        targets (np.ndarray): Batch target labels. Describes a single image and
            has `shape = (N, 5)` where `N` is the number of ground-truth objects.
            Each row is expected to be in
            `(x_min, y_min, x_max, y_max, class)` format.
        num_classes (int): Number of classes.
        conf_threshold (float): Detection confidence threshold between `0` and `1`.
            Detections with lower confidence will be excluded.
        iou_threshold (float): Detection iou  threshold between `0` and `1`.
            Detections with lower iou will be classified as `FP`.

    Returns:
        np.ndarray: Confusion matrix based on a single image.
    """
    result_matrix = np.zeros((num_classes + 1, num_classes + 1))

    conf_idx = 5
    confidence = predictions[:, conf_idx]
    detection_batch_filtered = predictions[confidence > conf_threshold]

    class_id_idx = 4
    true_classes = np.array(targets[:, class_id_idx], dtype=np.int16)
    detection_classes = np.array(
        detection_batch_filtered[:, class_id_idx], dtype=np.int16
    )
    true_boxes = targets[:, :class_id_idx]
    detection_boxes = detection_batch_filtered[:, :class_id_idx]

    iou_batch = box_iou_batch(
        boxes_true=true_boxes, boxes_detection=detection_boxes
    )
    matched_idx = np.asarray(iou_batch > iou_threshold).nonzero()

    if matched_idx[0].shape[0]:
        matches = np.stack(
            (matched_idx[0], matched_idx[1], iou_batch[matched_idx]), axis=1
        )
        matches = ConfusionMatrix._drop_extra_matches(matches=matches)
    else:
        matches = np.zeros((0, 3))

    matched_true_idx, matched_detection_idx, _ = matches.transpose().astype(
        np.int16
    )

    for i, true_class_value in enumerate(true_classes):
        j = matched_true_idx == i
        if matches.shape[0] > 0 and sum(j) == 1:
            result_matrix[
                true_class_value, detection_classes[matched_detection_idx[j]]
            ] += 1  # TP
        else:
            result_matrix[true_class_value, num_classes] += 1  # FN

    for i, detection_class_value in enumerate(detection_classes):
        if not any(matched_detection_idx == i):
            result_matrix[num_classes, detection_class_value] += 1  # FP

    return result_matrix

`from_detections(predictions, targets, classes, conf_threshold=0.3, iou_threshold=0.5)` `classmethod` ¶

Calculate confusion matrix based on predicted and ground-truth detections.

Parameters:

Name	Type	Description	Default
`targets`	`List[Detections]`	Detections objects from ground-truth.	required
`predictions`	`List[Detections]`	Detections objects predicted by the model.	required
`classes`	`List[str]`	Model class names.	required
`conf_threshold`	`float`	Detection confidence threshold between `0` and `1`. Detections with lower confidence will be excluded.	`0.3`
`iou_threshold`	`float`	Detection IoU threshold between `0` and `1`. Detections with lower IoU will be classified as `FP`.	`0.5`

Returns:

Name	Type	Description
`ConfusionMatrix`	`ConfusionMatrix`	New instance of ConfusionMatrix.

Example

>>> import supervision as sv

>>> targets = [
...     sv.Detections(...),
...     sv.Detections(...)
... ]

>>> predictions = [
...     sv.Detections(...),
...     sv.Detections(...)
... ]

>>> confusion_matrix = sv.ConfusionMatrix.from_detections(
...     predictions=predictions,
...     targets=target,
...     classes=['person', ...]
... )

>>> confusion_matrix.matrix
array([
    [0., 0., 0., 0.],
    [0., 1., 0., 1.],
    [0., 1., 1., 0.],
    [1., 1., 0., 0.]
])

Source code in supervision/metrics/detection.py

@classmethod
def from_detections(
    cls,
    predictions: List[Detections],
    targets: List[Detections],
    classes: List[str],
    conf_threshold: float = 0.3,
    iou_threshold: float = 0.5,
) -> ConfusionMatrix:
    """
    Calculate confusion matrix based on predicted and ground-truth detections.

    Args:
        targets (List[Detections]): Detections objects from ground-truth.
        predictions (List[Detections]): Detections objects predicted by the model.
        classes (List[str]): Model class names.
        conf_threshold (float): Detection confidence threshold between `0` and `1`.
            Detections with lower confidence will be excluded.
        iou_threshold (float): Detection IoU threshold between `0` and `1`.
            Detections with lower IoU will be classified as `FP`.

    Returns:
        ConfusionMatrix: New instance of ConfusionMatrix.

