本文介绍: 手把手教你在YoloV8中添加EIoU,SIoU,AlphaIoU,FocalEIoU,Wise-IoU.

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,我自己测试过程中,除了Focal_SIoU出现lossinf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ultralytics/yolo/utils/loss.py中BboxLoss Class中的forward函数修改一下:

原本的forward函数如下
在这里插入图片描述

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_sum
else:
    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

在这里插入图片描述
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,githubstar,谢谢啦!

原文地址:https://blog.csdn.net/qq_37706472/article/details/128743012

本文来自互联网用户投稿,该文观点仅代表作者本人,不代表本站立场。本站仅提供信息存储空间服务,不拥有所有权,不承担相关法律责任

如若转载,请注明出处:http://www.7code.cn/show_19079.html

如若内容造成侵权/违法违规/事实不符,请联系代码007邮箱suwngjj01@126.com进行投诉反馈,一经查实,立即删除

发表回复

您的邮箱地址不会被公开。 必填项已用 * 标注