Skip to content

Reference for ultralytics/utils/metrics.py

Note

Full source code for this file is available at https://github.com/ultralytics/ultralytics/blob/main/ultralytics/utils/metrics.py. Help us fix any issues you see by submitting a Pull Request 🛠️. Thank you 🙏!


ultralytics.utils.metrics.ConfusionMatrix

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

Attributes:

Name Type Description
task str

The type of task, either 'detect' or 'classify'.

matrix array

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.

Source code in 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.array): 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, labels):
        """
        Update confusion matrix for object detection task.

        Args:
            detections (Array[N, 6]): Detected bounding boxes and their associated information.
                                      Each row should contain (x1, y1, x2, y2, conf, class).
            labels (Array[M, 5]): Ground truth bounding boxes and their associated class labels.
                                  Each row should contain (class, x1, y1, x2, y2).
        """
        if detections is None:
            gt_classes = labels.int()
            for gc in gt_classes:
                self.matrix[self.nc, gc] += 1  # background FN
            return

        detections = detections[detections[:, 4] > self.conf]
        gt_classes = labels[:, 0].int()
        detection_classes = detections[:, 5].int()
        iou = box_iou(labels[:, 1:], 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 as sn

        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
        sn.set(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
            sn.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])))

__init__(nc, conf=0.25, iou_thres=0.45, task='detect')

Initialize attributes for the YOLO model.

Source code in ultralytics/utils/metrics.py
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

matrix()

Returns the confusion matrix.

Source code in ultralytics/utils/metrics.py
def matrix(self):
    """Returns the confusion matrix."""
    return self.matrix

plot(normalize=True, save_dir='', names=(), on_plot=None)

Plot the confusion matrix using seaborn and save it to a file.

Parameters:

Name Type Description Default
normalize bool

Whether to normalize the confusion matrix.

True
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.

None
Source code in ultralytics/utils/metrics.py
@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 as sn

    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
    sn.set(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
        sn.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)

print()

Print the confusion matrix to the console.

Source code in ultralytics/utils/metrics.py
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])))

process_batch(detections, labels)

Update confusion matrix for object detection task.

Parameters:

Name Type Description Default
detections Array[N, 6]

Detected bounding boxes and their associated information. Each row should contain (x1, y1, x2, y2, conf, class).

required
labels Array[M, 5]

Ground truth bounding boxes and their associated class labels. Each row should contain (class, x1, y1, x2, y2).

required
Source code in ultralytics/utils/metrics.py
def process_batch(self, detections, labels):
    """
    Update confusion matrix for object detection task.

    Args:
        detections (Array[N, 6]): Detected bounding boxes and their associated information.
                                  Each row should contain (x1, y1, x2, y2, conf, class).
        labels (Array[M, 5]): Ground truth bounding boxes and their associated class labels.
                              Each row should contain (class, x1, y1, x2, y2).
    """
    if detections is None:
        gt_classes = labels.int()
        for gc in gt_classes:
            self.matrix[self.nc, gc] += 1  # background FN
        return

    detections = detections[detections[:, 4] > self.conf]
    gt_classes = labels[:, 0].int()
    detection_classes = detections[:, 5].int()
    iou = box_iou(labels[:, 1:], 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

process_cls_preds(preds, targets)

Update confusion matrix for classification task

Parameters:

Name Type Description Default
preds Array[N, min(nc, 5)]

Predicted class labels.

required
targets Array[N, 1]

Ground truth class labels.

required
Source code in ultralytics/utils/metrics.py
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

tp_fp()

Returns true positives and false positives.

Source code in ultralytics/utils/metrics.py
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




ultralytics.utils.metrics.Metric

Bases: SimpleClass

Class for computing evaluation metrics for YOLOv8 model.

Attributes:

Name Type Description
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:

Name Description
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

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

Update metric attributes with new evaluation results.

Source code in ultralytics/utils/metrics.py
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:
        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 mAP50 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 mAP50 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):
        """
        Args:
            results (tuple): A tuple of (p, r, ap, f1, ap_class)
        """
        self.p, self.r, self.f1, self.all_ap, self.ap_class_index = results

ap property

Returns the Average Precision (AP) at an IoU threshold of 0.5-0.95 for all classes.

Returns:

Type Description
(ndarray, list)

Array of shape (nc,) with AP50-95 values per class, or an empty list if not available.

ap50 property

Returns the Average Precision (AP) at an IoU threshold of 0.5 for all classes.

Returns:

Type Description
(ndarray, list)

Array of shape (nc,) with AP50 values per class, or an empty list if not available.

map property

Returns the mean Average Precision (mAP) over IoU thresholds of 0.5 - 0.95 in steps of 0.05.

Returns:

Type Description
float

The mAP over IoU thresholds of 0.5 - 0.95 in steps of 0.05.

map50 property

Returns the mean Average Precision (mAP) at an IoU threshold of 0.5.

Returns:

Type Description
float

The mAP50 at an IoU threshold of 0.5.

map75 property

Returns the mean Average Precision (mAP) at an IoU threshold of 0.75.

Returns:

Type Description
float

The mAP50 at an IoU threshold of 0.75.

maps property

mAP of each class.

mp property

Returns the Mean Precision of all classes.

