优化改进YOLOv5算法之添加GIoU、DIoU、CIoU、EIoU、Wise-IoU模块(超详细)

目录

1、IoU

1.1 什么是IOU

 1.2 IOU代码

2、GIOU

2.1 为什么提出GIOU

2.2 GIoU代码

3 DIoU 

3.1 为什么提出DIOU

3.2 DIOU代码

4 CIOU

4.1 为什么提出CIOU

4.2 CIOU代码

5 EIOU

5.1 为什么提出EIOU 

5.2 EIOU代码

6 Wise-IoU

7 YOLOv5中添加GIoU、DIoU、CIoU、EIoU、Wise-IoU损失函数

---

1、IoU

1.1 什么是IOU

论文链接为：UnitBox: An Advanced Object Detection Network

IoU 的全称为交并比（Intersection over Union），通过这个名称我们大概可以猜到 IoU 的计算方法。IoU 计算的是 “预测的边框” 和 “真实的边框” 的交集和并集的比值。计算过程如下：

其中，绿色面积代表预测框B与真实框A的交集；则

显而易见，IOU的值越高也说明预测框与真实框重合程度越高，代表模型预测越准确，反之，IOU越低模型性能越差。 

但是，IOU作为损失函数会出现以下问题：

• 如果两个框没有相交，根据定义，IoU=0，不能度量IoU为零距离远近的程度。同时因为loss=0，没有梯度回传，无法进行学习训练。
• IoU无法精确的反映两者的重合度大小。如下图所示，三种情况IoU都相等，但看得出来他们的重合度是不一样的，左边的图回归的效果最好，右边的最差。

 1.2 IOU代码

import numpy as np
def Iou(box1, box2, wh=False):if wh == False:xmin1, ymin1, xmax1, ymax1 = box1xmin2, ymin2, xmax2, ymax2 = box2else:xmin1, ymin1 = int(box1[0]-box1[2]/2.0), int(box1[1]-box1[3]/2.0)xmax1, ymax1 = int(box1[0]+box1[2]/2.0), int(box1[1]+box1[3]/2.0)xmin2, ymin2 = int(box2[0]-box2[2]/2.0), int(box2[1]-box2[3]/2.0)xmax2, ymax2 = int(box2[0]+box2[2]/2.0), int(box2[1]+box2[3]/2.0)# 获取矩形框交集对应的左上角和右下角的坐标（intersection）xx1 = np.max([xmin1, xmin2])yy1 = np.max([ymin1, ymin2])xx2 = np.min([xmax1, xmax2])yy2 = np.min([ymax1, ymax2])	# 计算两个矩形框面积area1 = (xmax1-xmin1) * (ymax1-ymin1) area2 = (xmax2-xmin2) * (ymax2-ymin2)inter_area = (np.max([0, xx2-xx1])) * (np.max([0, yy2-yy1]))　#计算交集面积iou = inter_area / (area1+area2-inter_area+1e-6) 　#计算交并比return iou

2、GIOU

论文链接：Generalized Intersection over Union: A Metric and A Loss for Bounding Box Regression

2.1 为什么提出GIOU

为了解决上面两个问题，这篇论文提出了GIOU。由于IoU是比值的概念，对目标物体的scale是不敏感的。然而目标检测任务中的BBox的回归损失(MSE loss, l1-smooth loss等）优化和IoU优化不是完全等价的，而且 Ln 范数对物体的scale也比较敏感，IoU无法直接优化没有重叠的部分。这篇论文提出可以直接把IoU设为回归的loss。

GIOU的计算很简单，对于两个bounding box A和B。我们可以算出其最小凸集（同时包含了预测框和真实框的最小框的面积）C，有了最小凸集，就可以计算GIOU，如下所示

从公式可以看出，GIOU有几个优点：

• GIOU是IOU的下界，且取值范围为(-1, 1]。当两个框不重合时，IOU始终为0，不论A、B相隔多远，但是对于GIOU来说，A，B不重合度越高（离的越远），GIOU越趋近于-1。
• GIOU其实就是在IOU的基础上减掉了一个东西，这个减掉的东西，避免了两个bbox不重合时Loss为0的情况;
• 可导：这一点需要强调下，由于max，min，分段函数(比如ReLU)这些都是可导的，所以用1-GIOU作为Loss是可导的。
• 与IoU只关注重叠区域不同，GIoU不仅关注重叠区域，还关注其他的非重合区域，能更好的反映两者的重合度。

