【YOLOv5/v7改进系列】替换损失函数为WIOU、CIOU、GIOU、SIOU、DIOU、EIOU、Focal C/G/S/D/EIOU等

已于 2024-07-02 01:41:54 修改
阅读量1.2k 收藏 17
点赞数 29
分类专栏： YOLO改进指南 文章标签： YOLO 开发语言 机器学习 目标检测 计算机视觉 深度学习 pytorch
于 2024-07-01 18:21:25 首次发布
版权声明：本文为博主原创文章，遵循 CC 4.0 BY-SA 版权协议，转载请附上原文出处链接和本声明。
本文链接：https://blog.csdn.net/2401_84870184/article/details/138824720
版权
一、导言

在目标检测任务中，损失函数的主要作用是衡量模型预测的边界框（bounding boxes）与真实边界框之间的匹配程度，并指导模型学习如何更精确地定位和分类目标。损失函数通常由两部分构成：分类损失（用于判断物体属于哪个类别）和回归损失（用于调整预测边界框的位置和尺寸以更好地匹配真实目标）。一个好的损失函数能够帮助模型快速且准确地收敛，提高检测性能。

二、YOLO训练中常见且有效的损失函数
1.SIOU (Sum of Intersection over Union)

SIOU不是一个广泛认可的术语，但若假设这是对某种综合IoU概念的提及，其潜在的优点可能在于尝试结合不同IoU变体的优势，比如同时考虑重叠区域、最小外包矩形、中心点距离等，以提供一个更全面的评估标准，可能在某些特定场景下提升检测精度。

2.EIOU (Enhanced Intersection over Union)

EIOU是对IOU的一个增强版本，旨在进一步提升回归损失的效果。它可能通过额外考虑边界框尺寸、形状或位置关系的度量，以更精细地引导边界框的调整。EIOU的优点在于它能更有效地处理极端情况，如极度倾斜或部分重叠的目标，从而提高检测的鲁棒性和准确性。

3.DIOU (Distance Intersection over Union)

DIOU在传统IOU的基础上，加入了两个边界框中心点之间的欧几里得距离，这有助于直接最小化预测框与真实框之间的距离，加快了收敛速度并改善了对密集对象和极端长宽比目标的检测效果。其优点包括减少重叠区域之外的定位误差，尤其在处理重叠少或无重叠情况时更为有效。

4.GIOU (Generalized Intersection over Union)

GIOU解决了IOU无法惩罚预测框未能完全覆盖真实框的问题，通过计算预测框与真实框的最小外包矩形与它们交集的比值，促使预测框不仅尽可能重叠，而且形状和大小也要更加接近真实框。GIOU的优点在于能有效引导框的扩展，尤其是在目标被严重遮挡或仅部分可见时，提升检测的完整性。

5.CIOU (Complete Intersection over Union)

CIOU在GIOU的基础上，进一步加入了边界框中心点距离的惩罚项以及对宽高比的约束，形成了一个更为全面的损失函数。它不仅优化了重叠区域的测量，还解决了边界框尺寸不一致的问题，从而在各种复杂场景下都能提供稳定的性能提升。CIOU的优点在于它是目前较为全面的回归损失函数，能够综合考虑重叠、中心点距离和宽高比，提高了检测的准确性和效率。

这些改进的IoU损失函数都是为了克服传统IOU作为损失函数时存在的局限性，如只关注重叠区域而不考虑位置偏差或形状不匹配的问题，通过不断地优化，这些新提出的损失函数使得目标检测系统的性能得到了显著提升。

三、YOLOv7-tiny改进工作

了解二后，打开YOLOv7项目文件下的utils文件夹下的general.py，搜索def bbox_iou定位到如下行，

替换如下代码为

class WIoU_Scale:
    ''' monotonous: {
            None: origin v1
            True: monotonic FM v2
            False: non-monotonic FM v3
        }
        momentum: The momentum of running mean'''

    iou_mean = 1.
    monotonous = False  # (false为v3，true为v2，none为v1)
    _momentum = 1 - 0.5 ** (1 / 7000)
    _is_train = True

    def __init__(self, iou):
        self.iou = iou
        self._update(self)