Returns:

Type Description
float

The mean precision of all classes.

mr property

Returns the Mean Recall of all classes.

Returns:

Type Description
float

The mean recall of all classes.

class_result(i)

class-aware result, return p[i], r[i], ap50[i], ap[i].

Source code in ultralytics/utils/metrics.py
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]

fitness()

Model fitness as a weighted combination of metrics.

Source code in ultralytics/utils/metrics.py
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()

mean_results()

Mean of results, return mp, mr, map50, map.

Source code in ultralytics/utils/metrics.py
def mean_results(self):
    """Mean of results, return mp, mr, map50, map."""
    return [self.mp, self.mr, self.map50, self.map]

update(results)

Parameters:

Name Type Description Default
results tuple

A tuple of (p, r, ap, f1, ap_class)

required
Source code in ultralytics/utils/metrics.py
def update(self, results):
    """
    Args:
        results (tuple): A tuple of (p, r, ap, f1, ap_class)
    """
    self.p, self.r, self.f1, self.all_ap, self.ap_class_index = results




ultralytics.utils.metrics.DetMetrics

Bases: 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.

Parameters:

Name Type Description Default
save_dir Path

A path to the directory where the output plots will be saved. Defaults to current directory.

Path('.')
plot bool

A flag that indicates whether to plot precision-recall curves for each class. Defaults to False.

False
on_plot func

An optional callback to pass plots path and data when they are rendered. Defaults to None.

None
names tuple of str

A tuple of strings that represents the names of the classes. Defaults to an empty tuple.

()

Attributes:

Name Type Description
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:

Name Description
process

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

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.

Source code in ultralytics/utils/metrics.py
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.
    """

    def __init__(self, save_dir=Path('.'), plot=False, on_plot=None, names=()) -> None:
        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}

    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]))

ap_class_index property

Returns the average precision index per class.

fitness property

Returns the fitness of box object.

keys property

Returns a list of keys for accessing specific metrics.

maps property

Returns mean Average Precision (mAP) scores per class.

results_dict property

Returns dictionary of computed performance metrics and statistics.

class_result(i)

Return the result of evaluating the performance of an object detection model on a specific class.

Source code in ultralytics/utils/metrics.py
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)

mean_results()

Calculate mean of detected objects & return precision, recall, mAP50, and mAP50-95.

Source code in ultralytics/utils/metrics.py
def mean_results(self):
    """Calculate mean of detected objects & return precision, recall, mAP50, and mAP50-95."""
    return self.box.mean_results()

process(tp, conf, pred_cls, target_cls)

Process predicted results for object detection and update metrics.

Source code in ultralytics/utils/metrics.py
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)




ultralytics.utils.metrics.SegmentMetrics

Bases: SimpleClass

Calculates and aggregates detection and segmentation metrics over a given set of classes.

Parameters:

Name Type Description Default
save_dir Path

Path to the directory where the output plots should be saved. Default is the current directory.

Path('.')
plot bool

Whether to save the detection and segmentation plots. Default is False.

False
on_plot func

An optional callback to pass plots path and data when they are rendered. Defaults to None.

None
names list

List of class names. Default is an empty list.

()

Attributes:

Name Type Description
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:

Name Description
process

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

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.

Source code in ultralytics/utils/metrics.py
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:
        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}

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

        Args:
            tp_b (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_b,
                                   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]))

ap_class_index property

Boxes and masks have the same ap_class_index.

fitness property

Get the fitness score for both segmentation and bounding box models.

keys property

Returns a list of keys for accessing metrics.

maps property

Returns mAP scores for object detection and semantic segmentation models.

results_dict property

Returns results of object detection model for evaluation.

class_result(i)

Returns classification results for a specified class index.

Source code in ultralytics/utils/metrics.py
def class_result(self, i):
    """Returns classification results for a specified class index."""
    return self.box.class_result(i) + self.seg.class_result(i)

mean_results()

Return the mean metrics for bounding box and segmentation results.

Source code in ultralytics/utils/metrics.py
def mean_results(self):
    """Return the mean metrics for bounding box and segmentation results."""
    return self.box.mean_results() + self.seg.mean_results()

process(tp_b, tp_m, conf, pred_cls, target_cls)

Processes the detection and segmentation metrics over the given set of predictions.

Parameters:

Name Type Description Default
tp_b list

List of True Positive boxes.

required
tp_m list

List of True Positive masks.

required
conf list

List of confidence scores.

required
pred_cls list

List of predicted classes.

required
target_cls list

List of target classes.

required
Source code in ultralytics/utils/metrics.py
def process(self, tp_b, tp_m, conf, pred_cls, target_cls):
    """
    Processes the detection and segmentation metrics over the given set of predictions.

    Args:
        tp_b (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_b,
                               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)




ultralytics.utils.metrics.PoseMetrics

Bases: SegmentMetrics

Calculates and aggregates detection and pose metrics over a given set of classes.

Parameters:

Name Type Description Default
save_dir Path

Path to the directory where the output plots should be saved. Default is the current directory.

Path('.')
plot bool

Whether to save the detection and segmentation plots. Default is False.

False
on_plot func

An optional callback to pass plots path and data when they are rendered. Defaults to None.

None
names list

List of class names. Default is an empty list.

