参考 ultralytics/utils/metrics.py

class ConfusionMatrix:
    """
    A class for calculating and updating a confusion matrix for object detection and classification tasks.

    Attributes:
        task (str): The type of task, either 'detect' or 'classify'.
        matrix (np.ndarray): The confusion matrix, with dimensions depending on the task.
        nc (int): The number of classes.
        conf (float): The confidence threshold for detections.
        iou_thres (float): The Intersection over Union threshold.
    """

    def __init__(self, nc, conf=0.25, iou_thres=0.45, task="detect"):
        """Initialize attributes for the YOLO model."""
        self.task = task
        self.matrix = np.zeros((nc + 1, nc + 1)) if self.task == "detect" else np.zeros((nc, nc))
        self.nc = nc  # number of classes
        self.conf = 0.25 if conf in {None, 0.001} else conf  # apply 0.25 if default val conf is passed
        self.iou_thres = iou_thres

    def process_cls_preds(self, preds, targets):
        """
        Update confusion matrix for classification task.

        Args:
            preds (Array[N, min(nc,5)]): Predicted class labels.
            targets (Array[N, 1]): Ground truth class labels.
        """
        preds, targets = torch.cat(preds)[:, 0], torch.cat(targets)
        for p, t in zip(preds.cpu().numpy(), targets.cpu().numpy()):
            self.matrix[p][t] += 1

    def process_batch(self, detections, gt_bboxes, gt_cls):
        """
        Update confusion matrix for object detection task.

        Args:
            detections (Array[N, 6] | Array[N, 7]): Detected bounding boxes and their associated information.
                                      Each row should contain (x1, y1, x2, y2, conf, class)
                                      or with an additional element `angle` when it's obb.
            gt_bboxes (Array[M, 4]| Array[N, 5]): Ground truth bounding boxes with xyxy/xyxyr format.
            gt_cls (Array[M]): The class labels.
        """
        if gt_cls.shape[0] == 0:  # Check if labels is empty
            if detections is not None:
                detections = detections[detections[:, 4] > self.conf]
                detection_classes = detections[:, 5].int()
                for dc in detection_classes:
                    self.matrix[dc, self.nc] += 1  # false positives
            return
        if detections is None:
            gt_classes = gt_cls.int()
            for gc in gt_classes:
                self.matrix[self.nc, gc] += 1  # background FN
            return

        detections = detections[detections[:, 4] > self.conf]
        gt_classes = gt_cls.int()
        detection_classes = detections[:, 5].int()
        is_obb = detections.shape[1] == 7 and gt_bboxes.shape[1] == 5  # with additional `angle` dimension
        iou = (
            batch_probiou(gt_bboxes, torch.cat([detections[:, :4], detections[:, -1:]], dim=-1))
            if is_obb
            else box_iou(gt_bboxes, detections[:, :4])
        )

        x = torch.where(iou > self.iou_thres)
        if x[0].shape[0]:
            matches = torch.cat((torch.stack(x, 1), iou[x[0], x[1]][:, None]), 1).cpu().numpy()
            if x[0].shape[0] > 1:
                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]]
        else:
            matches = np.zeros((0, 3))

        n = matches.shape[0] > 0
        m0, m1, _ = matches.transpose().astype(int)
        for i, gc in enumerate(gt_classes):
            j = m0 == i
            if n and sum(j) == 1:
                self.matrix[detection_classes[m1[j]], gc] += 1  # correct
            else:
                self.matrix[self.nc, gc] += 1  # true background

        if n:
            for i, dc in enumerate(detection_classes):
                if not any(m1 == i):
                    self.matrix[dc, self.nc] += 1  # predicted background

    def matrix(self):
        """Returns the confusion matrix."""
        return self.matrix

    def tp_fp(self):
        """Returns true positives and false positives."""
        tp = self.matrix.diagonal()  # true positives
        fp = self.matrix.sum(1) - tp  # false positives
        # fn = self.matrix.sum(0) - tp  # false negatives (missed detections)
        return (tp[:-1], fp[:-1]) if self.task == "detect" else (tp, fp)  # remove background class if task=detect

    @TryExcept("WARNING ⚠️ ConfusionMatrix plot failure")
    @plt_settings()
    def plot(self, normalize=True, save_dir="", names=(), on_plot=None):
        """
        Plot the confusion matrix using seaborn and save it to a file.