但是GIOU同样存在一些问题，主要有：

• 状态1、2、3都是预测框在目标框内部且预测框大小一致的情况，这时预测框和目标框的差集都是相同的，因此这三种状态的GIOU值也都是相同的，这时GIOU退化成了IOU，无法区分相对位置关系；
• GIOU收敛较慢、回归不够准确。

2.2 GIoU代码

import numpy as npdef Giou_np(bbox_p, bbox_g):""":param bbox_p: predict of bbox(N,4)(x1,y1,x2,y2):param bbox_g: groundtruth of bbox(N,4)(x1,y1,x2,y2):return:"""# for details should go to https://arxiv.org/pdf/1902.09630.pdf# ensure predict's bbox formx1p = np.minimum(bbox_p[:, 0], bbox_p[:, 2]).reshape(-1,1)x2p = np.maximum(bbox_p[:, 0], bbox_p[:, 2]).reshape(-1,1)y1p = np.minimum(bbox_p[:, 1], bbox_p[:, 3]).reshape(-1,1)y2p = np.maximum(bbox_p[:, 1], bbox_p[:, 3]).reshape(-1,1)bbox_p = np.concatenate([x1p, y1p, x2p, y2p], axis=1)# calc area of Bgarea_p = (bbox_p[:, 2] - bbox_p[:, 0]) * (bbox_p[:, 3] - bbox_p[:, 1])# calc area of Bparea_g = (bbox_g[:, 2] - bbox_g[:, 0]) * (bbox_g[:, 3] - bbox_g[:, 1])# cal intersectionx1I = np.maximum(bbox_p[:, 0], bbox_g[:, 0])y1I = np.maximum(bbox_p[:, 1], bbox_g[:, 1])x2I = np.minimum(bbox_p[:, 2], bbox_g[:, 2])y2I = np.minimum(bbox_p[:, 3], bbox_g[:, 3])I = np.maximum((y2I - y1I), 0) * np.maximum((x2I - x1I), 0)# find enclosing boxx1C = np.minimum(bbox_p[:, 0], bbox_g[:, 0])y1C = np.minimum(bbox_p[:, 1], bbox_g[:, 1])x2C = np.maximum(bbox_p[:, 2], bbox_g[:, 2])y2C = np.maximum(bbox_p[:, 3], bbox_g[:, 3])# calc area of Bcarea_c = (x2C - x1C) * (y2C - y1C)U = area_p + area_g - Iiou = 1.0 * I / U# Giougiou = iou - (area_c - U) / area_c# loss_iou = 1 - iou loss_giou = 1 - giouloss_iou = 1.0 - iouloss_giou = 1.0 - gioureturn giou, loss_iou, loss_giou# def giou_tfif __name__ == '__main__':p = np.array([[21,45,103,172],[34,283,155,406],[202,174,271,255]])g = np.array([[59,106,154,230],[71,272,191,419],[257,244,329,351]])Giou_np(p, g)

3 DIoU 

论文连接：Distance-IoU Loss: Faster and Better Learning for Bounding Box Regression

3.1 为什么提出DIOU

一个好的目标框回归函数应该考虑三个重要几何因素：重叠面积、中心点距离，长宽比。

针对IOU和GIOU存在的问题，作者从两个方面进行考虑

• 如何最小化预测框和目标框之间的归一化距离？
• 如何在预测框和目标框重叠时，回归的更准确？

 针对第一个问题，提出了DIOU_Loss（Distance_IOU_Loss）

DIOU_Loss考虑了重叠面积和中心点距离，当目标框包裹预测框的时候，直接度量2个框的距离，因此DIOU_Loss收敛的更快。DIOU损失的优点有：

• 与GIoU loss类似，DIoU loss在与目标框不重叠时，仍然可以为边界框提供移动方向。
• DIoU loss可以直接最小化两个目标框的距离，因此比GIoU loss收敛快得多。
• 对于包含两个框在水平方向和垂直方向上这种情况，DIoU损失可以使回归非常快，而GIoU损失几乎退化为IoU损失。
• DIoU还可以替换普通的IoU评价策略，应用于NMS中，使得NMS得到的结果更加合理和有效。