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

        >>> targets = [
        ...     sv.Detections(...),
        ...     sv.Detections(...)
        ... ]

        >>> predictions = [
        ...     sv.Detections(...),
        ...     sv.Detections(...)
        ... ]

        >>> confusion_matrix = sv.ConfusionMatrix.from_detections(
        ...     predictions=predictions,
        ...     targets=target,
        ...     classes=['person', ...]
        ... )

        >>> confusion_matrix.matrix
        array([
            [0., 0., 0., 0.],
            [0., 1., 0., 1.],
            [0., 1., 1., 0.],
            [1., 1., 0., 0.]
        ])
        ```
    """

    prediction_tensors = []
    target_tensors = []
    for prediction, target in zip(predictions, targets):
        prediction_tensors.append(
            detections_to_tensor(prediction, with_confidence=True)
        )
        target_tensors.append(detections_to_tensor(target, with_confidence=False))
    return cls.from_tensors(
        predictions=prediction_tensors,
        targets=target_tensors,
        classes=classes,
        conf_threshold=conf_threshold,
        iou_threshold=iou_threshold,
    )

`from_tensors(predictions, targets, classes, conf_threshold=0.3, iou_threshold=0.5)` `classmethod` ¶

Calculate confusion matrix based on predicted and ground-truth detections.

Parameters:

Name	Type	Description	Default
`predictions`	`List[ndarray]`	Each element of the list describes a single image and has `shape = (M, 6)` where `M` is the number of detected objects. Each row is expected to be in `(x_min, y_min, x_max, y_max, class, conf)` format.	required
`targets`	`List[ndarray]`	Each element of the list describes a single image and has `shape = (N, 5)` where `N` is the number of ground-truth objects. Each row is expected to be in `(x_min, y_min, x_max, y_max, class)` format.	required
`classes`	`List[str]`	Model class names.	required
`conf_threshold`	`float`	Detection confidence threshold between `0` and `1`. Detections with lower confidence will be excluded.	`0.3`
`iou_threshold`	`float`	Detection iou threshold between `0` and `1`. Detections with lower iou will be classified as `FP`.	`0.5`

Returns:

Name	Type	Description
`ConfusionMatrix`	`ConfusionMatrix`	New instance of ConfusionMatrix.

Example

>>> import supervision as sv

>>> targets = (
...     [
...         array(
...             [
...                 [0.0, 0.0, 3.0, 3.0, 1],
...                 [2.0, 2.0, 5.0, 5.0, 1],
...                 [6.0, 1.0, 8.0, 3.0, 2],
...             ]
...         ),
...         array([1.0, 1.0, 2.0, 2.0, 2]),
...     ]
... )

>>> predictions = [
...     array(
...         [
...             [0.0, 0.0, 3.0, 3.0, 1, 0.9],
...             [0.1, 0.1, 3.0, 3.0, 0, 0.9],
...             [6.0, 1.0, 8.0, 3.0, 1, 0.8],
...             [1.0, 6.0, 2.0, 7.0, 1, 0.8],
...         ]
...     ),
...     array([[1.0, 1.0, 2.0, 2.0, 2, 0.8]])
... ]

>>> confusion_matrix = sv.ConfusionMatrix.from_tensors(
...     predictions=predictions,
...     targets=targets,
...     classes=['person', ...]
... )

>>> confusion_matrix.matrix
array([
    [0., 0., 0., 0.],
    [0., 1., 0., 1.],
    [0., 1., 1., 0.],
    [1., 1., 0., 0.]
])

Source code in supervision/metrics/detection.py

@classmethod
def from_tensors(
    cls,
    predictions: List[np.ndarray],
    targets: List[np.ndarray],
    classes: List[str],
    conf_threshold: float = 0.3,
    iou_threshold: float = 0.5,
) -> ConfusionMatrix:
    """
    Calculate confusion matrix based on predicted and ground-truth detections.

    Args:
        predictions (List[np.ndarray]): Each element of the list describes a single
            image and has `shape = (M, 6)` where `M` is the number of detected
            objects. Each row is expected to be in
            `(x_min, y_min, x_max, y_max, class, conf)` format.
        targets (List[np.ndarray]): Each element of the list describes a single
            image and has `shape = (N, 5)` where `N` is the number of
            ground-truth objects. Each row is expected to be in
            `(x_min, y_min, x_max, y_max, class)` format.
        classes (List[str]): Model class names.
        conf_threshold (float): Detection confidence threshold between `0` and `1`.
            Detections with lower confidence will be excluded.
        iou_threshold (float): Detection iou  threshold between `0` and `1`.
            Detections with lower iou will be classified as `FP`.

    Returns:
        ConfusionMatrix: New instance of ConfusionMatrix.