()

Attributes:

Name Type Description
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.

pose 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:

Name Description
process

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

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.

Source code in ultralytics/utils/metrics.py
class PoseMetrics(SegmentMetrics):
    """
    Calculates and aggregates detection and pose 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.
        pose (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:
        super().__init__(save_dir, plot, names)
        self.save_dir = save_dir
        self.plot = plot
        self.on_plot = on_plot
        self.names = names
        self.box = Metric()
        self.pose = Metric()
        self.speed = {'preprocess': 0.0, 'inference': 0.0, 'loss': 0.0, 'postprocess': 0.0}

    def process(self, tp_b, tp_p, conf, pred_cls, target_cls):
        """
        Processes the detection and pose metrics over the given set of predictions.

        Args:
            tp_b (list): List of True Positive boxes.
            tp_p (list): List of True Positive keypoints.
            conf (list): List of confidence scores.
            pred_cls (list): List of predicted classes.
            target_cls (list): List of target classes.
        """

        results_pose = ap_per_class(tp_p,
                                    conf,
                                    pred_cls,
                                    target_cls,
                                    plot=self.plot,
                                    on_plot=self.on_plot,
                                    save_dir=self.save_dir,
                                    names=self.names,
                                    prefix='Pose')[2:]
        self.pose.nc = len(self.names)
        self.pose.update(results_pose)
        results_box = ap_per_class(tp_b,
                                   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 list of evaluation metric keys."""
        return [
            'metrics/precision(B)', 'metrics/recall(B)', 'metrics/mAP50(B)', 'metrics/mAP50-95(B)',
            'metrics/precision(P)', 'metrics/recall(P)', 'metrics/mAP50(P)', 'metrics/mAP50-95(P)']

    def mean_results(self):
        """Return the mean results of box and pose."""
        return self.box.mean_results() + self.pose.mean_results()

    def class_result(self, i):
        """Return the class-wise detection results for a specific class i."""
        return self.box.class_result(i) + self.pose.class_result(i)

    @property
    def maps(self):
        """Returns the mean average precision (mAP) per class for both box and pose detections."""
        return self.box.maps + self.pose.maps

    @property
    def fitness(self):
        """Computes classification metrics and speed using the `targets` and `pred` inputs."""
        return self.pose.fitness() + self.box.fitness()

fitness property

Computes classification metrics and speed using the targets and pred inputs.

keys property

Returns list of evaluation metric keys.

maps property

Returns the mean average precision (mAP) per class for both box and pose detections.

class_result(i)

Return the class-wise detection results for a specific class i.

Source code in ultralytics/utils/metrics.py
def class_result(self, i):
    """Return the class-wise detection results for a specific class i."""
    return self.box.class_result(i) + self.pose.class_result(i)

mean_results()

Return the mean results of box and pose.

Source code in ultralytics/utils/metrics.py
def mean_results(self):
    """Return the mean results of box and pose."""
    return self.box.mean_results() + self.pose.mean_results()

process(tp_b, tp_p, conf, pred_cls, target_cls)

Processes the detection and pose metrics over the given set of predictions.

Parameters:

Name Type Description Default
tp_b list

List of True Positive boxes.

required
tp_p list

List of True Positive keypoints.

required
conf list

List of confidence scores.

required
pred_cls list

List of predicted classes.

required
target_cls list

List of target classes.

required
Source code in ultralytics/utils/metrics.py
def process(self, tp_b, tp_p, conf, pred_cls, target_cls):
    """
    Processes the detection and pose metrics over the given set of predictions.

    Args:
        tp_b (list): List of True Positive boxes.
        tp_p (list): List of True Positive keypoints.
        conf (list): List of confidence scores.
        pred_cls (list): List of predicted classes.
        target_cls (list): List of target classes.
    """

    results_pose = ap_per_class(tp_p,
                                conf,
                                pred_cls,
                                target_cls,
                                plot=self.plot,
                                on_plot=self.on_plot,
                                save_dir=self.save_dir,
                                names=self.names,
                                prefix='Pose')[2:]
    self.pose.nc = len(self.names)
    self.pose.update(results_pose)
    results_box = ap_per_class(tp_b,
                               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)




ultralytics.utils.metrics.ClassifyMetrics

Bases: SimpleClass

Class for computing classification metrics including top-1 and top-5 accuracy.

Attributes:

Name Type Description
top1 float

The top-1 accuracy.

top5 float

The top-5 accuracy.

speed Dict[str, float]

A dictionary containing the time taken for each step in the pipeline.

Properties

fitness (float): The fitness of the model, which is equal to top-5 accuracy. results_dict (Dict[str, Union[float, str]]): A dictionary containing the classification metrics and fitness. keys (List[str]): A list of keys for the results_dict.

Methods:

Name Description
process

Processes the targets and predictions to compute classification metrics.

Source code in ultralytics/utils/metrics.py
class ClassifyMetrics(SimpleClass):
    """
    Class for computing classification metrics including top-1 and top-5 accuracy.

    Attributes:
        top1 (float): The top-1 accuracy.
        top5 (float): The top-5 accuracy.
        speed (Dict[str, float]): A dictionary containing the time taken for each step in the pipeline.