但DIOU同样存在缺点，那就是没有考虑到长宽比。比如下面三种情况，目标框包裹预测框，本来DIOU_Loss可以起作用。但预测框的中心点的位置都是一样的，因此按照DIOU_Loss的计算公式，三者的值都是相同的。

3.2 DIOU代码

def Diou(bboxes1, bboxes2):rows = bboxes1.shape[0]cols = bboxes2.shape[0]dious = torch.zeros((rows, cols))if rows * cols == 0:#return diousexchange = Falseif bboxes1.shape[0] > bboxes2.shape[0]:bboxes1, bboxes2 = bboxes2, bboxes1dious = torch.zeros((cols, rows))exchange = True# #xmin,ymin,xmax,ymax->[:,0],[:,1],[:,2],[:,3]w1 = bboxes1[:, 2] - bboxes1[:, 0]h1 = bboxes1[:, 3] - bboxes1[:, 1] w2 = bboxes2[:, 2] - bboxes2[:, 0]h2 = bboxes2[:, 3] - bboxes2[:, 1]area1 = w1 * h1area2 = w2 * h2center_x1 = (bboxes1[:, 2] + bboxes1[:, 0]) / 2 center_y1 = (bboxes1[:, 3] + bboxes1[:, 1]) / 2 center_x2 = (bboxes2[:, 2] + bboxes2[:, 0]) / 2center_y2 = (bboxes2[:, 3] + bboxes2[:, 1]) / 2inter_max_xy = torch.min(bboxes1[:, 2:],bboxes2[:, 2:]) inter_min_xy = torch.max(bboxes1[:, :2],bboxes2[:, :2]) out_max_xy = torch.max(bboxes1[:, 2:],bboxes2[:, 2:]) out_min_xy = torch.min(bboxes1[:, :2],bboxes2[:, :2])inter = torch.clamp((inter_max_xy - inter_min_xy), min=0)inter_area = inter[:, 0] * inter[:, 1]inter_diag = (center_x2 - center_x1)**2 + (center_y2 - center_y1)**2outer = torch.clamp((out_max_xy - out_min_xy), min=0)outer_diag = (outer[:, 0] ** 2) + (outer[:, 1] ** 2)union = area1+area2-inter_areadious = inter_area / union - (inter_diag) / outer_diagdious = torch.clamp(dious,min=-1.0,max = 1.0)if exchange:dious = dious.Treturn dious

4 CIOU

论文链接：Distance-IoU Loss: Faster and Better Learning for Bounding Box Regression

4.1 为什么提出CIOU

 CIOU论文考虑到bbox回归三要素中的长宽比还没被考虑到计算中，因此，进一步在DIoU的基础上提出了CIoU。其惩罚项如下面公式：

其中是权重函数，而用来度量长宽比的相似性，定义为

 完整的CIOU损失函数定义：

4.2 CIOU代码

def bbox_overlaps_ciou(bboxes1, bboxes2):rows = bboxes1.shape[0]cols = bboxes2.shape[0]cious = torch.zeros((rows, cols))if rows * cols == 0:return ciousexchange = Falseif bboxes1.shape[0] > bboxes2.shape[0]:bboxes1, bboxes2 = bboxes2, bboxes1cious = torch.zeros((cols, rows))exchange = Truew1 = bboxes1[:, 2] - bboxes1[:, 0]h1 = bboxes1[:, 3] - bboxes1[:, 1]w2 = bboxes2[:, 2] - bboxes2[:, 0]h2 = bboxes2[:, 3] - bboxes2[:, 1]area1 = w1 * h1area2 = w2 * h2center_x1 = (bboxes1[:, 2] + bboxes1[:, 0]) / 2center_y1 = (bboxes1[:, 3] + bboxes1[:, 1]) / 2center_x2 = (bboxes2[:, 2] + bboxes2[:, 0]) / 2center_y2 = (bboxes2[:, 3] + bboxes2[:, 1]) / 2inter_max_xy = torch.min(bboxes1[:, 2:],bboxes2[:, 2:])inter_min_xy = torch.max(bboxes1[:, :2],bboxes2[:, :2])out_max_xy = torch.max(bboxes1[:, 2:],bboxes2[:, 2:])out_min_xy = torch.min(bboxes1[:, :2],bboxes2[:, :2])inter = torch.clamp((inter_max_xy - inter_min_xy), min=0)inter_area = inter[:, 0] * inter[:, 1]inter_diag = (center_x2 - center_x1)**2 + (center_y2 - center_y1)**2outer = torch.clamp((out_max_xy - out_min_xy), min=0)outer_diag = (outer[:, 0] ** 2) + (outer[:, 1] ** 2)union = area1+area2-inter_areau = (inter_diag) / outer_diagiou = inter_area / unionwith torch.no_grad():arctan = torch.atan(w2 / h2) - torch.atan(w1 / h1)v = (4 / (math.pi ** 2)) * torch.pow((torch.atan(w2 / h2) - torch.atan(w1 / h1)), 2)S = 1 - ioualpha = v / (S + v)w_temp = 2 * w1ar = (8 / (math.pi ** 2)) * arctan * ((w1 - w_temp) * h1)cious = iou - (u + alpha * ar)cious = torch.clamp(cious,min=-1.0,max = 1.0)if exchange:cious = cious.Treturn cious

