【yolo系列:YOLOV7改进-添加EIOU,SIOU,AlphaIOU,FocalEIOU.】

yolo系列文章目录


在YoloV7中添加EIoU,SIoU,AlphaIoU,FocalEIoU,Wise-IoU.
2023-2-7 更新 yolov7添加Wise-IoUB站链接

重磅!!!!! YOLO系列模型改进损失函数

文章目录

  • yolo系列文章目录
  • 一、初始的yolov7损失函数
  • 二、首先在yolov7代码中,找到utils/general.py
  • 三、搜索ComputeLossOTA
  • 总结



一、初始的yolov7损失函数

yolov7中box_iou其默认用的是CIoU,其中代码还带有GIoU,DIoU,文件路径:utils/metrics.py,函数名为:bbox_iou
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。

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

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.

二、首先在yolov7代码中,找到utils/general.py

第344行,替换


def bbox_iou(box1, box2, x1y1x2y2=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 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
    if scale:
        self = WIoU_Scale(1 - (inter / union))

    # 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 or WIoU:
        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 or WIoU:  # 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
            elif 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/2301.10051
                else:
                    return iou, torch.exp((rho2 / c2)) # WIoU v1
            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

替换完毕,去utils/loss.py

三、搜索ComputeLossOTA

找到606行

注释lbox += (1.0 - iou).mean()  # iou loss

粘贴以下代码

#lbox += (1.0 - iou).mean()  # iou loss
                if type(iou) is tuple:
                        lbox += (iou[1].detach() * (1 - iou[0])).mean()
                        iou = iou[0]
                else:
                    lbox += (1.0 - iou).mean()  # iou loss

【yolo系列:YOLOV7改进-添加EIOU,SIOU,AlphaIOU,FocalEIOU.】_第1张图片
换iou只需要修改

 iou = bbox_iou(pbox.T, selected_tbox, x1y1x2y2=False, EIoU=True,gamma=0.5)  # iou(prediction, target)

默认data下面的hyp.scratch.p5.yaml运行,
【yolo系列:YOLOV7改进-添加EIOU,SIOU,AlphaIOU,FocalEIOU.】_第2张图片
如果修改了运行文件需要看

loss_ota: 1 # use ComputeLossOTA, use 0 for faster training

如果是1去ComputeLossOTA,否则就去ComputeLoss里面按上述修改。
【yolo系列:YOLOV7改进-添加EIOU,SIOU,AlphaIOU,FocalEIOU.】_第3张图片

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

最后希望这篇文章可以帮助到大家,当然这部分对于yolov5也是适用的,因为yolov7的架构跟yolov5是比较类似的,大家可以试着修改一下。
参考博文如下:
YOLOV5改进-添加EIoU,SIoU,AlphaIoU,FocalEIoU,Wise-IoU
YOLO系列模型改进指南

总结

Focal_EIoU思想的应用:
    Focal_EIoU思想可以用于其他IoU的变种。你可以通过将Focal参数设置为True,启用Focal_EIoU思想。在测试中,除了Focal_SIoU可能出现loss为inf的情况外,其他IoU变种均正常。不过,由于不同数据集可能产生不同结果,建议根据具体情况进行测试。

参数设置:
    gamma参数: Focal_EIoU中的gamma参数通常为0.5,你可以根据需要自行更改。
    alpha参数: AlphaIoU中的alpha参数,默认为1。设置为1时,效果与正常的IoU相同。如果想使用AlphaIoU的特性,可以将alpha设置为3。你可以根据需要选择是否启用AlphaIoU特性。

IoU变种选择:
    你可以选择任意IoU变种,并将相应的参数设置为True以启用该变种。
    如果设置了alpha为3,并且将除CIoU之外的其他IoU参数设置为False,那就是AlphaIoU。如果同时将CIoU参数设置为True,那就是AlphaCIoU。具体效果取决于数据集和模型,建议自行测试。

AlphaIoU与Focal_EIoU的组合使用:
    理论上,AlphaIoU和Focal_EIoU没有直接冲突。然而,作者没有详细测试过两者同时使用时的效果。如果你有兴趣,可以自行测试AlphaIoU和Focal_EIoU的组合效果。

请确保在实际应用中充分测试和验证这些方法,以确定最适合你的数据集和模型的配置。

你可能感兴趣的:(yolo系列,#,学习笔记,python深度学习,YOLO,bash,c++,pygame,linux)