    Properties:
        fitness (float): The fitness of the model, which is equal to top-5 accuracy.
        results_dict (Dict[str, Union[float, str]]): A dictionary containing the classification metrics and fitness.
        keys (List[str]): A list of keys for the results_dict.

    Methods:
        process(targets, pred): Processes the targets and predictions to compute classification metrics.
    """

    def __init__(self) -> None:
        self.top1 = 0
        self.top5 = 0
        self.speed = {'preprocess': 0.0, 'inference': 0.0, 'loss': 0.0, 'postprocess': 0.0}

    def process(self, targets, pred):
        """Target classes and predicted classes."""
        pred, targets = torch.cat(pred), torch.cat(targets)
        correct = (targets[:, None] == pred).float()
        acc = torch.stack((correct[:, 0], correct.max(1).values), dim=1)  # (top1, top5) accuracy
        self.top1, self.top5 = acc.mean(0).tolist()

    @property
    def fitness(self):
        """Returns mean of top-1 and top-5 accuracies as fitness score."""
        return (self.top1 + self.top5) / 2

    @property
    def results_dict(self):
        """Returns a dictionary with model's performance metrics and fitness score."""
        return dict(zip(self.keys + ['fitness'], [self.top1, self.top5, self.fitness]))

    @property
    def keys(self):
        """Returns a list of keys for the results_dict property."""
        return ['metrics/accuracy_top1', 'metrics/accuracy_top5']

fitness property

Returns mean of top-1 and top-5 accuracies as fitness score.

keys property

Returns a list of keys for the results_dict property.

results_dict property

Returns a dictionary with model's performance metrics and fitness score.

process(targets, pred)

Target classes and predicted classes.

Source code in ultralytics/utils/metrics.py
def process(self, targets, pred):
    """Target classes and predicted classes."""
    pred, targets = torch.cat(pred), torch.cat(targets)
    correct = (targets[:, None] == pred).float()
    acc = torch.stack((correct[:, 0], correct.max(1).values), dim=1)  # (top1, top5) accuracy
    self.top1, self.top5 = acc.mean(0).tolist()




ultralytics.utils.metrics.bbox_ioa(box1, box2, iou=False, eps=1e-07)

Calculate the intersection over box2 area given box1 and box2. Boxes are in x1y1x2y2 format.

Parameters:

Name Type Description Default
box1 array

A numpy array of shape (n, 4) representing n bounding boxes.

required
box2 array

A numpy array of shape (m, 4) representing m bounding boxes.

required
iou bool

Calculate the standard iou if True else return inter_area/box2_area.

False
eps float

A small value to avoid division by zero. Defaults to 1e-7.

1e-07

Returns:

Type Description
array

A numpy array of shape (n, m) representing the intersection over box2 area.

Source code in ultralytics/utils/metrics.py
def bbox_ioa(box1, box2, iou=False, eps=1e-7):
    """
    Calculate the intersection over box2 area given box1 and box2. Boxes are in x1y1x2y2 format.

    Args:
        box1 (np.array): A numpy array of shape (n, 4) representing n bounding boxes.
        box2 (np.array): A numpy array of shape (m, 4) representing m bounding boxes.
        iou (bool): Calculate the standard iou if True else return inter_area/box2_area.
        eps (float, optional): A small value to avoid division by zero. Defaults to 1e-7.

    Returns:
        (np.array): A numpy array of shape (n, m) representing the intersection over box2 area.
    """

    # Get the coordinates of bounding boxes
    b1_x1, b1_y1, b1_x2, b1_y2 = box1.T
    b2_x1, b2_y1, b2_x2, b2_y2 = box2.T

    # Intersection area
    inter_area = (np.minimum(b1_x2[:, None], b2_x2) - np.maximum(b1_x1[:, None], b2_x1)).clip(0) * \
                 (np.minimum(b1_y2[:, None], b2_y2) - np.maximum(b1_y1[:, None], b2_y1)).clip(0)

    # box2 area
    area = (b2_x2 - b2_x1) * (b2_y2 - b2_y1)
    if iou:
        box1_area = (b1_x2 - b1_x1) * (b1_y2 - b1_y1)
        area = area + box1_area[:, None] - inter_area

    # Intersection over box2 area
    return inter_area / (area + eps)




ultralytics.utils.metrics.box_iou(box1, box2, eps=1e-07)

Calculate intersection-over-union (IoU) of boxes. Both sets of boxes are expected to be in (x1, y1, x2, y2) format. Based on https://github.com/pytorch/vision/blob/master/torchvision/ops/boxes.py

Parameters:

Name Type Description Default
box1 Tensor

A tensor of shape (N, 4) representing N bounding boxes.

required
box2 Tensor

A tensor of shape (M, 4) representing M bounding boxes.

required
eps float

A small value to avoid division by zero. Defaults to 1e-7.

1e-07

Returns:

Type Description
Tensor

An NxM tensor containing the pairwise IoU values for every element in box1 and box2.

Source code in ultralytics/utils/metrics.py
def box_iou(box1, box2, eps=1e-7):
    """
    Calculate intersection-over-union (IoU) of boxes.
    Both sets of boxes are expected to be in (x1, y1, x2, y2) format.
    Based on https://github.com/pytorch/vision/blob/master/torchvision/ops/boxes.py

    Args:
        box1 (torch.Tensor): A tensor of shape (N, 4) representing N bounding boxes.
        box2 (torch.Tensor): A tensor of shape (M, 4) representing M bounding boxes.
        eps (float, optional): A small value to avoid division by zero. Defaults to 1e-7.