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

        >>> targets = (
        ...     [
        ...         array(
        ...             [
        ...                 [0.0, 0.0, 3.0, 3.0, 1],
        ...                 [2.0, 2.0, 5.0, 5.0, 1],
        ...                 [6.0, 1.0, 8.0, 3.0, 2],
        ...             ]
        ...         ),
        ...         array([1.0, 1.0, 2.0, 2.0, 2]),
        ...     ]
        ... )

        >>> predictions = [
        ...     array(
        ...         [
        ...             [0.0, 0.0, 3.0, 3.0, 1, 0.9],
        ...             [0.1, 0.1, 3.0, 3.0, 0, 0.9],
        ...             [6.0, 1.0, 8.0, 3.0, 1, 0.8],
        ...             [1.0, 6.0, 2.0, 7.0, 1, 0.8],
        ...         ]
        ...     ),
        ...     array([[1.0, 1.0, 2.0, 2.0, 2, 0.8]])
        ... ]

        >>> confusion_matrix = sv.ConfusionMatrix.from_tensors(
        ...     predictions=predictions,
        ...     targets=targets,
        ...     classes=['person', ...]
        ... )

        >>> confusion_matrix.matrix
        array([
            [0., 0., 0., 0.],
            [0., 1., 0., 1.],
            [0., 1., 1., 0.],
            [1., 1., 0., 0.]
        ])
        ```
    """
    validate_input_tensors(predictions, targets)

    num_classes = len(classes)
    matrix = np.zeros((num_classes + 1, num_classes + 1))
    for true_batch, detection_batch in zip(targets, predictions):
        matrix += cls.evaluate_detection_batch(
            predictions=detection_batch,
            targets=true_batch,
            num_classes=num_classes,
            conf_threshold=conf_threshold,
            iou_threshold=iou_threshold,
        )
    return cls(
        matrix=matrix,
        classes=classes,
        conf_threshold=conf_threshold,
        iou_threshold=iou_threshold,
    )

`plot(save_path=None, title=None, classes=None, normalize=False, fig_size=(12, 10))` ¶

Create confusion matrix plot and save it at selected location.

Parameters:

Name	Type	Description	Default
`save_path`	`Optional[str]`	Path to save the plot. If not provided, plot will be displayed.	`None`
`title`	`Optional[str]`	Title of the plot.	`None`
`classes`	`Optional[List[str]]`	List of classes to be displayed on the plot. If not provided, all classes will be displayed.	`None`
`normalize`	`bool`	If True, normalize the confusion matrix.	`False`
`fig_size`	`Tuple[int, int]`	Size of the plot.	`(12, 10)`

Returns:

Type	Description
`Figure`	matplotlib.figure.Figure: Confusion matrix plot.

Source code in supervision/metrics/detection.py

def plot(
    self,
    save_path: Optional[str] = None,
    title: Optional[str] = None,
    classes: Optional[List[str]] = None,
    normalize: bool = False,
    fig_size: Tuple[int, int] = (12, 10),
) -> matplotlib.figure.Figure:
    """
    Create confusion matrix plot and save it at selected location.

    Args:
        save_path (Optional[str]): Path to save the plot. If not provided,
            plot will be displayed.
        title (Optional[str]): Title of the plot.
        classes (Optional[List[str]]): List of classes to be displayed on the plot.
            If not provided, all classes will be displayed.
        normalize (bool): If True, normalize the confusion matrix.
        fig_size (Tuple[int, int]): Size of the plot.

    Returns:
        matplotlib.figure.Figure: Confusion matrix plot.
    """

    array = self.matrix.copy()

    if normalize:
        eps = 1e-8
        array = array / (array.sum(0).reshape(1, -1) + eps)

    array[array < 0.005] = np.nan

    fig, ax = plt.subplots(figsize=fig_size, tight_layout=True, facecolor="white")

    class_names = classes if classes is not None else self.classes
    use_labels_for_ticks = class_names is not None and (0 < len(class_names) < 99)
    if use_labels_for_ticks:
        x_tick_labels = class_names + ["FN"]
        y_tick_labels = class_names + ["FP"]
        num_ticks = len(x_tick_labels)
    else:
        x_tick_labels = None
        y_tick_labels = None
        num_ticks = len(array)
    im = ax.imshow(array, cmap="Blues")

    cbar = ax.figure.colorbar(im, ax=ax)
    cbar.mappable.set_clim(vmin=0, vmax=np.nanmax(array))

    if x_tick_labels is None:
        tick_interval = 2
    else:
        tick_interval = 1
    ax.set_xticks(np.arange(0, num_ticks, tick_interval), labels=x_tick_labels)
    ax.set_yticks(np.arange(0, num_ticks, tick_interval), labels=y_tick_labels)

    plt.setp(ax.get_xticklabels(), rotation=90, ha="right", rotation_mode="default")

    labelsize = 10 if num_ticks < 50 else 8
    ax.tick_params(axis="both", which="both", labelsize=labelsize)

    if num_ticks < 30:
        for i in range(array.shape[0]):
            for j in range(array.shape[1]):
                n_preds = array[i, j]
                if not np.isnan(n_preds):
                    ax.text(
                        j,
                        i,
                        f"{n_preds:.2f}" if normalize else f"{n_preds:.0f}",
                        ha="center",
                        va="center",
                        color="black"
                        if n_preds < 0.5 * np.nanmax(array)
                        else "white",
                    )

    if title:
        ax.set_title(title, fontsize=20)

    ax.set_xlabel("Predicted")
    ax.set_ylabel("True")
    ax.set_facecolor("white")
    if save_path:
        fig.savefig(
            save_path, dpi=250, facecolor=fig.get_facecolor(), transparent=True
        )
    return fig

MeanAveragePrecision¶

Mean Average Precision for object detection tasks.

