2021SC@SDUSC山东大学软件学院软件工程应用与实践--YOLOV5代码分析（十四）metrics.py-2

最新推荐文章于 2024-05-20 19:08:38 发布

xjunjin

最新推荐文章于 2024-05-20 19:08:38 发布

阅读量2.1k

点赞数 1

分类专栏： yolov5 文章标签：目标检测计算机视觉人工智能

本文链接：https://blog.csdn.net/xjunjin/article/details/121632967

版权

yolov5 专栏收录该内容

18 篇文章 25 订阅

订阅专栏

2021SC@SDUSC

前言

本篇继续分析metrics文件，主要是一些计算IOU的方法

bbox_iou函数

def bbox_iou(box1, box2, x1y1x2y2=True, GIoU=False, DIoU=False, CIoU=False, eps=1e-7):
    # Returns the IoU of box1 to box2. box1 is 4, box2 is nx4
    box2 = box2.T

    # Get the coordinates of bounding boxes
    if x1y1x2y2:  # x1, y1, x2, y2 = box1
        b1_x1, b1_y1, b1_x2, b1_y2 = box1[0], box1[1], box1[2], box1[3]
        b2_x1, b2_y1, b2_x2, b2_y2 = box2[0], box2[1], box2[2], box2[3]
    else:  # transform from xywh to xyxy
        b1_x1, b1_x2 = box1[0] - box1[2] / 2, box1[0] + box1[2] / 2
        b1_y1, b1_y2 = box1[1] - box1[3] / 2, box1[1] + box1[3] / 2
        b2_x1, b2_x2 = box2[0] - box2[2] / 2, box2[0] + box2[2] / 2
        b2_y1, b2_y2 = box2[1] - box2[3] / 2, box2[1] + box2[3] / 2

    # Intersection area
    inter = (torch.min(b1_x2, b2_x2) - torch.max(b1_x1, b2_x1)).clamp(0) * \
            (torch.min(b1_y2, b2_y2) - torch.max(b1_y1, b2_y1)).clamp(0)

    # Union Area
    w1, h1 = b1_x2 - b1_x1, b1_y2 - b1_y1 + eps
    w2, h2 = b2_x2 - b2_x1, b2_y2 - b2_y1 + eps
    union = w1 * h1 + w2 * h2 - inter + eps

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

该函数计算box1于box2之间的IOU值，box1是4维的向量，box2是n*4的矩阵

参数：

box1：如上

box2：如上

x1y1x2y2：box的形式是否是xyxy

GIoU：计算GIoU的值

DIoU：计算DIoU的值

CIoU：计算CIoU的值

# Get the coordinates of bounding boxes
    if x1y1x2y2:  # x1, y1, x2, y2 = box1
        b1_x1, b1_y1, b1_x2, b1_y2 = box1[0], box1[1], box1[2], box1[3]
        b2_x1, b2_y1, b2_x2, b2_y2 = box2[0], box2[1], box2[2], box2[3]
    else:  # transform from xywh to xyxy
        b1_x1, b1_x2 = box1[0] - box1[2] / 2, box1[0] + box1[2] / 2
        b1_y1, b1_y2 = box1[1] - box1[3] / 2, box1[1] + box1[3] / 2
        b2_x1, b2_x2 = box2[0] - box2[2] / 2, box2[0] + box2[2] / 2
        b2_y1, b2_y2 = box2[1] - box2[3] / 2, box2[1] + box2[3] / 2

将box的坐标取出来，如果是xywh的形式则将其转换为xyxy的形式

# Intersection area
    inter = (torch.min(b1_x2, b2_x2) - torch.max(b1_x1, b2_x1)).clamp(0) * \
            (torch.min(b1_y2, b2_y2) - torch.max(b1_y1, b2_y1)).clamp(0)

计算box1和box2交叉的面积

# Union Area
    w1, h1 = b1_x2 - b1_x1, b1_y2 - b1_y1 + eps
    w2, h2 = b2_x2 - b2_x1, b2_y2 - b2_y1 + eps
    union = w1 * h1 + w2 * h2 - inter + eps

计算box1和box2的union 面积

    if GIoU or DIoU or CIoU:
        cw = torch.max(b1_x2, b2_x2) - torch.min(b1_x1, b2_x1)  # convex (smallest enclosing box) width
        ch = torch.max(b1_y2, b2_y2) - torch.min(b1_y1, 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 distance squared
            if DIoU:
                return iou - rho2 / c2  # DIoU
            elif CIoU:  # https://github.com/Zzh-tju/DIoU-SSD-pytorch/blob/master/utils/box/box_utils.py#L47
                v = (4 / math.pi ** 2) * torch.pow(torch.atan(w2 / h2) - torch.atan(w1 / h1), 2)
                with torch.no_grad():
                    alpha = v / (v - iou + (1 + eps))
                return iou - (rho2 / c2 + v * alpha)  # CIoU
        else:  # GIoU https://arxiv.org/pdf/1902.09630.pdf
            c_area = cw * ch + eps  # convex area
            return iou - (c_area - union) / c_area  # GIoU
    else:
        return iou  # IoU

接下来的代码就是根据参数来计算GIou、DIoU、CIoU，下面将重点介绍一下这三个评估指标。

GIoU

论文地址：https://arxiv.org/pdf/1902.09630.pdf

计算方法如下：

假设蓝色框为A，灰色框为B，黄色框就是上式的C，GIoU就是用IoU减去A和B不在A和B闭包的占闭包的比率。在代码中c_area即上面公式中的C，cw和ch分别是C的宽和高。