        Args:
            normalize (bool): Whether to normalize the confusion matrix.
            save_dir (str): Directory where the plot will be saved.
            names (tuple): Names of classes, used as labels on the plot.
            on_plot (func): An optional callback to pass plots path and data when they are rendered.
        """
        import seaborn  # scope for faster 'import ultralytics'

        array = self.matrix / ((self.matrix.sum(0).reshape(1, -1) + 1e-9) if normalize else 1)  # normalize columns
        array[array < 0.005] = np.nan  # don't annotate (would appear as 0.00)

        fig, ax = plt.subplots(1, 1, figsize=(12, 9), tight_layout=True)
        nc, nn = self.nc, len(names)  # number of classes, names
        seaborn.set_theme(font_scale=1.0 if nc < 50 else 0.8)  # for label size
        labels = (0 < nn < 99) and (nn == nc)  # apply names to ticklabels
        ticklabels = (list(names) + ["background"]) if labels else "auto"
        with warnings.catch_warnings():
            warnings.simplefilter("ignore")  # suppress empty matrix RuntimeWarning: All-NaN slice encountered
            seaborn.heatmap(
                array,
                ax=ax,
                annot=nc < 30,
                annot_kws={"size": 8},
                cmap="Blues",
                fmt=".2f" if normalize else ".0f",
                square=True,
                vmin=0.0,
                xticklabels=ticklabels,
                yticklabels=ticklabels,
            ).set_facecolor((1, 1, 1))
        title = "Confusion Matrix" + " Normalized" * normalize
        ax.set_xlabel("True")
        ax.set_ylabel("Predicted")
        ax.set_title(title)
        plot_fname = Path(save_dir) / f'{title.lower().replace(" ", "_")}.png'
        fig.savefig(plot_fname, dpi=250)
        plt.close(fig)
        if on_plot:
            on_plot(plot_fname)

    def print(self):
        """Print the confusion matrix to the console."""
        for i in range(self.nc + 1):
            LOGGER.info(" ".join(map(str, self.matrix[i])))

class Metric(SimpleClass):
    """
    Class for computing evaluation metrics for YOLOv8 model.

    Attributes:
        p (list): Precision for each class. Shape: (nc,).
        r (list): Recall for each class. Shape: (nc,).
        f1 (list): F1 score for each class. Shape: (nc,).
        all_ap (list): AP scores for all classes and all IoU thresholds. Shape: (nc, 10).
        ap_class_index (list): Index of class for each AP score. Shape: (nc,).
        nc (int): Number of classes.

    Methods:
        ap50(): AP at IoU threshold of 0.5 for all classes. Returns: List of AP scores. Shape: (nc,) or [].
        ap(): AP at IoU thresholds from 0.5 to 0.95 for all classes. Returns: List of AP scores. Shape: (nc,) or [].
        mp(): Mean precision of all classes. Returns: Float.
        mr(): Mean recall of all classes. Returns: Float.
        map50(): Mean AP at IoU threshold of 0.5 for all classes. Returns: Float.
        map75(): Mean AP at IoU threshold of 0.75 for all classes. Returns: Float.
        map(): Mean AP at IoU thresholds from 0.5 to 0.95 for all classes. Returns: Float.
        mean_results(): Mean of results, returns mp, mr, map50, map.
        class_result(i): Class-aware result, returns p[i], r[i], ap50[i], ap[i].
        maps(): mAP of each class. Returns: Array of mAP scores, shape: (nc,).
        fitness(): Model fitness as a weighted combination of metrics. Returns: Float.
        update(results): Update metric attributes with new evaluation results.
    """

    def __init__(self) -> None:
        """Initializes a Metric instance for computing evaluation metrics for the YOLOv8 model."""
        self.p = []  # (nc, )
        self.r = []  # (nc, )
        self.f1 = []  # (nc, )
        self.all_ap = []  # (nc, 10)
        self.ap_class_index = []  # (nc, )
        self.nc = 0

    @property
    def ap50(self):
        """
        Returns the Average Precision (AP) at an IoU threshold of 0.5 for all classes.

