YOLOv5改进（七）--改进损失函数EIoU、Alpha-IoU、SIoU、Focal-EIOU

1、前言

YOLOv5默认使用损失函数为CIoU，本文主要针对损失函数进行修改，主要将bbox_iou函数进行修改，添加 EIoU、Alpha-IoU、SIoU、Focal-IOU等边界框回归损失。

2、损失函数代码实现

2.1、修改metrics.py

（1）首先找到utils/metrics.py文件，然后找到该python文件下的bbox_iou函数，其实在yolov5源码中设置是有GIoU, DIoU, CIoU这些边界框iou损失，但是默认值都为False。

（2）将原始的bbox_iou函数代码注释掉，替换成如下代码，这段代码是将EIoU、Alpha-IoU、SIoU、Focal-EIOU这几个功能集中在一起，如果想要使用不同的Iou计算边界框损失，只需要修改utils/loss.py下的iou方法即可。

# 优化后的代码
def bbox_iou(box1, box2, xywh=True, GIoU=False, DIoU=False, CIoU=False, SIoU=False, EIoU=False, Focal=False, alpha=1,
             gamma=0.5, eps=1e-7):
    # Returns Intersection over Union (IoU) of box1(1,4) to box2(n,4)

    # 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).clamp(eps)
        w2, h2 = b2_x2 - b2_x1, (b2_y2 - b2_y1).clamp(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 # ori iou
    iou = torch.pow(inter / (union + eps), alpha)  # alpha iou
    if CIoU or DIoU or GIoU or EIoU or SIoU:
        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 or EIoU or SIoU:  # Distance or Complete IoU https://arxiv.org/abs/1911.08287v1
            c2 = (cw ** 2 + ch ** 2) ** alpha + eps  # convex diagonal squared
            rho2 = (((b2_x1 + b2_x2 - b1_x1 - b1_x2) ** 2 + (
                        b2_y1 + b2_y2 - b1_y1 - b1_y2) ** 2) / 4) ** alpha  # 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_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_CIoU
                else:
                    return iou - (rho2 / c2 + torch.pow(v * alpha_ciou + eps, alpha))  # CIoU
            elif EIoU:
                rho_w2 = ((b2_x2 - b2_x1) - (b1_x2 - b1_x1)) ** 2
                rho_h2 = ((b2_y2 - b2_y1) - (b1_y2 - b1_y1)) ** 2
                cw2 = 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_EIou
                else:
                    return iou - (rho2 / c2 + rho_w2 / cw2 + rho_h2 / ch2)  # EIou
            elif SIoU:
                # SIoU Loss https://arxiv.org/pdf/2205.12740.pdf
                s_cw = (b2_x1 + b2_x2 - b1_x1 - b1_x2) * 0.5 + eps
                s_ch = (b2_y1 + b2_y2 - b1_y1 - b1_y2) * 0.5 + eps
                sigma = torch.pow(s_cw ** 2 + s_ch ** 2, 0.5)
                sin_alpha_1 = torch.abs(s_cw) / sigma
                sin_alpha_2 = torch.abs(s_ch) / sigma
                threshold = pow(2, 0.5) / 2
                sin_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) ** 2
                rho_y = (s_ch / ch) ** 2
                gamma = angle_cost - 2
                distance_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_SIou
                else:
                    return iou - torch.pow(0.5 * (distance_cost + shape_cost) + eps, alpha)  # SIou
            if Focal:
                return iou - rho2 / c2, torch.pow(inter / (union + eps), gamma)  # Focal_DIoU
            else:
                return iou - rho2 / c2  # DIoU
        c_area = cw * ch + eps  # convex area
        if 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.pdf
        else:
            return iou - torch.pow((c_area - union) / c_area + eps, alpha)  # GIoU https://arxiv.org/pdf/1902.09630.pdf
    if Focal:
        return iou, torch.pow(inter / (union + eps), gamma)  # Focal_IoU
    else:
        return iou  # IoU

要点

1. gamma参数： 是Focal EloU中的gamma参数，一般就是为0.5，有需要可以自行更改。
2. alpha参数：为Alpha-IOU中的alpha参数，默认为1，即使用原始I0U。若需要使用Alpha-IOU，只需将其设置为任意值(论文中默认设置为3)

2.2、修改loss.py

找到utils/loss.py损失函数计算文件，修改ComputeLoss类下面的__call__函数，通过修改iou = bbox_iou(pbox, tbox[i],x1y1x2y2=False, CIoU=True)里面第4个参数实现不同的损失函数。

将红框内容替换成如下代码：

iou = bbox_iou(pbox, tbox[i], CIoU=True)  # iou(prediction, target)
if type(iou) is tuple:
    lbox += (iou[1].detach().squeeze() * (1 - iou[0].squeeze())).mean()
    iou = iou[0].squeeze()
else:
    lbox += (1.0 - iou.squeeze()).mean()  # iou loss
    iou = iou.squeeze()

3、替换EIOU

如果想要使用EIOU，只需要将CIoU替换成EIOU:

iou = bbox_iou(pbox, tbox[i], EIoU=True) 

4、替换SIoU

如果想要使用SIoU，只需要将CIoU替换成SIoU：

iou = bbox_iou(pbox, tbox[i], SIoU=True) 

5、替换Alpha-IoU

如果想要使用Alpha-IoU，只需要添加alpha=3这个参数项开启Alpha，如果不设置该参数，alpha默认为1:

iou = bbox_iou(pbox, tbox[i], CIoU=True, alpha=3) 

6、替换Focal-EIOU

Focal-EIOU相对于EIOU只多了一个Focal项，这两个iou损失都是出自同一篇论文，只需要设置Focal=True即可。

iou = bbox_iou(pbox, tbox[i], EIoU=True, Focal=True) 

当然Focal项也可以用于CIoU、SIoU，至于效果需要根据不同数据集进行测试，修改如下:

Focal-CIoU

iou = bbox_iou(pbox, tbox[i], CIOU=True, Focal=True) 

Focal-SIoU

iou = bbox_iou(pbox, tbox[i], SIOU=True, Focal=True) 

7、目标检测系列文章

1. YOLOv5s网络模型讲解(一看就会)
2. 生活垃圾数据集（YOLO版）
3. YOLOv5如何训练自己的数据集
4. 双向控制舵机（树莓派版）
5. 树莓派部署YOLOv5目标检测（详细篇）
6. YOLO_Tracking 实践 （环境搭建 & 案例测试）
7. 目标检测：数据集划分 & XML数据集转YOLO标签
8. DeepSort行人车辆识别系统（实现目标检测+跟踪+统计）
9. YOLOv5参数大全(parse_opt篇)
10. YOLOv5改进（一）-- 轻量化YOLOv5s模型
11. YOLOv5改进（二）-- 目标检测优化点（添加小目标头检测）
12. YOLOv5改进（三）-- 引进Focaler-IoU损失函数
13. YOLOv5改进（四）–轻量化模型ShuffleNetv2
14. YOLOv5改进（五）-- 轻量化模型MobileNetv3
15. YOLOv5改进（六）–引入YOLOv8中C2F模块