    Returns:
        (torch.Tensor): An NxM tensor containing the pairwise IoU values for every element in box1 and box2.
    """

    # inter(N,M) = (rb(N,M,2) - lt(N,M,2)).clamp(0).prod(2)
    (a1, a2), (b1, b2) = box1.unsqueeze(1).chunk(2, 2), box2.unsqueeze(0).chunk(2, 2)
    inter = (torch.min(a2, b2) - torch.max(a1, b1)).clamp_(0).prod(2)

    # IoU = inter / (area1 + area2 - inter)
    return inter / ((a2 - a1).prod(2) + (b2 - b1).prod(2) - inter + eps)




ultralytics.utils.metrics.bbox_iou(box1, box2, xywh=True, GIoU=False, DIoU=False, CIoU=False, eps=1e-07)

Calculate Intersection over Union (IoU) of box1(1, 4) to box2(n, 4).

Parameters:

Name Type Description Default
box1 Tensor

A tensor representing a single bounding box with shape (1, 4).

required
box2 Tensor

A tensor representing n bounding boxes with shape (n, 4).

required
xywh bool

If True, input boxes are in (x, y, w, h) format. If False, input boxes are in (x1, y1, x2, y2) format. Defaults to True.

True
GIoU bool

If True, calculate Generalized IoU. Defaults to False.

False
DIoU bool

If True, calculate Distance IoU. Defaults to False.

False
CIoU bool

If True, calculate Complete IoU. Defaults to False.

False
eps float

A small value to avoid division by zero. Defaults to 1e-7.

1e-07

Returns:

Type Description
Tensor

IoU, GIoU, DIoU, or CIoU values depending on the specified flags.

Source code in ultralytics/utils/metrics.py
def bbox_iou(box1, box2, xywh=True, GIoU=False, DIoU=False, CIoU=False, eps=1e-7):
    """
    Calculate Intersection over Union (IoU) of box1(1, 4) to box2(n, 4).

    Args:
        box1 (torch.Tensor): A tensor representing a single bounding box with shape (1, 4).
        box2 (torch.Tensor): A tensor representing n bounding boxes with shape (n, 4).
        xywh (bool, optional): If True, input boxes are in (x, y, w, h) format. If False, input boxes are in
                               (x1, y1, x2, y2) format. Defaults to True.
        GIoU (bool, optional): If True, calculate Generalized IoU. Defaults to False.
        DIoU (bool, optional): If True, calculate Distance IoU. Defaults to False.
        CIoU (bool, optional): If True, calculate Complete IoU. Defaults to False.
        eps (float, optional): A small value to avoid division by zero. Defaults to 1e-7.

    Returns:
        (torch.Tensor): IoU, GIoU, DIoU, or CIoU values depending on the specified flags.
    """

    # Get the coordinates of bounding boxes
    if xywh:  # transform from xywh to xyxy
        (x1, y1, w1, h1), (x2, y2, w2, h2) = box1.chunk(4, -1), box2.chunk(4, -1)
        w1_, h1_, w2_, h2_ = w1 / 2, h1 / 2, w2 / 2, h2 / 2
        b1_x1, b1_x2, b1_y1, b1_y2 = x1 - w1_, x1 + w1_, y1 - h1_, y1 + h1_
        b2_x1, b2_x2, b2_y1, b2_y2 = x2 - w2_, x2 + w2_, y2 - h2_, y2 + h2_
    else:  # x1, y1, x2, y2 = box1
        b1_x1, b1_y1, b1_x2, b1_y2 = box1.chunk(4, -1)
        b2_x1, b2_y1, b2_x2, b2_y2 = box2.chunk(4, -1)
        w1, h1 = b1_x2 - b1_x1, b1_y2 - b1_y1 + eps
        w2, h2 = b2_x2 - b2_x1, b2_y2 - b2_y1 + eps

    # Intersection area
    inter = (b1_x2.minimum(b2_x2) - b1_x1.maximum(b2_x1)).clamp_(0) * \
            (b1_y2.minimum(b2_y2) - b1_y1.maximum(b2_y1)).clamp_(0)

    # Union Area
    union = w1 * h1 + w2 * h2 - inter + eps

    # IoU
    iou = inter / union
    if CIoU or DIoU or GIoU:
        cw = b1_x2.maximum(b2_x2) - b1_x1.minimum(b2_x1)  # convex (smallest enclosing box) width
        ch = b1_y2.maximum(b2_y2) - b1_y1.minimum(b2_y1)  # convex height
        if CIoU or DIoU:  # Distance or Complete IoU https://arxiv.org/abs/1911.08287v1
            c2 = cw ** 2 + ch ** 2 + eps  # convex diagonal squared
            rho2 = ((b2_x1 + b2_x2 - b1_x1 - b1_x2) ** 2 + (b2_y1 + b2_y2 - b1_y1 - b1_y2) ** 2) / 4  # center dist ** 2
            if CIoU:  # https://github.com/Zzh-tju/DIoU-SSD-pytorch/blob/master/utils/box/box_utils.py#L47
                v = (4 / math.pi ** 2) * (torch.atan(w2 / h2) - torch.atan(w1 / h1)).pow(2)
                with torch.no_grad():
                    alpha = v / (v - iou + (1 + eps))
                return iou - (rho2 / c2 + v * alpha)  # CIoU
            return iou - rho2 / c2  # DIoU
        c_area = cw * ch + eps  # convex area
        return iou - (c_area - union) / c_area  # GIoU https://arxiv.org/pdf/1902.09630.pdf
    return iou  # IoU




ultralytics.utils.metrics.mask_iou(mask1, mask2, eps=1e-07)

Calculate masks IoU.

