在YoloV8中添加EIoU,SIoU,AlphaIoU,FocalEIoU,Wise-IoU.

2023-2-7 更新 yolov8添加Wise-IoUB站链接

重磅！！！！！ YOLO模型改进集合指南-CSDN

yolov8中box_iou其默认用的是CIoU，其中代码还带有GIoU，DIoU，文件路径：ultralytics/yolo/utils/metrics.py，函数名为：bbox_iou

def bbox_iou(box1, box2, xywh=True, GIoU=False, DIoU=False, CIoU=False, 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    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

我们可以看到函数顶部，有GIoU，DIoU，CIoU的bool参数可以选择，如果全部为False的时候，其会返回最普通的Iou，如果其中一个为True的时候，即返回设定为True的那个Iou。

那么重点来了，我们怎么在这个函数里面添加EIoU,SIoU,AlphaIoU,FocalEIoU呢？

我们只需要把上面提及到的这个函数替换成以下，代码出自：github链接，这个github上还有一些yolov5的改进源码和一些常用的脚本，有兴趣可以去看看，请各位也帮忙点个star支持下，谢谢！

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

注意事项

1. 我认为Focal_EIoU的思想是可以用作与其他IoU的变种，因此我对里面所有的IoU都支持Focal_EIoU的思想，只需要设定Focal参数为True即可，我自己测试的过程中，除了Focal_SIoU出现loss为inf之外，其他的都正常，不过这个不同的数据集可能出现不一样，具体可以自行测试下。
2. gamma参数是Focal_EIoU中的gamma参数，一般就是为0.5，有需要可以自行更改。
3. alpha参数为AlphaIoU中的alpha参数，默认为1,1的意思就是跟正常的IoU一样，如果想采用AlphaIoU的话，论文alpha默认值为3。(比如我不想使用AlphaIoU的特性，我就把alpha设置为1就可以，如果我想使用AlphaIoU的特性，我可以设置alpha为3)。
4. 跟Focal_EIoU一样，我认为AlphaIoU的思想同样可以用在其他的IoU变种上，简单来说就是如果你设置了alpha为3，其他IoU设定的参数(GIoU，DIoU，CIoU，EIoU，SIoU)为False的时候，那就是AlphaIoU，如果你设置了alpha为3，CIoU为True的时候，那就是AlphaCIoU，效果的话就因数据集和模型而已，具体可以自行测试下。
5. 想用那个IoU变种，就直接设置参数为True即可。
6. AlphaIoU理论上与Focal_EIoU没有直接的冲突，但是作者这边没有详细测试过，这两者一起用会是什么效果，有兴趣可以自行测试下。

除了以上这个函数替换，还需要在ultralytics/yolo/utils/loss.py中BboxLoss Class中的forward函数中修改一下：

原本的forward函数如下：

主要对红框部分替换为以下代码：

iou = bbox_iou(pred_bboxes[fg_mask], target_bboxes[fg_mask], xywh=False, CIoU=True)if type(iou) is tuple:    loss_iou = ((1.0 - iou[0]) * iou[1].detach() * weight).sum() / target_scores_sumelse:    loss_iou = ((1.0 - iou) * weight).sum() / target_scores_sum

最后修改参数就在调用bbox_iou中进行修改即可，比如上面的代码就是使用了CIoU，如果你想使用Focal_EIoU那么你可以修改为下：

iou = bbox_iou(pred_bboxes[fg_mask], target_bboxes[fg_mask], xywh=False, EIoU=True, Focal=True) 

YoloV8中在标签分配规则中也有用到bbox_iou的函数，具体在:ultralytics/yolo/utils/tal.py的TaskAlignedAssigner class中的get_box_metrics函数：

对于这个我个人修改建议就是跟你计算IoU Loss的时候选择一样即可，但是这里不需要开启Focal选项，因为这里只是单纯求交并比。意思就是你在计算IoU Loss的时候，比如选择了Focal=True和CIoU=True，那么在这里你只需要选择CIoU=True即可。

最后希望这篇文章可以帮助到大家。博文求点赞，github求star，谢谢啦！

来源地址：https://blog.csdn.net/qq_37706472/article/details/128743012