        Returns:
            (np.ndarray, list): Array of shape (nc,) with AP50 values per class, or an empty list if not available.
        """
        return self.all_ap[:, 0] if len(self.all_ap) else []

    @property
    def ap(self):
        """
        Returns the Average Precision (AP) at an IoU threshold of 0.5-0.95 for all classes.

        Returns:
            (np.ndarray, list): Array of shape (nc,) with AP50-95 values per class, or an empty list if not available.
        """
        return self.all_ap.mean(1) if len(self.all_ap) else []

    @property
    def mp(self):
        """
        Returns the Mean Precision of all classes.

        Returns:
            (float): The mean precision of all classes.
        """
        return self.p.mean() if len(self.p) else 0.0

    @property
    def mr(self):
        """
        Returns the Mean Recall of all classes.

        Returns:
            (float): The mean recall of all classes.
        """
        return self.r.mean() if len(self.r) else 0.0

    @property
    def map50(self):
        """
        Returns the mean Average Precision (mAP) at an IoU threshold of 0.5.

        Returns:
            (float): The mAP at an IoU threshold of 0.5.
        """
        return self.all_ap[:, 0].mean() if len(self.all_ap) else 0.0

    @property
    def map75(self):
        """
        Returns the mean Average Precision (mAP) at an IoU threshold of 0.75.

        Returns:
            (float): The mAP at an IoU threshold of 0.75.
        """
        return self.all_ap[:, 5].mean() if len(self.all_ap) else 0.0

    @property
    def map(self):
        """
        Returns the mean Average Precision (mAP) over IoU thresholds of 0.5 - 0.95 in steps of 0.05.

        Returns:
            (float): The mAP over IoU thresholds of 0.5 - 0.95 in steps of 0.05.
        """
        return self.all_ap.mean() if len(self.all_ap) else 0.0

    def mean_results(self):
        """Mean of results, return mp, mr, map50, map."""
        return [self.mp, self.mr, self.map50, self.map]

    def class_result(self, i):
        """Class-aware result, return p[i], r[i], ap50[i], ap[i]."""
        return self.p[i], self.r[i], self.ap50[i], self.ap[i]

    @property
    def maps(self):
        """MAP of each class."""
        maps = np.zeros(self.nc) + self.map
        for i, c in enumerate(self.ap_class_index):
            maps[c] = self.ap[i]
        return maps

    def fitness(self):
        """Model fitness as a weighted combination of metrics."""
        w = [0.0, 0.0, 0.1, 0.9]  # weights for [P, R, mAP@0.5, mAP@0.5:0.95]
        return (np.array(self.mean_results()) * w).sum()

    def update(self, results):
        """
        Updates the evaluation metrics of the model with a new set of results.

        Args:
            results (tuple): A tuple containing the following evaluation metrics:
                - p (list): Precision for each class. Shape: (nc,).
                - r (list): Recall for each class. Shape: (nc,).
                - f1 (list): F1 score for each class. Shape: (nc,).
                - all_ap (list): AP scores for all classes and all IoU thresholds. Shape: (nc, 10).
                - ap_class_index (list): Index of class for each AP score. Shape: (nc,).

        Side Effects:
            Updates the class attributes `self.p`, `self.r`, `self.f1`, `self.all_ap`, and `self.ap_class_index` based
            on the values provided in the `results` tuple.
        """
        (
            self.p,
            self.r,
            self.f1,
            self.all_ap,
            self.ap_class_index,
            self.p_curve,
            self.r_curve,
            self.f1_curve,
            self.px,
            self.prec_values,
        ) = results

    @property
    def curves(self):
        """Returns a list of curves for accessing specific metrics curves."""
        return []

    @property
    def curves_results(self):
        """Returns a list of curves for accessing specific metrics curves."""
        return [
            [self.px, self.prec_values, "Recall", "Precision"],
            [self.px, self.f1_curve, "Confidence", "F1"],
            [self.px, self.p_curve, "Confidence", "Precision"],
            [self.px, self.r_curve, "Confidence", "Recall"],
        ]

class DetMetrics(SimpleClass):
    """
    This class is a utility class for computing detection metrics such as precision, recall, and mean average precision
    (mAP) of an object detection model.