Attributes:

Name	Type	Description
`map50_95`	`float`	Mean Average Precision (mAP) calculated over IoU thresholds ranging from `0.50` to `0.95` with a step size of `0.05`.
`map50`	`float`	Mean Average Precision (mAP) calculated specifically at an IoU threshold of `0.50`.
`map75`	`float`	Mean Average Precision (mAP) calculated specifically at an IoU threshold of `0.75`.
`per_class_ap50_95`	`ndarray`	Average Precision (AP) values calculated over IoU thresholds ranging from `0.50` to `0.95` with a step size of `0.05`, provided for each individual class.

Source code in supervision/metrics/detection.py

@dataclass(frozen=True)
class MeanAveragePrecision:
    """
    Mean Average Precision for object detection tasks.

    Attributes:
        map50_95 (float): Mean Average Precision (mAP) calculated over IoU thresholds
            ranging from `0.50` to `0.95` with a step size of `0.05`.
        map50 (float): Mean Average Precision (mAP) calculated specifically at
            an IoU threshold of `0.50`.
        map75 (float): Mean Average Precision (mAP) calculated specifically at
            an IoU threshold of `0.75`.
        per_class_ap50_95 (np.ndarray): Average Precision (AP) values calculated over
            IoU thresholds ranging from `0.50` to `0.95` with a step size of `0.05`,
            provided for each individual class.
    """

    map50_95: float
    map50: float
    map75: float
    per_class_ap50_95: np.ndarray

    @classmethod
    def from_detections(
        cls,
        predictions: List[Detections],
        targets: List[Detections],
    ) -> MeanAveragePrecision:
        """
        Calculate mean average precision based on predicted and ground-truth detections.

        Args:
            targets (List[Detections]): Detections objects from ground-truth.
            predictions (List[Detections]): Detections objects predicted by the model.
        Returns:
            MeanAveragePrecision: New instance of ConfusionMatrix.

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

            >>> targets = [
            ...     sv.Detections(...),
            ...     sv.Detections(...)
            ... ]

            >>> predictions = [
            ...     sv.Detections(...),
            ...     sv.Detections(...)
            ... ]

            >>> mean_average_precision = sv.MeanAveragePrecision.from_detections(
            ...     predictions=predictions,
            ...     targets=target,
            ... )

            >>> mean_average_precison.map50_95
            0.2899
            ```
        """
        prediction_tensors = []
        target_tensors = []
        for prediction, target in zip(predictions, targets):
            prediction_tensors.append(
                detections_to_tensor(prediction, with_confidence=True)
            )
            target_tensors.append(detections_to_tensor(target, with_confidence=False))
        return cls.from_tensors(
            predictions=prediction_tensors,
            targets=target_tensors,
        )

    @classmethod
    def benchmark(
        cls,
        dataset: DetectionDataset,
        callback: Callable[[np.ndarray], Detections],
    ) -> MeanAveragePrecision:
        """
        Calculate mean average precision from dataset and callback function.

        Args:
            dataset (DetectionDataset): Object detection dataset used for evaluation.
            callback (Callable[[np.ndarray], Detections]): Function that takes
                an image as input and returns Detections object.
        Returns:
            MeanAveragePrecision: New instance of MeanAveragePrecision.

        Example:
            ```python
            >>> import supervision as sv
            >>> from ultralytics import YOLO

            >>> dataset = sv.DetectionDataset.from_yolo(...)

            >>> model = YOLO(...)
            >>> def callback(image: np.ndarray) -> sv.Detections:
            ...     result = model(image)[0]
            ...     return sv.Detections.from_ultralytics(result)

            >>> mean_average_precision = sv.MeanAveragePrecision.benchmark(
            ...     dataset = dataset,
            ...     callback = callback
            ... )

            >>> mean_average_precision.map50_95
            0.433
            ```
        """
        predictions, targets = [], []
        for img_name, img in dataset.images.items():
            predictions_batch = callback(img)
            predictions.append(predictions_batch)
            targets_batch = dataset.annotations[img_name]
            targets.append(targets_batch)
        return cls.from_detections(
            predictions=predictions,
            targets=targets,
        )

    @classmethod
    def from_tensors(
        cls,
        predictions: List[np.ndarray],
        targets: List[np.ndarray],
    ) -> MeanAveragePrecision:
        """
        Calculate Mean Average Precision based on predicted and ground-truth
            detections at different threshold.

        Args:
            predictions (List[np.ndarray]): Each element of the list describes
                a single image and has `shape = (M, 6)` where `M` is
                the number of detected objects. Each row is expected to be
                in `(x_min, y_min, x_max, y_max, class, conf)` format.
            targets (List[np.ndarray]): Each element of the list describes a single
                image and has `shape = (N, 5)` where `N` is the
                number of ground-truth objects. Each row is expected to be in
                `(x_min, y_min, x_max, y_max, class)` format.
        Returns:
            MeanAveragePrecision: New instance of MeanAveragePrecision.

