2021SC@SDUSC山东大学软件学院软件工程应用与实践--YOLOV5代码分析(十三)metrics.py-1

2021SC@SDUSC

前言

这篇分析metrics.py文件,这个文件是用来计算评估指标,包括mAP、混淆矩阵、IOU相关的函数。

fitness函数

def fitness(x):
    # Model fitness as a weighted combination of metrics
    w = [0.0, 0.0, 0.1, 0.9]  # weights for [P, R, [email protected], [email protected]:0.95]
    return (x[:, :4] * w).sum(1)

这个函数用来计算最终的mAP,通过对P、R、[email protected][email protected]:0.95的加权平均计算mAP

ap_per_class函数

def ap_per_class(tp, conf, pred_cls, target_cls, plot=False, save_dir='.', names=()):
    """ Compute the average precision, given the recall and precision curves.
    Source: https://github.com/rafaelpadilla/Object-Detection-Metrics.
    # Arguments
        tp:  True positives (nparray, nx1 or nx10).
        conf:  Objectness value from 0-1 (nparray).
        pred_cls:  Predicted object classes (nparray).
        target_cls:  True object classes (nparray).
        plot:  Plot precision-recall curve at [email protected]
        save_dir:  Plot save directory
    # Returns
        The average precision as computed in py-faster-rcnn.
    """

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

    # Find unique classes
    unique_classes = np.unique(target_cls)
    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 = (target_cls == c).sum()  # number of labels
        n_p = i.sum()  # number of predictions

        if n_p == 0 or n_l == 0:
            continue
        else:
            # Accumulate FPs and TPs
            fpc = (1 - tp[i]).cumsum(0)
            tpc = tp[i].cumsum(0)

            # Recall
            recall = tpc / (n_l + 1e-16)  # 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 [email protected]

    # Compute F1 (harmonic mean of precision and recall)
    f1 = 2 * p * r / (p + r + 1e-16)
    if plot:
        plot_pr_curve(px, py, ap, Path(save_dir) / 'PR_curve.png', names)
        plot_mc_curve(px, f1, Path(save_dir) / 'F1_curve.png', names, ylabel='F1')
        plot_mc_curve(px, p, Path(save_dir) / 'P_curve.png', names, ylabel='Precision')
        plot_mc_curve(px, r, Path(save_dir) / 'R_curve.png', names, ylabel='Recall')

    i = f1.mean(0).argmax()  # max F1 index
    return p[:, i], r[:, i], ap, f1[:, i], unique_classes.astype('int32')

计算每一个类的平均precision并绘制P-R曲线

参数:

tp:true positive

conf:预测框的conf

pred_cls:预测框的class

target_cls:GT的class

plot:是否绘制PR曲线

save_dir:保存路径

返回值:

p:最大平均f1时每个类别的precision

r:最大平均f1时每个类别的recall

ap:每个类别在10个iou阈值下的mAP

f1:最大平均f1时每个类别的f1

unique_classes:数据集中所有的类别index

i = np.argsort(-conf)

按conf从大到小排序,返回数据对应的索引

tp, conf, pred_cls = tp[i], conf[i], pred_cls[i]

得到重新排序后对应的tp、conf、pred_cls

unique_classes = np.unique(target_cls)
nc = unique_classes.shape[0]

对类别去重,nc为类别数

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))

初始化

    for ci, c in enumerate(unique_classes):
        i = pred_cls == c
        n_l = (target_cls == c).sum()  # number of labels
        n_p = i.sum()  # number of predictions

        if n_p == 0 or n_l == 0:
            continue
        else:
            # Accumulate FPs and TPs
            fpc = (1 - tp[i]).cumsum(0)
            tpc = tp[i].cumsum(0)

            # Recall
            recall = tpc / (n_l + 1e-16)  # 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 [email protected]

计算fp、tp、recall、precision

f1 = 2 * p * r / (p + r + 1e-16)

计算f1

    if plot:
        plot_pr_curve(px, py, ap, Path(save_dir) / 'PR_curve.png', names)
        plot_mc_curve(px, f1, Path(save_dir) / 'F1_curve.png', names, ylabel='F1')
        plot_mc_curve(px, p, Path(save_dir) / 'P_curve.png', names, ylabel='Precision')
        plot_mc_curve(px, r, Path(save_dir) / 'R_curve.png', names, ylabel='Recall')