5 EIOU

论文链接：Focal and Efficient IOU Loss for Accurate Bounding Box Regression

5.1 为什么提出EIOU 

CIOU Loss虽然考虑了边界框回归的重叠面积、中心点距离、纵横比。但是通过其公式中的v反映的纵横比的差异，而不是宽高分别与其置信度的真实差异，所以有时会阻碍模型有效的优化相似性，于是提出EIOU，它的主要思想是：

•  一是认为CIoU loss对于长宽比加入loss的设计不太合理，于是将CIoU loss中反应长宽比一致性的部分替换成了分别对于长和宽的一致性loss，形成了EIoU loss。
•         二是认为不太好的回归样本对回归loss产生了比较大的影响，回归质量相对较好的样本则难以进一步优化，所以论文提出Focal EIoU loss进行回归质量较好和质量较差的样本之间的平衡。

EIOU Loss优点：

• 1）将纵横比的损失项拆分成预测的宽高分别与最小外接框宽高的差值，加速了收敛提高了回归精度。
• 2）引入了Focal Loss优化了边界框回归任务中的样本不平衡问题，即减少与目标框重叠较少的大量锚框对BBox 回归的优化贡献，使回归过程专注于高质量锚框。

5.2 EIOU代码

def bbox_iou(box1, box2, x1y1x2y2=True, GIoU=False, DIoU=False, CIoU=False,  EIoU=False, eps=1e-7):# Returns the IoU of box1 to box2. box1 is 4, box2 is nx4box2 = box2.T# Get the coordinates of bounding boxesif x1y1x2y2:  # x1, y1, x2, y2 = box1b1_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 xyxyb1_x1, b1_x2 = box1[0] - box1[2] / 2, box1[0] + box1[2] / 2b1_y1, b1_y2 = box1[1] - box1[3] / 2, box1[1] + box1[3] / 2b2_x1, b2_x2 = box2[0] - box2[2] / 2, box2[0] + box2[2] / 2b2_y1, b2_y2 = box2[1] - box2[3] / 2, box2[1] + box2[3] / 2# Intersection areainter = (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 Areaw1, h1 = b1_x2 - b1_x1, b1_y2 - b1_y1 + epsw2, h2 = b2_x2 - b2_x1, b2_y2 - b2_y1 + epsunion = w1 * h1 + w2 * h2 - inter + epsiou = inter / unionif GIoU or DIoU or CIoU or EIoU:cw = torch.max(b1_x2, b2_x2) - torch.min(b1_x1, b2_x1)  # convex (smallest enclosing box) widthch = torch.max(b1_y2, b2_y2) - torch.min(b1_y1, b2_y1)  # convex heightif CIoU or DIoU or EIoU:  # Distance or Complete IoU https://arxiv.org/abs/1911.08287v1c2 = cw ** 2 + ch ** 2 + eps  # convex diagonal squaredrho2 = ((b2_x1 + b2_x2 - b1_x1 - b1_x2) ** 2 +(b2_y1 + b2_y2 - b1_y1 - b1_y2) ** 2) / 4  # center distance squaredif DIoU:return iou - rho2 / c2  # DIoUelif CIoU:  # https://github.com/Zzh-tju/DIoU-SSD-pytorch/blob/master/utils/box/box_utils.py#L47v = (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)  # CIoUelif EIoU:rho_w2 = ((b2_x2 - b2_x1) - (b1_x2 - b1_x1)) ** 2rho_h2 = ((b2_y2 - b2_y1) - (b1_y2 - b1_y1)) ** 2cw2 = cw ** 2 + epsch2 = ch ** 2 + epsreturn iou - (rho2 / c2 + rho_w2 / cw2 + rho_h2 / ch2)else:  # GIoU https://arxiv.org/pdf/1902.09630.pdfc_area = cw * ch + eps  # convex areareturn iou - (c_area - union) / c_area  # GIoUelse:return iou  # IoU