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

            >>> targets = (
            ...     [
            ...         array(
            ...             [
            ...                 [0.0, 0.0, 3.0, 3.0, 1],
            ...                 [2.0, 2.0, 5.0, 5.0, 1],
            ...                 [6.0, 1.0, 8.0, 3.0, 2],
            ...             ]
            ...         ),
            ...         array([1.0, 1.0, 2.0, 2.0, 2]),
            ...     ]
            ... )

            >>> predictions = [
            ...     array(
            ...         [
            ...             [0.0, 0.0, 3.0, 3.0, 1, 0.9],
            ...             [0.1, 0.1, 3.0, 3.0, 0, 0.9],
            ...             [6.0, 1.0, 8.0, 3.0, 1, 0.8],
            ...             [1.0, 6.0, 2.0, 7.0, 1, 0.8],
            ...         ]
            ...     ),
            ...     array([[1.0, 1.0, 2.0, 2.0, 2, 0.8]])
            ... ]

            >>> mean_average_precison = sv.MeanAveragePrecision.from_tensors(
            ...     predictions=predictions,
            ...     targets=targets,
            ... )

            >>> mean_average_precison.map50_95
            0.2899
            ```
        """
        validate_input_tensors(predictions, targets)
        iou_thresholds = np.linspace(0.5, 0.95, 10)
        stats = []

        # Gather matching stats for predictions and targets
        for true_objs, predicted_objs in zip(targets, predictions):
            if predicted_objs.shape[0] == 0:
                if true_objs.shape[0]:
                    stats.append(
                        (
                            np.zeros((0, iou_thresholds.size), dtype=bool),
                            *np.zeros((2, 0)),
                            true_objs[:, 4],
                        )
                    )
                continue

            if true_objs.shape[0]:
                matches = cls._match_detection_batch(
                    predicted_objs, true_objs, iou_thresholds
                )
                stats.append(
                    (
                        matches,
                        predicted_objs[:, 5],
                        predicted_objs[:, 4],
                        true_objs[:, 4],
                    )
                )

        # Compute average precisions if any matches exist
        if stats:
            concatenated_stats = [np.concatenate(items, 0) for items in zip(*stats)]
            average_precisions = cls._average_precisions_per_class(*concatenated_stats)
            map50 = average_precisions[:, 0].mean()
            map75 = average_precisions[:, 5].mean()
            map50_95 = average_precisions.mean()
        else:
            map50, map75, map50_95 = 0, 0, 0
            average_precisions = []

        return cls(
            map50_95=map50_95,
            map50=map50,
            map75=map75,
            per_class_ap50_95=average_precisions,
        )

    @staticmethod
    def compute_average_precision(recall: np.ndarray, precision: np.ndarray) -> float:
        """
        Compute the average precision using 101-point interpolation (COCO), given
            the recall and precision curves.

        Args:
            recall (np.ndarray): The recall curve.
            precision (np.ndarray): The precision curve.

        Returns:
            float: Average precision.
        """
        extended_recall = np.concatenate(([0.0], recall, [1.0]))
        extended_precision = np.concatenate(([1.0], precision, [0.0]))
        max_accumulated_precision = np.flip(
            np.maximum.accumulate(np.flip(extended_precision))
        )
        interpolated_recall_levels = np.linspace(0, 1, 101)
        interpolated_precision = np.interp(
            interpolated_recall_levels, extended_recall, max_accumulated_precision
        )
        average_precision = np.trapz(interpolated_precision, interpolated_recall_levels)
        return average_precision

    @staticmethod
    def _match_detection_batch(
        predictions: np.ndarray, targets: np.ndarray, iou_thresholds: np.ndarray
    ) -> np.ndarray:
        """
        Match predictions with target labels based on IoU levels.

        Args:
            predictions (np.ndarray): Batch prediction. Describes a single image and
                has `shape = (M, 6)` where `M` is the number of detected objects.
                Each row is expected to be in
                `(x_min, y_min, x_max, y_max, class, conf)` format.
            targets (np.ndarray): Batch target labels. Describes a single image and
                has `shape = (N, 5)` where `N` is the number of ground-truth objects.
                Each row is expected to be in
                `(x_min, y_min, x_max, y_max, class)` format.
            iou_thresholds (np.ndarray): Array contains different IoU thresholds.