Parameters:

Name Type Description Default
mask1 Tensor

A tensor of shape (N, n) where N is the number of ground truth objects and n is the product of image width and height.

required
mask2 Tensor

A tensor of shape (M, n) where M is the number of predicted objects and n is the product of image width and height.

required
eps float

A small value to avoid division by zero. Defaults to 1e-7.

1e-07

Returns:

Type Description
Tensor

A tensor of shape (N, M) representing masks IoU.

Source code in ultralytics/utils/metrics.py
def mask_iou(mask1, mask2, eps=1e-7):
    """
    Calculate masks IoU.

    Args:
        mask1 (torch.Tensor): A tensor of shape (N, n) where N is the number of ground truth objects and n is the
                        product of image width and height.
        mask2 (torch.Tensor): A tensor of shape (M, n) where M is the number of predicted objects and n is the
                        product of image width and height.
        eps (float, optional): A small value to avoid division by zero. Defaults to 1e-7.

    Returns:
        (torch.Tensor): A tensor of shape (N, M) representing masks IoU.
    """
    intersection = torch.matmul(mask1, mask2.T).clamp_(0)
    union = (mask1.sum(1)[:, None] + mask2.sum(1)[None]) - intersection  # (area1 + area2) - intersection
    return intersection / (union + eps)




ultralytics.utils.metrics.kpt_iou(kpt1, kpt2, area, sigma, eps=1e-07)

Calculate Object Keypoint Similarity (OKS).

Parameters:

Name Type Description Default
kpt1 Tensor

A tensor of shape (N, 17, 3) representing ground truth keypoints.

required
kpt2 Tensor

A tensor of shape (M, 17, 3) representing predicted keypoints.

required
area Tensor

A tensor of shape (N,) representing areas from ground truth.

required
sigma list

A list containing 17 values representing keypoint scales.

required
eps float

A small value to avoid division by zero. Defaults to 1e-7.

1e-07

Returns:

Type Description
Tensor

A tensor of shape (N, M) representing keypoint similarities.

Source code in ultralytics/utils/metrics.py
def kpt_iou(kpt1, kpt2, area, sigma, eps=1e-7):
    """
    Calculate Object Keypoint Similarity (OKS).

    Args:
        kpt1 (torch.Tensor): A tensor of shape (N, 17, 3) representing ground truth keypoints.
        kpt2 (torch.Tensor): A tensor of shape (M, 17, 3) representing predicted keypoints.
        area (torch.Tensor): A tensor of shape (N,) representing areas from ground truth.
        sigma (list): A list containing 17 values representing keypoint scales.
        eps (float, optional): A small value to avoid division by zero. Defaults to 1e-7.

    Returns:
        (torch.Tensor): A tensor of shape (N, M) representing keypoint similarities.
    """
    d = (kpt1[:, None, :, 0] - kpt2[..., 0]) ** 2 + (kpt1[:, None, :, 1] - kpt2[..., 1]) ** 2  # (N, M, 17)
    sigma = torch.tensor(sigma, device=kpt1.device, dtype=kpt1.dtype)  # (17, )
    kpt_mask = kpt1[..., 2] != 0  # (N, 17)
    e = d / (2 * sigma) ** 2 / (area[:, None, None] + eps) / 2  # from cocoeval
    # e = d / ((area[None, :, None] + eps) * sigma) ** 2 / 2  # from formula
    return (torch.exp(-e) * kpt_mask[:, None]).sum(-1) / (kpt_mask.sum(-1)[:, None] + eps)




ultralytics.utils.metrics.smooth_BCE(eps=0.1)

Source code in ultralytics/utils/metrics.py
def smooth_BCE(eps=0.1):  # https://github.com/ultralytics/yolov3/issues/238#issuecomment-598028441
    # return positive, negative label smoothing BCE targets
    return 1.0 - 0.5 * eps, 0.5 * eps




ultralytics.utils.metrics.smooth(y, f=0.05)

Box filter of fraction f.

Source code in ultralytics/utils/metrics.py
def smooth(y, f=0.05):
    """Box filter of fraction f."""
    nf = round(len(y) * f * 2) // 2 + 1  # number of filter elements (must be odd)
    p = np.ones(nf // 2)  # ones padding
    yp = np.concatenate((p * y[0], y, p * y[-1]), 0)  # y padded
    return np.convolve(yp, np.ones(nf) / nf, mode='valid')  # y-smoothed




ultralytics.utils.metrics.plot_pr_curve(px, py, ap, save_dir=Path('pr_curve.png'), names=(), on_plot=None)

Plots a precision-recall curve.