6 Wise-IoU

论文链接：Wise-IoU: Bounding Box Regression Loss with Dynamic Focusing Mechanism

具体关于Wise-IoU损失的介绍请参考前期博客

优化改进YOLOv5算法之Wise-IOU损失函数_yolov5算法优化_AI追随者的博客-CSDN博客

7 YOLOv5中添加GIoU、DIoU、CIoU、EIoU、Wise-IoU损失函数

 yolov5-6.1版本中的iou损失函数是在utils/metrics.py文件定义的，在该文件添加以下关于GIoU、DIoU、CIoU、EIoU、Wise-IoU函数的代码，如下所示

import numpy as np
import torch, mathclass WIoU_Scale:''' monotonous: {None: origin v1True: monotonic FM v2False: non-monotonic FM v3}momentum: The momentum of running mean'''iou_mean = 1.monotonous = False_momentum = 1 - 0.5 ** (1 / 7000)_is_train = Truedef __init__(self, iou):self.iou = iouself._update(self)@classmethoddef _update(cls, self):if cls._is_train: cls.iou_mean = (1 - cls._momentum) * cls.iou_mean + \cls._momentum * self.iou.detach().mean().item()@classmethoddef _scaled_loss(cls, self, gamma=1.9, delta=3):if isinstance(self.monotonous, bool):if self.monotonous:return (self.iou.detach() / self.iou_mean).sqrt()else:beta = self.iou.detach() / self.iou_meanalpha = delta * torch.pow(gamma, beta - delta)return beta / alphareturn 1def bbox_iou(box1, box2, xywh=True, GIoU=False, DIoU=False, CIoU=False, SIoU=False, EIoU=False, WIoU=False, Focal=False, alpha=1, gamma=0.5, scale=False, eps=1e-7):# Returns Intersection over Union (IoU) of box1(1,4) to box2(n,4)# Get the coordinates of bounding boxesif 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 / 2b1_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 = box1b1_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).clamp(eps)w2, h2 = b2_x2 - b2_x1, (b2_y2 - b2_y1).clamp(eps)# Intersection areainter = (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 Areaunion = w1 * h1 + w2 * h2 - inter + epsif scale:self = WIoU_Scale(1 - (inter / union))# IoU# iou = inter / union # ori iouiou = torch.pow(inter/(union + eps), alpha) # alpha iouif CIoU or DIoU or GIoU or EIoU or SIoU or WIoU:cw = b1_x2.maximum(b2_x2) - b1_x1.minimum(b2_x1)  # convex (smallest enclosing box) widthch = b1_y2.maximum(b2_y2) - b1_y1.minimum(b2_y1)  # convex heightif CIoU or DIoU or EIoU or SIoU or WIoU:  # Distance or Complete IoU https://arxiv.org/abs/1911.08287v1c2 = (cw ** 2 + ch ** 2) ** alpha + eps  # convex diagonal squaredrho2 = (((b2_x1 + b2_x2 - b1_x1 - b1_x2) ** 2 + (b2_y1 + b2_y2 - b1_y1 - b1_y2) ** 2) / 4) ** alpha  # center dist ** 2if CIoU:  # https://github.com/Zzh-tju/DIoU-SSD-pytorch/blob/master/utils/box/box_utils.py#L47v = (4 / math.pi ** 2) * (torch.atan(w2 / h2) - torch.atan(w1 / h1)).pow(2)with torch.no_grad():alpha_ciou = v / (v - iou + (1 + eps))if