    Args:
        save_dir (Path): A path to the directory where the output plots will be saved. Defaults to current directory.
        plot (bool): A flag that indicates whether to plot precision-recall curves for each class. Defaults to False.
        on_plot (func): An optional callback to pass plots path and data when they are rendered. Defaults to None.
        names (tuple of str): A tuple of strings that represents the names of the classes. Defaults to an empty tuple.

    Attributes:
        save_dir (Path): A path to the directory where the output plots will be saved.
        plot (bool): A flag that indicates whether to plot the precision-recall curves for each class.
        on_plot (func): An optional callback to pass plots path and data when they are rendered.
        names (tuple of str): A tuple of strings that represents the names of the classes.
        box (Metric): An instance of the Metric class for storing the results of the detection metrics.
        speed (dict): A dictionary for storing the execution time of different parts of the detection process.

    Methods:
        process(tp, conf, pred_cls, target_cls): Updates the metric results with the latest batch of predictions.
        keys: Returns a list of keys for accessing the computed detection metrics.
        mean_results: Returns a list of mean values for the computed detection metrics.
        class_result(i): Returns a list of values for the computed detection metrics for a specific class.
        maps: Returns a dictionary of mean average precision (mAP) values for different IoU thresholds.
        fitness: Computes the fitness score based on the computed detection metrics.
        ap_class_index: Returns a list of class indices sorted by their average precision (AP) values.
        results_dict: Returns a dictionary that maps detection metric keys to their computed values.
        curves: TODO
        curves_results: TODO
    """

    def __init__(self, save_dir=Path("."), plot=False, on_plot=None, names=()) -> None:
        """Initialize a DetMetrics instance with a save directory, plot flag, callback function, and class names."""
        self.save_dir = save_dir
        self.plot = plot
        self.on_plot = on_plot
        self.names = names
        self.box = Metric()
        self.speed = {"preprocess": 0.0, "inference": 0.0, "loss": 0.0, "postprocess": 0.0}
        self.task = "detect"

    def process(self, tp, conf, pred_cls, target_cls):
        """Process predicted results for object detection and update metrics."""
        results = ap_per_class(
            tp,
            conf,
            pred_cls,
            target_cls,
            plot=self.plot,
            save_dir=self.save_dir,
            names=self.names,
            on_plot=self.on_plot,
        )[2:]
        self.box.nc = len(self.names)
        self.box.update(results)

    @property
    def keys(self):
        """Returns a list of keys for accessing specific metrics."""
        return ["metrics/precision(B)", "metrics/recall(B)", "metrics/mAP50(B)", "metrics/mAP50-95(B)"]

    def mean_results(self):
        """Calculate mean of detected objects & return precision, recall, mAP50, and mAP50-95."""
        return self.box.mean_results()

    def class_result(self, i):
        """Return the result of evaluating the performance of an object detection model on a specific class."""
        return self.box.class_result(i)

    @property
    def maps(self):
        """Returns mean Average Precision (mAP) scores per class."""
        return self.box.maps

    @property
    def fitness(self):
        """Returns the fitness of box object."""
        return self.box.fitness()

    @property
    def ap_class_index(self):
        """Returns the average precision index per class."""
        return self.box.ap_class_index

    @property
    def results_dict(self):
        """Returns dictionary of computed performance metrics and statistics."""
        return dict(zip(self.keys + ["fitness"], self.mean_results() + [self.fitness]))

    @property
    def curves(self):
        """Returns a list of curves for accessing specific metrics curves."""
        return ["Precision-Recall(B)", "F1-Confidence(B)", "Precision-Confidence(B)", "Recall-Confidence(B)"]

    @property
    def curves_results(self):
        """Returns dictionary of computed performance metrics and statistics."""
        return self.box.curves_results

class SegmentMetrics(SimpleClass):
    """
    Calculates and aggregates detection and segmentation metrics over a given set of classes.

    Args:
        save_dir (Path): Path to the directory where the output plots should be saved. Default is the current directory.
        plot (bool): Whether to save the detection and segmentation plots. Default is False.
        on_plot (func): An optional callback to pass plots path and data when they are rendered. Defaults to None.
        names (list): List of class names. Default is an empty list.