Source code in ultralytics/utils/metrics.py
@plt_settings()
def plot_pr_curve(px, py, ap, save_dir=Path('pr_curve.png'), names=(), on_plot=None):
    """Plots a precision-recall curve."""
    fig, ax = plt.subplots(1, 1, figsize=(9, 6), tight_layout=True)
    py = np.stack(py, axis=1)

    if 0 < len(names) < 21:  # display per-class legend if < 21 classes
        for i, y in enumerate(py.T):
            ax.plot(px, y, linewidth=1, label=f'{names[i]} {ap[i, 0]:.3f}')  # plot(recall, precision)
    else:
        ax.plot(px, py, linewidth=1, color='grey')  # plot(recall, precision)

    ax.plot(px, py.mean(1), linewidth=3, color='blue', label='all classes %.3f mAP@0.5' % ap[:, 0].mean())
    ax.set_xlabel('Recall')
    ax.set_ylabel('Precision')
    ax.set_xlim(0, 1)
    ax.set_ylim(0, 1)
    ax.legend(bbox_to_anchor=(1.04, 1), loc='upper left')
    ax.set_title('Precision-Recall Curve')
    fig.savefig(save_dir, dpi=250)
    plt.close(fig)
    if on_plot:
        on_plot(save_dir)




ultralytics.utils.metrics.plot_mc_curve(px, py, save_dir=Path('mc_curve.png'), names=(), xlabel='Confidence', ylabel='Metric', on_plot=None)

Plots a metric-confidence curve.

Source code in ultralytics/utils/metrics.py
@plt_settings()
def plot_mc_curve(px, py, save_dir=Path('mc_curve.png'), names=(), xlabel='Confidence', ylabel='Metric', on_plot=None):
    """Plots a metric-confidence curve."""
    fig, ax = plt.subplots(1, 1, figsize=(9, 6), tight_layout=True)

    if 0 < len(names) < 21:  # display per-class legend if < 21 classes
        for i, y in enumerate(py):
            ax.plot(px, y, linewidth=1, label=f'{names[i]}')  # plot(confidence, metric)
    else:
        ax.plot(px, py.T, linewidth=1, color='grey')  # plot(confidence, metric)

    y = smooth(py.mean(0), 0.05)
    ax.plot(px, y, linewidth=3, color='blue', label=f'all classes {y.max():.2f} at {px[y.argmax()]:.3f}')
    ax.set_xlabel(xlabel)
    ax.set_ylabel(ylabel)
    ax.set_xlim(0, 1)
    ax.set_ylim(0, 1)
    ax.legend(bbox_to_anchor=(1.04, 1), loc='upper left')
    ax.set_title(f'{ylabel}-Confidence Curve')
    fig.savefig(save_dir, dpi=250)
    plt.close(fig)
    if on_plot:
        on_plot(save_dir)




ultralytics.utils.metrics.compute_ap(recall, precision)

Compute the average precision (AP) given the recall and precision curves.

Parameters:

Name Type Description Default
recall list

The recall curve.

required
precision list

The precision curve.

required

Returns:

Type Description
float

Average precision.

ndarray

Precision envelope curve.

ndarray

Modified recall curve with sentinel values added at the beginning and end.

Source code in ultralytics/utils/metrics.py
def compute_ap(recall, precision):
    """
    Compute the average precision (AP) given the recall and precision curves.

    Args:
        recall (list): The recall curve.
        precision (list): The precision curve.

    Returns:
        (float): Average precision.
        (np.ndarray): Precision envelope curve.
        (np.ndarray): Modified recall curve with sentinel values added at the beginning and end.
    """

    # Append sentinel values to beginning and end
    mrec = np.concatenate(([0.0], recall, [1.0]))
    mpre = np.concatenate(([1.0], precision, [0.0]))

    # Compute the precision envelope
    mpre = np.flip(np.maximum.accumulate(np.flip(mpre)))

    # Integrate area under curve
    method = 'interp'  # methods: 'continuous', 'interp'
    if method == 'interp':
        x = np.linspace(0, 1, 101)  # 101-point interp (COCO)
        ap = np.trapz(np.interp(x, mrec, mpre), x)  # integrate
    else:  # 'continuous'
        i = np.where(mrec[1:] != mrec[:-1])[0]  # points where x-axis (recall) changes
        ap = np.sum((mrec[i + 1] - mrec[i]) * mpre[i + 1])  # area under curve

    return ap, mpre, mrec




ultralytics.utils.metrics.ap_per_class(tp, conf, pred_cls, target_cls, plot=False, on_plot=None, save_dir=Path(), names=(), eps=1e-16, prefix='')

Computes the average precision per class for object detection evaluation.

Parameters:

Name Type Description Default
tp ndarray

Binary array indicating whether the detection is correct (True) or not (False).

required
conf ndarray

Array of confidence scores of the detections.

required
pred_cls ndarray

Array of predicted classes of the detections.

required
target_cls ndarray

Array of true classes of the detections.

required
plot bool

Whether to plot PR curves or not. Defaults to False.

False
on_plot func

A callback to pass plots path and data when they are rendered. Defaults to None.

None
save_dir Path

Directory to save the PR curves. Defaults to an empty path.