Focal:return iou - (rho2 / c2 + torch.pow(v * alpha_ciou + eps, alpha)), torch.pow(inter/(union + eps), gamma)  # Focal_CIoUelse:return iou - (rho2 / c2 + torch.pow(v * alpha_ciou + eps, alpha))  # CIoUelif EIoU:rho_w2 = ((b2_x2 - b2_x1) - (b1_x2 - b1_x1)) ** 2rho_h2 = ((b2_y2 - b2_y1) - (b1_y2 - b1_y1)) ** 2cw2 = torch.pow(cw ** 2 + eps, alpha)ch2 = torch.pow(ch ** 2 + eps, alpha)if Focal:return iou - (rho2 / c2 + rho_w2 / cw2 + rho_h2 / ch2), torch.pow(inter/(union + eps), gamma) # Focal_EIouelse:return iou - (rho2 / c2 + rho_w2 / cw2 + rho_h2 / ch2) # EIouelif SIoU:# SIoU Loss https://arxiv.org/pdf/2205.12740.pdfs_cw = (b2_x1 + b2_x2 - b1_x1 - b1_x2) * 0.5 + epss_ch = (b2_y1 + b2_y2 - b1_y1 - b1_y2) * 0.5 + epssigma = torch.pow(s_cw ** 2 + s_ch ** 2, 0.5)sin_alpha_1 = torch.abs(s_cw) / sigmasin_alpha_2 = torch.abs(s_ch) / sigmathreshold = pow(2, 0.5) / 2sin_alpha = torch.where(sin_alpha_1 > threshold, sin_alpha_2, sin_alpha_1)angle_cost = torch.cos(torch.arcsin(sin_alpha) * 2 - math.pi / 2)rho_x = (s_cw / cw) ** 2rho_y = (s_ch / ch) ** 2gamma = angle_cost - 2distance_cost = 2 - torch.exp(gamma * rho_x) - torch.exp(gamma * rho_y)omiga_w = torch.abs(w1 - w2) / torch.max(w1, w2)omiga_h = torch.abs(h1 - h2) / torch.max(h1, h2)shape_cost = torch.pow(1 - torch.exp(-1 * omiga_w), 4) + torch.pow(1 - torch.exp(-1 * omiga_h), 4)if Focal:return iou - torch.pow(0.5 * (distance_cost + shape_cost) + eps, alpha), torch.pow(inter/(union + eps), gamma) # Focal_SIouelse:return iou - torch.pow(0.5 * (distance_cost + shape_cost) + eps, alpha) # SIouelif WIoU:if Focal:raise RuntimeError("WIoU do not support Focal.")elif scale:return getattr(WIoU_Scale, '_scaled_loss')(self), (1 - iou) * torch.exp((rho2 / c2)), iou # WIoU https://arxiv.org/abs/2301.10051else:return iou, torch.exp((rho2 / c2)) # WIoU v1if Focal:return iou - rho2 / c2, torch.pow(inter/(union + eps), gamma)  # Focal_DIoUelse:return iou - rho2 / c2  # DIoUc_area = cw * ch + eps  # convex areaif Focal:return iou - torch.pow((c_area - union) / c_area + eps, alpha), torch.pow(inter/(union + eps), gamma)  # Focal_GIoU https://arxiv.org/pdf/1902.09630.pdfelse:return iou - torch.pow((c_area - union) / c_area + eps, alpha)  # GIoU https://arxiv.org/pdf/1902.09630.pdfif Focal:return iou, torch.pow(inter/(union + eps), gamma)  # Focal_IoUelse:return iou  # IoU

然后在utils/loss.py文件中调用bbox_iou损失函数时，将对应的IOU设置为True即可。 

参考文章：【深度学习小知识】目标检测中的IOU、GIOU、DIOU、CIOU、EIOU等理论解析_你好啊：）的博客-CSDN博客 深入浅出Yolo系列之Yolov3&Yolov4&Yolov5&Yolox核心基础知识完整讲解 - 知乎

详解IoU、GIoU、DIoU、CIoU、EIoU和DIoU-NMS_小Aer的博客-CSDN博客