    @classmethod
    def _update(cls, self):
        if cls._is_train: cls.iou_mean = (1 - cls._momentum) * cls.iou_mean + \
                                         cls._momentum * self.iou.detach().mean().item()

    @classmethod
    def _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_mean
                alpha = delta * torch.pow(gamma, beta - delta)
                return beta / alpha
        return 1


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

打开utils文件夹下的loss.py，搜索class ComputeLossOTA定位到如下行：

替换ComputeLossOTA下的该两行为如下代码

                iou = bbox_iou(pbox.T, selected_tbox, x1y1x2y2=False, CIoU=True)  # iou(prediction, target)
                #iou = bbox_iou(pbox.T, selected_tbox, x1y1x2y2=False, WIoU=True, scale=True)  # iou(prediction, target)
                #iou = bbox_iou(pbox.T, selected_tbox, x1y1x2y2=False, GIoU=True)  # iou(prediction, target)
                #iou = bbox_iou(pbox.T, selected_tbox, x1y1x2y2=False, SIoU=True)  # iou(prediction, target)
                #iou = bbox_iou(pbox.T, selected_tbox, x1y1x2y2=False, DIoU=True)  # iou(prediction, target)
                #iou = bbox_iou(pbox.T, selected_tbox, x1y1x2y2=False, EIoU=True)  # iou(prediction, target)
                #iou = bbox_iou(pbox.T, selected_tbox, x1y1x2y2=False, CIoU=True, Focal=True)
                #iou = bbox_iou(pbox.T, selected_tbox, x1y1x2y2=False, SIoU=True, Focal=True)
                #iou = bbox_iou(pbox.T, selected_tbox, x1y1x2y2=False, DIoU=True, Focal=True)
                #iou = bbox_iou(pbox.T, selected_tbox, x1y1x2y2=False, EIoU=True, Focal=True)
                #iou = bbox_iou(pbox.T, selected_tbox, x1y1x2y2=False, GIoU=True, Focal=True)
                if type(iou) is tuple:
                    if len(iou) == 2:
                        lbox += (iou[1].detach() * (1 - iou[0])).mean()
                        iou = iou[0]
                    else:
                        lbox += (iou[0] * iou[1]).mean()
                        iou = iou[-1]
                else:
                    lbox += (1.0 - iou).mean()  # iou loss

使用时，取消掉不要的注释即可（如base是CIOU，你想使用SIOU，注释掉CIOU这行，SIOU那行取消注释即可）。

四、YOLOv7改进工作

 了解二后，打开YOLOv7项目文件下的utils文件夹下的general.py，搜索def bbox_iou定位到如下行，

替换如下代码为

class WIoU_Scale:
    ''' monotonous: {
            None: origin v1
            True: monotonic FM v2
            False: non-monotonic FM v3
        }
        momentum: The momentum of running mean'''

    iou_mean = 1.
    monotonous = False  # (false为v3，true为v2，none为v1)
    _momentum = 1 - 0.5 ** (1 / 7000)
    _is_train = True

    def __init__(self, iou):
        self.iou = iou
        self._update(self)

    @classmethod
    def _update(cls, self):
        if cls._is_train: cls.iou_mean = (1 - cls._momentum) * cls.iou_mean + \
                                         cls._momentum * self.iou.detach().mean().item()

    @classmethod
    def _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_mean
                alpha = delta * torch.pow(gamma, beta - delta)
                return beta / alpha
        return 1


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

打开utils文件夹下的loss.py，搜索class ComputeLoss:定位到如下行：

 