画出pr曲线

compute_ap函数

def compute_ap(recall, precision):
    """ Compute the average precision, given the recall and precision curves
    # Arguments
        recall:    The recall curve (list)
        precision: The precision curve (list)
    # Returns
        Average precision, precision curve, recall curve
    """

    # 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

计算某个类别在某个iou阈值下的mAP

返回值:

ap:平均precision

mpre:添加保护值的precision

mrec:添加保护值的recall

该函数根据给定不同阈值下的precision和recall,计算出mAP

ConfusionMatrix类

class ConfusionMatrix:
    # Updated version of https://github.com/kaanakan/object_detection_confusion_matrix
    def __init__(self, nc, conf=0.25, iou_thres=0.45):
        self.matrix = np.zeros((nc + 1, nc + 1))
        self.nc = nc  # number of classes
        self.conf = conf
        self.iou_thres = iou_thres

    def process_batch(self, detections, labels):
        """
        Return intersection-over-union (Jaccard index) of boxes.
        Both sets of boxes are expected to be in (x1, y1, x2, y2) format.
        Arguments:
            detections (Array[N, 6]), x1, y1, x2, y2, conf, class
            labels (Array[M, 5]), class, x1, y1, x2, y2
        Returns:
            None, updates confusion matrix accordingly
        """
        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(np.int16)
        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  # background FP

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

    def matrix(self):
        return self.matrix

    def plot(self, normalize=True, save_dir='', names=()):
        try:
            import seaborn as sn

            array = self.matrix / ((self.matrix.sum(0).reshape(1, -1) + 1E-6) if normalize else 1)  # normalize columns
            array[array < 0.005] = np.nan  # don't annotate (would appear as 0.00)

            fig = plt.figure(figsize=(12, 9), tight_layout=True)
            sn.set(font_scale=1.0 if self.nc < 50 else 0.8)  # for label size
            labels = (0 < len(names) < 99) and len(names) == self.nc  # apply names to ticklabels
            with warnings.catch_warnings():
                warnings.simplefilter('ignore')  # suppress empty matrix RuntimeWarning: All-NaN slice encountered
                sn.heatmap(array, annot=self.nc < 30, annot_kws={"size": 8}, cmap='Blues', fmt='.2f', square=True,
                           xticklabels=names + ['background FP'] if labels else "auto",
                           yticklabels=names + ['background FN'] if labels else "auto").set_facecolor((1, 1, 1))
            fig.axes[0].set_xlabel('True')
            fig.axes[0].set_ylabel('Predicted')
            fig.savefig(Path(save_dir) / 'confusion_matrix.png', dpi=250)
            plt.close()
        except Exception as e:
            print(f'WARNING: ConfusionMatrix plot failure: {e}')

    def print(self):
        for i in range(self.nc + 1):
            print(' '.join(map(str, self.matrix[i])))

计算混淆矩阵

init方法

 def __init__(self, nc, conf=0.25, iou_thres=0.45):
        self.matrix = np.zeros((nc + 1, nc + 1))
        self.nc = nc  # number of classes
        self.conf = conf
        self.iou_thres = iou_thres

初始化,nc:类别个数,conf:预测框置信度阈值,iou_thres:iou阈值

process_batch方法

detections:预测结果

labels:目标结果

detections = detections[detections[:, 4] > self.conf]

筛除置信度过低的预测框

gt_classes = labels[:, 0].int()

所有gt框类别

detection_classes = detections[:, 5].int()

所有预测框类别

iou = box_iou(labels[:, 1:], detections[:, :4])

求出所有gt框和所有预测框的iou

x = torch.where(iou > self.iou_thres)

选出大于阈值的

        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))

得到每一种预测框和所有gt框中iou最大的

        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  # background FP

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

计算混肴矩阵

matrix方法

    def matrix(self):
        return self.matrix

返回混肴矩阵

plot和print方法

plot用于可视化混肴矩阵,print方法则是用来输出打印混肴矩阵,就不仔细说了

总结

用到了比较多的numpy矩阵操作,比较复杂,需要仔细debug才能搞懂,剩下的部分下一篇继续。

你可能感兴趣的:(目标检测,python,目标检测,计算机视觉)