    Attributes:
        save_dir (Path): Path to the directory where the output plots should be saved.
        plot (bool): Whether to save the detection and segmentation plots.
        on_plot (func): An optional callback to pass plots path and data when they are rendered.
        names (list): List of class names.
        box (Metric): An instance of the Metric class to calculate box detection metrics.
        seg (Metric): An instance of the Metric class to calculate mask segmentation metrics.
        speed (dict): Dictionary to store the time taken in different phases of inference.

    Methods:
        process(tp_m, tp_b, conf, pred_cls, target_cls): Processes metrics over the given set of predictions.
        mean_results(): Returns the mean of the detection and segmentation metrics over all the classes.
        class_result(i): Returns the detection and segmentation metrics of class `i`.
        maps: Returns the mean Average Precision (mAP) scores for IoU thresholds ranging from 0.50 to 0.95.
        fitness: Returns the fitness scores, which are a single weighted combination of metrics.
        ap_class_index: Returns the list of indices of classes used to compute Average Precision (AP).
        results_dict: Returns the dictionary containing all the detection and segmentation metrics and fitness score.
    """

    def __init__(self, save_dir=Path("."), plot=False, on_plot=None, names=()) -> None:
        """Initialize a SegmentMetrics instance with a save directory, plot flag, callback function, and class names."""
        self.save_dir = save_dir
        self.plot = plot
        self.on_plot = on_plot
        self.names = names
        self.box = Metric()
        self.seg = Metric()
        self.speed = {"preprocess": 0.0, "inference": 0.0, "loss": 0.0, "postprocess": 0.0}
        self.task = "segment"

    def process(self, tp, tp_m, conf, pred_cls, target_cls):
        """
        Processes the detection and segmentation metrics over the given set of predictions.

        Args:
            tp (list): List of True Positive boxes.
            tp_m (list): List of True Positive masks.
            conf (list): List of confidence scores.
            pred_cls (list): List of predicted classes.
            target_cls (list): List of target classes.
        """

        results_mask = ap_per_class(
            tp_m,
            conf,
            pred_cls,
            target_cls,
            plot=self.plot,
            on_plot=self.on_plot,
            save_dir=self.save_dir,
            names=self.names,
            prefix="Mask",
        )[2:]
        self.seg.nc = len(self.names)
        self.seg.update(results_mask)
        results_box = ap_per_class(
            tp,
            conf,
            pred_cls,
            target_cls,
            plot=self.plot,
            on_plot=self.on_plot,
            save_dir=self.save_dir,
            names=self.names,
            prefix="Box",
        )[2:]
        self.box.nc = len(self.names)
        self.box.update(results_box)

    @property
    def keys(self):
        """Returns a list of keys for accessing metrics."""
        return [
            "metrics/precision(B)",
            "metrics/recall(B)",
            "metrics/mAP50(B)",
            "metrics/mAP50-95(B)",
            "metrics/precision(M)",
            "metrics/recall(M)",
            "metrics/mAP50(M)",
            "metrics/mAP50-95(M)",
        ]

    def mean_results(self):
        """Return the mean metrics for bounding box and segmentation results."""
        return self.box.mean_results() + self.seg.mean_results()

    def class_result(self, i):
        """Returns classification results for a specified class index."""
        return self.box.class_result(i) + self.seg.class_result(i)

    @property
    def maps(self):
        """Returns mAP scores for object detection and semantic segmentation models."""
        return self.box.maps + self.seg.maps

    @property
    def fitness(self):
        """Get the fitness score for both segmentation and bounding box models."""
        return self.seg.fitness() + self.box.fitness()

    @property
    def ap_class_index(self):
        """Boxes and masks have the same ap_class_index."""
        return self.box.ap_class_index

    @property
    def results_dict(self):
        """Returns results of object detection model for evaluation."""
        return dict(zip(self.keys + ["fitness"], self.mean_results() + [self.fitness]))

    @property
    def curves(self):
        """Returns a list of curves for accessing specific metrics curves."""
        return [
            "Precision-Recall(B)",
            "F1-Confidence(B)",
            "Precision-Confidence(B)",
            "Recall-Confidence(B)",
            "Precision-Recall(M)",
            "F1-Confidence(M)",
            "Precision-Confidence(M)",
            "Recall-Confidence(M)",
        ]

    @property
    def curves_results(self):
        """Returns dictionary of computed performance metrics and statistics."""
        return self.box.curves_results + self.seg.curves_results