替换该两行为如下代码

                iou = bbox_iou(pbox.T, tbox[i], x1y1x2y2=False, CIoU=True)  # iou(prediction, target)
                #iou = bbox_iou(pbox.T, tbox[i], x1y1x2y2=False, WIoU=True, scale=True)  # iou(prediction, target)
                #iou = bbox_iou(pbox.T, tbox[i], x1y1x2y2=False, GIoU=True)  # iou(prediction, target)
                #iou = bbox_iou(pbox.T, tbox[i], x1y1x2y2=False, SIoU=True)  # iou(prediction, target)
                #iou = bbox_iou(pbox.T, tbox[i], x1y1x2y2=False, DIoU=True)  # iou(prediction, target)
                #iou = bbox_iou(pbox.T, tbox[i], x1y1x2y2=False, EIoU=True)  # iou(prediction, target)
                #iou = bbox_iou(pbox.T, tbox[i], x1y1x2y2=False, CIoU=True, Focal=True)
                #iou = bbox_iou(pbox.T, tbox[i], x1y1x2y2=False, SIoU=True, Focal=True)
                #iou = bbox_iou(pbox.T, tbox[i], x1y1x2y2=False, DIoU=True, Focal=True)
                #iou = bbox_iou(pbox.T, tbox[i], x1y1x2y2=False, EIoU=True, Focal=True)
                #iou = bbox_iou(pbox.T, tbox[i], x1y1x2y2=False, GIoU=True, Focal=True)
                if type(iou) is tuple:
                    if len(iou) == 2:
                        lbox += (iou[1].detach() * (1 - iou[0])).mean()
                        iou = iou[0]
                    else:
                        lbox += (iou[0] * iou[1]).mean()
                        iou = iou[-1]
                else:
                    lbox += (1.0 - iou).mean()  # iou loss

使用时，取消掉不要的注释即可（如base是CIOU，你想使用SIOU，注释掉CIOU这行，SIOU那行取消注释即可）。

五、YOLOv5改进工作

了解二后，打开YOLOv5项目文件下的utils文件夹下的metrics.py，搜索def bbox_iou定位到如下行，

将该函数替换为如下代码

class WIoU_Scale:
    ''' monotonous: {
            None: origin v1
            True: monotonic FM v2
            False: non-monotonic FM v3
        }
        momentum: The momentum of running mean'''

    iou_mean = 1.
    monotonous = False  # (false为v3，true为v2，none为v1)
    _momentum = 1 - 0.5 ** (1 / 7000)
    _is_train = True

    def __init__(self, iou):
        self.iou = iou
        self._update(self)

    @classmethod
    def _update(cls, self):
        if cls._is_train: cls.iou_mean = (1 - cls._momentum) * cls.iou_mean + \
                                         cls._momentum * self.iou.detach().mean().item()

    @classmethod
    def _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_mean
                alpha = delta * torch.pow(gamma, beta - delta)
                return beta / alpha
        return 1


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

打开utils文件夹下的loss.py，搜索ciou

替换该两行为

                iou = bbox_iou(pbox.T, tbox[i], x1y1x2y2=False, CIoU=True)  # iou(prediction, target)
                #iou = bbox_iou(pbox.T, tbox[i], x1y1x2y2=False, WIoU=True, scale=True)  # iou(prediction, target)
                #iou = bbox_iou(pbox.T, tbox[i], x1y1x2y2=False, GIoU=True)  # iou(prediction, target)
                #iou = bbox_iou(pbox.T, tbox[i], x1y1x2y2=False, SIoU=True)  # iou(prediction, target)
                #iou = bbox_iou(pbox.T, tbox[i], x1y1x2y2=False, DIoU=True)  # iou(prediction, target)
                #iou = bbox_iou(pbox.T, tbox[i], x1y1x2y2=False, EIoU=True)  # iou(prediction, target)
                #iou = bbox_iou(pbox.T, tbox[i], x1y1x2y2=False, CIoU=True, Focal=True)
                #iou = bbox_iou(pbox.T, tbox[i], x1y1x2y2=False, SIoU=True, Focal=True)
                #iou = bbox_iou(pbox.T, tbox[i], x1y1x2y2=False, DIoU=True, Focal=True)
                #iou = bbox_iou(pbox.T, tbox[i], x1y1x2y2=False, EIoU=True, Focal=True)
                #iou = bbox_iou(pbox.T, tbox[i], x1y1x2y2=False, GIoU=True, Focal=True)
                if type(iou) is tuple:
                    if len(iou) == 2:
                        lbox += (iou[1].detach() * (1 - iou[0])).mean()
                        iou = iou[0]
                    else:
                        lbox += (iou[0] * iou[1]).mean()
                        iou = iou[-1]
                else:
                    lbox += (1.0 - iou).mean()  # iou loss