        Returns:
            np.ndarray: Matched prediction with target labels result.
        """
        num_predictions, num_iou_levels = predictions.shape[0], iou_thresholds.shape[0]
        correct = np.zeros((num_predictions, num_iou_levels), dtype=bool)
        iou = box_iou_batch(targets[:, :4], predictions[:, :4])
        correct_class = targets[:, 4:5] == predictions[:, 4]

        for i, iou_level in enumerate(iou_thresholds):
            matched_indices = np.where((iou >= iou_level) & correct_class)

            if matched_indices[0].shape[0]:
                combined_indices = np.stack(matched_indices, axis=1)
                iou_values = iou[matched_indices][:, None]
                matches = np.hstack([combined_indices, iou_values])

                if matched_indices[0].shape[0] > 1:
                    matches = matches[matches[:, 2].argsort()[::-1]]
                    matches = matches[np.unique(matches[:, 1], return_index=True)[1]]
                    matches = matches[np.unique(matches[:, 0], return_index=True)[1]]

                correct[matches[:, 1].astype(int), i] = True

        return correct

    @staticmethod
    def _average_precisions_per_class(
        matches: np.ndarray,
        prediction_confidence: np.ndarray,
        prediction_class_ids: np.ndarray,
        true_class_ids: np.ndarray,
        eps: float = 1e-16,
    ) -> np.ndarray:
        """
        Compute the average precision, given the recall and precision curves.
        Source: https://github.com/rafaelpadilla/Object-Detection-Metrics.

        Args:
            matches (np.ndarray): True positives.
            prediction_confidence (np.ndarray): Objectness value from 0-1.
            prediction_class_ids (np.ndarray): Predicted object classes.
            true_class_ids (np.ndarray): True object classes.
            eps (float, optional): Small value to prevent division by zero.

        Returns:
            np.ndarray: Average precision for different IoU levels.
        """
        sorted_indices = np.argsort(-prediction_confidence)
        matches = matches[sorted_indices]
        prediction_class_ids = prediction_class_ids[sorted_indices]

        unique_classes, class_counts = np.unique(true_class_ids, return_counts=True)
        num_classes = unique_classes.shape[0]

        average_precisions = np.zeros((num_classes, matches.shape[1]))

        for class_idx, class_id in enumerate(unique_classes):
            is_class = prediction_class_ids == class_id
            total_true = class_counts[class_idx]
            total_prediction = is_class.sum()

            if total_prediction == 0 or total_true == 0:
                continue

            false_positives = (1 - matches[is_class]).cumsum(0)
            true_positives = matches[is_class].cumsum(0)
            recall = true_positives / (total_true + eps)
            precision = true_positives / (true_positives + false_positives)

            for iou_level_idx in range(matches.shape[1]):
                average_precisions[
                    class_idx, iou_level_idx
                ] = MeanAveragePrecision.compute_average_precision(
                    recall[:, iou_level_idx], precision[:, iou_level_idx]
                )

        return average_precisions

`benchmark(dataset, callback)` `classmethod` ¶

Calculate mean average precision from dataset and callback function.

Parameters:

Name	Type	Description	Default
`dataset`	`DetectionDataset`	Object detection dataset used for evaluation.	required
`callback`	`Callable[[ndarray], Detections]`	Function that takes an image as input and returns Detections object.	required

Returns: MeanAveragePrecision: New instance of MeanAveragePrecision.

Example

>>> import supervision as sv
>>> from ultralytics import YOLO

>>> dataset = sv.DetectionDataset.from_yolo(...)

>>> model = YOLO(...)
>>> def callback(image: np.ndarray) -> sv.Detections:
...     result = model(image)[0]
...     return sv.Detections.from_ultralytics(result)

>>> mean_average_precision = sv.MeanAveragePrecision.benchmark(
...     dataset = dataset,
...     callback = callback
... )

>>> mean_average_precision.map50_95
0.433

Source code in supervision/metrics/detection.py

@classmethod
def benchmark(
    cls,
    dataset: DetectionDataset,
    callback: Callable[[np.ndarray], Detections],
) -> MeanAveragePrecision:
    """
    Calculate mean average precision from dataset and callback function.

    Args:
        dataset (DetectionDataset): Object detection dataset used for evaluation.
        callback (Callable[[np.ndarray], Detections]): Function that takes
            an image as input and returns Detections object.
    Returns:
        MeanAveragePrecision: New instance of MeanAveragePrecision.

    Example:
        ```python
        >>> import supervision as sv
        >>> from ultralytics import YOLO

        >>> dataset = sv.DetectionDataset.from_yolo(...)

        >>> model = YOLO(...)
        >>> def callback(image: np.ndarray) -> sv.Detections:
        ...     result = model(image)[0]
        ...     return sv.Detections.from_ultralytics(result)

        >>> mean_average_precision = sv.MeanAveragePrecision.benchmark(
        ...     dataset = dataset,
        ...     callback = callback
        ... )

        >>> mean_average_precision.map50_95
        0.433
        ```
    """
    predictions, targets = [], []
    for img_name, img in dataset.images.items():
        predictions_batch = callback(img)
        predictions.append(predictions_batch)
        targets_batch = dataset.annotations[img_name]
        targets.append(targets_batch)
    return cls.from_detections(
        predictions=predictions,
        targets=targets,
    )

`compute_average_precision(recall, precision)` `staticmethod` ¶

Compute the average precision using 101-point interpolation (COCO), given the recall and precision curves.

Parameters:

Name	Type	Description	Default
`recall`	`ndarray`	The recall curve.	required
`precision`	`ndarray`	The precision curve.	required

Returns:

Name	Type	Description
`float`	`float`	Average precision.