DIoU

计算公式如下

$IoU-\frac{d^2}{c^2}$

$d^2=(\frac{x_{gt}-x_{predict}}{2})^2+(\frac{y_{gt}-y_{predict}}{2})^2$

$c^2=cw^2+ch^2$

d是GT与预测框中心的距离，c是闭包的对角线长度。

CIoU

CIoU在DIoU的基础上又减去了一项：

$CIoU=IoU-GIoU-\alpha*v$

$v=\frac{4}{\pi^2}*(arctan\frac{w2}{h2}-arctan\frac{w1}{h1})^2$

$\alpha=\frac{v}{v-IoU+1}$

论文地址：https://arxiv.org/pdf/1911.08287.pdf

这样再来看代码就能够轻易读懂了，其实就是一些公式的计算方法。

box_iou函数

def box_iou(box1, box2):
    # https://github.com/pytorch/vision/blob/master/torchvision/ops/boxes.py
    """
    Return intersection-over-union (Jaccard index) of boxes.
    Both sets of boxes are expected to be in (x1, y1, x2, y2) format.
    Arguments:
        box1 (Tensor[N, 4])
        box2 (Tensor[M, 4])
    Returns:
        iou (Tensor[N, M]): the NxM matrix containing the pairwise
            IoU values for every element in boxes1 and boxes2
    """

    def box_area(box):
        # box = 4xn
        return (box[2] - box[0]) * (box[3] - box[1])

    area1 = box_area(box1.T)
    area2 = box_area(box2.T)

    # inter(N,M) = (rb(N,M,2) - lt(N,M,2)).clamp(0).prod(2)
    inter = (torch.min(box1[:, None, 2:], box2[:, 2:]) - torch.max(box1[:, None, :2], box2[:, :2])).clamp(0).prod(2)
    return inter / (area1[:, None] + area2 - inter)  # iou = inter / (area1 + area2 - inter)

这个函数直接计算box1和box2的iou值，box_area函数计算给定box的面积，再计算交并比并返回

bbox_ioa函数

def bbox_ioa(box1, box2, eps=1E-7):
    """ Returns the intersection over box2 area given box1, box2. Boxes are x1y1x2y2
    box1:       np.array of shape(4)
    box2:       np.array of shape(nx4)
    returns:    np.array of shape(n)
    """

    box2 = box2.transpose()

    # Get the coordinates of bounding boxes
    b1_x1, b1_y1, b1_x2, b1_y2 = box1[0], box1[1], box1[2], box1[3]
    b2_x1, b2_y1, b2_x2, b2_y2 = box2[0], box2[1], box2[2], box2[3]

    # Intersection area
    inter_area = (np.minimum(b1_x2, b2_x2) - np.maximum(b1_x1, b2_x1)).clip(0) * \
                 (np.minimum(b1_y2, b2_y2) - np.maximum(b1_y1, b2_y1)).clip(0)

    # box2 area
    box2_area = (b2_x2 - b2_x1) * (b2_y2 - b2_y1) + eps

    # Intersection over box2 area
    return inter_area / box2_area

该函数计算IoU与box2面积的比值

wh_iou函数

def wh_iou(wh1, wh2):
    # Returns the nxm IoU matrix. wh1 is nx2, wh2 is mx2
    wh1 = wh1[:, None]  # [N,1,2]
    wh2 = wh2[None]  # [1,M,2]
    inter = torch.min(wh1, wh2).prod(2)  # [N,M]
    return inter / (wh1.prod(2) + wh2.prod(2) - inter)  # iou = inter / (area1 + area2 - inter)

计算给定wh1和wh2的iou矩阵，返回的矩阵大小为N*M

plot

# Plots ----------------------------------------------------------------------------------------------------------------

def plot_pr_curve(px, py, ap, save_dir='pr_curve.png', names=()):
    # 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)
    plt.legend(bbox_to_anchor=(1.04, 1), loc="upper left")
    fig.savefig(Path(save_dir), dpi=250)
    plt.close()


def plot_mc_curve(px, py, save_dir='mc_curve.png', names=(), xlabel='Confidence', ylabel='Metric'):
    # 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 = py.mean(0)
    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)
    plt.legend(bbox_to_anchor=(1.04, 1), loc="upper left")
    fig.savefig(Path(save_dir), dpi=250)
    plt.close()

这两个函数用来画出pr曲线和mc曲线，就简单带过了。

总结

这篇内容总的来说比较简单，只要理解了几个公式基本都可以看懂，IoU是yolo对模型性能评估的一个重要指标，也是模型在训练过程中必不可少的一个值，在非极大值抑制中就需要用到IoU，通过设定一个阈值，将IoU值低于该阈值的预测框都移除掉；同时IoU也可以当作损失函数来评估模型。

xjunjin

关注

1
点赞
踩
9

收藏

觉得还不错? 一键收藏
1
评论
2021SC@SDUSC山东大学软件学院软件工程应用与实践--YOLOV5代码分析（十四）metrics.py-2

2021SC@SDUSC目录前言bbox_iou函数GIoUDIoUCIoUbox_iou函数bbox_ioa函数wh_iou函数plot总结前言本篇继续分析metrics文件，主要是一些计算IOU的方法bbox_iou函数def bbox_iou(box1, box2, x1y1x2y2=True, GIoU=False, DIoU=False, CIoU=False, eps=1e-7): # Returns the IoU of
复制链接

扫一扫