Path()
names tuple

Tuple of class names to plot PR curves. Defaults to an empty tuple.

()
eps float

A small value to avoid division by zero. Defaults to 1e-16.

1e-16
prefix str

A prefix string for saving the plot files. Defaults to an empty string.

''

Returns:

Type Description
tuple

A tuple of six arrays and one array of unique classes, where: tp (np.ndarray): True positive counts for each class. fp (np.ndarray): False positive counts for each class. p (np.ndarray): Precision values at each confidence threshold. r (np.ndarray): Recall values at each confidence threshold. f1 (np.ndarray): F1-score values at each confidence threshold. ap (np.ndarray): Average precision for each class at different IoU thresholds. unique_classes (np.ndarray): An array of unique classes that have data.

Source code in ultralytics/utils/metrics.py
def ap_per_class(tp,
                 conf,
                 pred_cls,
                 target_cls,
                 plot=False,
                 on_plot=None,
                 save_dir=Path(),
                 names=(),
                 eps=1e-16,
                 prefix=''):
    """
    Computes the average precision per class for object detection evaluation.

    Args:
        tp (np.ndarray): Binary array indicating whether the detection is correct (True) or not (False).
        conf (np.ndarray): Array of confidence scores of the detections.
        pred_cls (np.ndarray): Array of predicted classes of the detections.
        target_cls (np.ndarray): Array of true classes of the detections.
        plot (bool, optional): Whether to plot PR curves or not. Defaults to False.
        on_plot (func, optional): A callback to pass plots path and data when they are rendered. Defaults to None.
        save_dir (Path, optional): Directory to save the PR curves. Defaults to an empty path.
        names (tuple, optional): Tuple of class names to plot PR curves. Defaults to an empty tuple.
        eps (float, optional): A small value to avoid division by zero. Defaults to 1e-16.
        prefix (str, optional): A prefix string for saving the plot files. Defaults to an empty string.

    Returns:
        (tuple): A tuple of six arrays and one array of unique classes, where:
            tp (np.ndarray): True positive counts for each class.
            fp (np.ndarray): False positive counts for each class.
            p (np.ndarray): Precision values at each confidence threshold.
            r (np.ndarray): Recall values at each confidence threshold.
            f1 (np.ndarray): F1-score values at each confidence threshold.
            ap (np.ndarray): Average precision for each class at different IoU thresholds.
            unique_classes (np.ndarray): An array of unique classes that have data.

    """

    # Sort by objectness
    i = np.argsort(-conf)
    tp, conf, pred_cls = tp[i], conf[i], pred_cls[i]

    # Find unique classes
    unique_classes, nt = np.unique(target_cls, return_counts=True)
    nc = unique_classes.shape[0]  # number of classes, number of detections

    # Create Precision-Recall curve and compute AP for each class
    px, py = np.linspace(0, 1, 1000), []  # for plotting
    ap, p, r = np.zeros((nc, tp.shape[1])), np.zeros((nc, 1000)), np.zeros((nc, 1000))
    for ci, c in enumerate(unique_classes):
        i = pred_cls == c
        n_l = nt[ci]  # number of labels
        n_p = i.sum()  # number of predictions
        if n_p == 0 or n_l == 0:
            continue

        # Accumulate FPs and TPs
        fpc = (1 - tp[i]).cumsum(0)
        tpc = tp[i].cumsum(0)

        # Recall
        recall = tpc / (n_l + eps)  # recall curve
        r[ci] = np.interp(-px, -conf[i], recall[:, 0], left=0)  # negative x, xp because xp decreases

        # Precision
        precision = tpc / (tpc + fpc)  # precision curve
        p[ci] = np.interp(-px, -conf[i], precision[:, 0], left=1)  # p at pr_score

        # AP from recall-precision curve
        for j in range(tp.shape[1]):
            ap[ci, j], mpre, mrec = compute_ap(recall[:, j], precision[:, j])
            if plot and j == 0:
                py.append(np.interp(px, mrec, mpre))  # precision at mAP@0.5

    # Compute F1 (harmonic mean of precision and recall)
    f1 = 2 * p * r / (p + r + eps)
    names = [v for k, v in names.items() if k in unique_classes]  # list: only classes that have data
    names = dict(enumerate(names))  # to dict
    if plot:
        plot_pr_curve(px, py, ap, save_dir / f'{prefix}PR_curve.png', names, on_plot=on_plot)
        plot_mc_curve(px, f1, save_dir / f'{prefix}F1_curve.png', names, ylabel='F1', on_plot=on_plot)
        plot_mc_curve(px, p, save_dir / f'{prefix}P_curve.png', names, ylabel='Precision', on_plot=on_plot)
        plot_mc_curve(px, r, save_dir / f'{prefix}R_curve.png', names, ylabel='Recall', on_plot=on_plot)

    i = smooth(f1.mean(0), 0.1).argmax()  # max F1 index
    p, r, f1 = p[:, i], r[:, i], f1[:, i]
    tp = (r * nt).round()  # true positives
    fp = (tp / (p + eps) - tp).round()  # false positives
    return tp, fp, p, r, f1, ap, unique_classes.astype(int)




Created 2023-07-16, Updated 2023-08-22
Authors: glenn-jocher (6), Laughing-q (1)