Source code in supervision/metrics/detection.py

@staticmethod
def compute_average_precision(recall: np.ndarray, precision: np.ndarray) -> float:
    """
    Compute the average precision using 101-point interpolation (COCO), given
        the recall and precision curves.

    Args:
        recall (np.ndarray): The recall curve.
        precision (np.ndarray): The precision curve.

    Returns:
        float: Average precision.
    """
    extended_recall = np.concatenate(([0.0], recall, [1.0]))
    extended_precision = np.concatenate(([1.0], precision, [0.0]))
    max_accumulated_precision = np.flip(
        np.maximum.accumulate(np.flip(extended_precision))
    )
    interpolated_recall_levels = np.linspace(0, 1, 101)
    interpolated_precision = np.interp(
        interpolated_recall_levels, extended_recall, max_accumulated_precision
    )
    average_precision = np.trapz(interpolated_precision, interpolated_recall_levels)
    return average_precision

`from_detections(predictions, targets)` `classmethod` ¶

Calculate mean average precision based on predicted and ground-truth detections.

Parameters:

Name	Type	Description	Default
`targets`	`List[Detections]`	Detections objects from ground-truth.	required
`predictions`	`List[Detections]`	Detections objects predicted by the model.	required

Returns: MeanAveragePrecision: New instance of ConfusionMatrix.

Example

>>> import supervision as sv

>>> targets = [
...     sv.Detections(...),
...     sv.Detections(...)
... ]

>>> predictions = [
...     sv.Detections(...),
...     sv.Detections(...)
... ]

>>> mean_average_precision = sv.MeanAveragePrecision.from_detections(
...     predictions=predictions,
...     targets=target,
... )

>>> mean_average_precison.map50_95
0.2899

Source code in supervision/metrics/detection.py

@classmethod
def from_detections(
    cls,
    predictions: List[Detections],
    targets: List[Detections],
) -> MeanAveragePrecision:
    """
    Calculate mean average precision based on predicted and ground-truth detections.

    Args:
        targets (List[Detections]): Detections objects from ground-truth.
        predictions (List[Detections]): Detections objects predicted by the model.
    Returns:
        MeanAveragePrecision: New instance of ConfusionMatrix.

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

        >>> targets = [
        ...     sv.Detections(...),
        ...     sv.Detections(...)
        ... ]

        >>> predictions = [
        ...     sv.Detections(...),
        ...     sv.Detections(...)
        ... ]

        >>> mean_average_precision = sv.MeanAveragePrecision.from_detections(
        ...     predictions=predictions,
        ...     targets=target,
        ... )

        >>> mean_average_precison.map50_95
        0.2899
        ```
    """
    prediction_tensors = []
    target_tensors = []
    for prediction, target in zip(predictions, targets):
        prediction_tensors.append(
            detections_to_tensor(prediction, with_confidence=True)
        )
        target_tensors.append(detections_to_tensor(target, with_confidence=False))
    return cls.from_tensors(
        predictions=prediction_tensors,
        targets=target_tensors,
    )

`from_tensors(predictions, targets)` `classmethod` ¶

Calculate Mean Average Precision based on predicted and ground-truth detections at different threshold.

Parameters:

Name	Type	Description	Default
`predictions`	`List[ndarray]`	Each element of the list describes a single image and has `shape = (M, 6)` where `M` is the number of detected objects. Each row is expected to be in `(x_min, y_min, x_max, y_max, class, conf)` format.	required
`targets`	`List[ndarray]`	Each element of the list describes a single image and has `shape = (N, 5)` where `N` is the number of ground-truth objects. Each row is expected to be in `(x_min, y_min, x_max, y_max, class)` format.	required

Returns: MeanAveragePrecision: New instance of MeanAveragePrecision.

Example

>>> import supervision as sv

>>> targets = (
...     [
...         array(
...             [
...                 [0.0, 0.0, 3.0, 3.0, 1],
...                 [2.0, 2.0, 5.0, 5.0, 1],
...                 [6.0, 1.0, 8.0, 3.0, 2],
...             ]
...         ),
...         array([1.0, 1.0, 2.0, 2.0, 2]),
...     ]
... )

>>> predictions = [
...     array(
...         [
...             [0.0, 0.0, 3.0, 3.0, 1, 0.9],
...             [0.1, 0.1, 3.0, 3.0, 0, 0.9],
...             [6.0, 1.0, 8.0, 3.0, 1, 0.8],
...             [1.0, 6.0, 2.0, 7.0, 1, 0.8],
...         ]
...     ),
...     array([[1.0, 1.0, 2.0, 2.0, 2, 0.8]])
... ]

>>> mean_average_precison = sv.MeanAveragePrecision.from_tensors(
...     predictions=predictions,
...     targets=targets,
... )

>>> mean_average_precison.map50_95
0.2899

Source code in supervision/metrics/detection.py

@classmethod
def from_tensors(
    cls,
    predictions: List[np.ndarray],
    targets: List[np.ndarray],
) -> MeanAveragePrecision:
    """
    Calculate Mean Average Precision based on predicted and ground-truth
        detections at different threshold.

    Args:
        predictions (List[np.ndarray]): Each element of the list describes
            a single image and has `shape = (M, 6)` where `M` is
            the number of detected objects. Each row is expected to be
            in `(x_min, y_min, x_max, y_max, class, conf)` format.
        targets (List[np.ndarray]): Each element of the list describes a single
            image and has `shape = (N, 5)` where `N` is the
            number of ground-truth objects. Each row is expected to be in
            `(x_min, y_min, x_max, y_max, class)` format.
    Returns:
        MeanAveragePrecision: New instance of MeanAveragePrecision.

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

        >>> targets = (
        ...     [
        ...         array(
        ...             [
        ...                 [0.0, 0.0, 3.0, 3.0, 1],
        ...                 [2.0, 2.0, 5.0, 5.0, 1],
        ...                 [6.0, 1.0, 8.0, 3.0, 2],
        ...             ]
        ...         ),
        ...         array([1.0, 1.0, 2.0, 2.0, 2]),
        ...     ]
        ... )

        >>> predictions = [
        ...     array(
        ...         [
        ...             [0.0, 0.0, 3.0, 3.0, 1, 0.9],
        ...             [0.1, 0.1, 3.0, 3.0, 0, 0.9],
        ...             [6.0, 1.0, 8.0, 3.0, 1, 0.8],
        ...             [1.0, 6.0, 2.0, 7.0, 1, 0.8],
        ...         ]
        ...     ),
        ...     array([[1.0, 1.0, 2.0, 2.0, 2, 0.8]])
        ... ]

        >>> mean_average_precison = sv.MeanAveragePrecision.from_tensors(
        ...     predictions=predictions,
        ...     targets=targets,
        ... )

        >>> mean_average_precison.map50_95
        0.2899
        ```
    """
    validate_input_tensors(predictions, targets)
    iou_thresholds = np.linspace(0.5, 0.95, 10)
    stats = []

    # Gather matching stats for predictions and targets
    for true_objs, predicted_objs in zip(targets, predictions):
        if predicted_objs.shape[0] == 0:
            if true_objs.shape[0]:
                stats.append(
                    (
                        np.zeros((0, iou_thresholds.size), dtype=bool),
                        *np.zeros((2, 0)),
                        true_objs[:, 4],
                    )
                )
            continue

        if true_objs.shape[0]:
            matches = cls._match_detection_batch(
                predicted_objs, true_objs, iou_thresholds
            )
            stats.append(
                (
                    matches,
                    predicted_objs[:, 5],
                    predicted_objs[:, 4],
                    true_objs[:, 4],
                )
            )

    # Compute average precisions if any matches exist
    if stats:
        concatenated_stats = [np.concatenate(items, 0) for items in zip(*stats)]
        average_precisions = cls._average_precisions_per_class(*concatenated_stats)
        map50 = average_precisions[:, 0].mean()
        map75 = average_precisions[:, 5].mean()
        map50_95 = average_precisions.mean()
    else:
        map50, map75, map50_95 = 0, 0, 0
        average_precisions = []

    return cls(
        map50_95=map50_95,
        map50=map50,
        map75=map75,
        per_class_ap50_95=average_precisions,
    )

Object Detection

ConfusionMatrix¶

benchmark(dataset, callback, conf_threshold=0.3, iou_threshold=0.5) classmethod ¶

evaluate_detection_batch(predictions, targets, num_classes, conf_threshold, iou_threshold) staticmethod ¶

from_detections(predictions, targets, classes, conf_threshold=0.3, iou_threshold=0.5) classmethod ¶

from_tensors(predictions, targets, classes, conf_threshold=0.3, iou_threshold=0.5) classmethod ¶

plot(save_path=None, title=None, classes=None, normalize=False, fig_size=(12, 10)) ¶

MeanAveragePrecision¶

benchmark(dataset, callback) classmethod ¶

compute_average_precision(recall, precision) staticmethod ¶

from_detections(predictions, targets) classmethod ¶

from_tensors(predictions, targets) classmethod ¶

`benchmark(dataset, callback, conf_threshold=0.3, iou_threshold=0.5)` `classmethod` ¶

`evaluate_detection_batch(predictions, targets, num_classes, conf_threshold, iou_threshold)` `staticmethod` ¶

`from_detections(predictions, targets, classes, conf_threshold=0.3, iou_threshold=0.5)` `classmethod` ¶

`from_tensors(predictions, targets, classes, conf_threshold=0.3, iou_threshold=0.5)` `classmethod` ¶

`plot(save_path=None, title=None, classes=None, normalize=False, fig_size=(12, 10))` ¶

`benchmark(dataset, callback)` `classmethod` ¶

`compute_average_precision(recall, precision)` `staticmethod` ¶

`from_detections(predictions, targets)` `classmethod` ¶

`from_tensors(predictions, targets)` `classmethod` ¶