使用时，取消掉不要的注释即可（如base是CIOU，你想使用SIOU，注释掉CIOU这行，SIOU那行取消注释即可）。

六、一些注意的点

采用WIOU进行训练时，默认采用的是WIOUv3

想要训练WIOUv1、v2时将该行改为none、true即可。

更多文章产出中，主打简洁和准确，欢迎关注我，共同探讨！

拿下Nahida
关注
  • 29
    点赞
  • 踩
  • 17
    收藏
    觉得还不错? 一键收藏
  • 0
    评论
专栏目录
YOLOv8 损失函数探索：CIoU / DIoU / EIoU / GIoU / SIoU / WIoU / Focal_xIoU 汇总解析
一直在水些技术小文
11-08 1897
YOLOv8是一种先进的目标检测模型，以其出色的性能和速度而闻名。在YOLOv8中，损失函数的选择对于模型的训练和检测性能至关重要。本文将深入探讨YOLOv8中可供选择的多种损失函数，包括CIoU、DIoU、EIoU、GIoU、SIoU、WIoU和Focal_xIoU。通过详细分析这些损失函数的原理、特点和实际应用，希望能帮助读者更好地理解和选择适合其任务的损失函数。
损失函数篇 | YOLOv8更换损失函数之CIoU / DIoU / EIoU / GIoU / SIoU / WIoU
突然好想你
03-23 1886
IoU（Intersection over Union）系列损失函数是用于目标检测和语义分割任务中的一种常用损失函数，本节课作者就教大家如何进行该系列损失函数的更换！~🌈
YoloV8改进策略：将CIoU替换成Wise-IoU，幸福涨点，值得拥有，还支持EIoU、GIoU、DIoU、SIoU无缝替换
08-04
YoloV8改进策略：将CIoU替换成Wise-IoU，幸福涨点，值得拥有，还支持EIoU、GIoU、DIoU、SIoU无缝替换
损失函数：IoU、GIoU、DIoU、CIoU、EIoU、alpha IoU、SIoU、WIoU超详细精讲及Pytorch实现
热门推荐
路人贾的博客
06-20 2万+
一文带你了解IoU、GIoU、DIoU、CIoU、EIoU、alpha IoU、SIoU、WIoU。超级详细的解读，包含代码实现，适合小白！
L1 LOSS -- EIoU loss 一览 .pdf
02-03
L1 LOSS -- EIoU loss
目标检测常用IOU总结
03-25
本文将深入探讨几种常用的边界框回归损失函数，包括IOU（Intersection over Union）、GIoU（Generalized Intersection over Union）、DIoU（Distance Intersection over Union）以及CIoU（Complete IoU）。...
基于改进 YOLOv8 模型的轻量化板栗果实识别方法
07-05
强多尺度特征融合性能，最后，更改边界框损失函数为动态非单调聚焦机制 WIoU（wise intersection over union， WIoU），提高模型收敛速度，进一步提升模型检测性能。试验结果表明，改进 YOLOv8-PBi 模型准确率、...
YOLOV3翻译
smilejfy的博客
07-15 524
我们对 YOLO 进行了一些更新！我们在设计上做了一些小改动，使它变得更好。我们还训练了一个新的网络，它非常强大。在模型上，它比上次的大了一点，但更准确了，不过速度还是很快，不用担心。在 320×320 时，YOLOv3 以 28.2 mAP 在 22 毫秒内运行，与 SSD 一样精确，但速度快三倍。当我们使用旧的 0.5 IOU mAP 检测指标时，YOLOv3 的表现相当不错。
YOLOv1翻译（You Only Look Once: Unified, Real-Time Object Detection）
smilejfy的博客
07-12 701
我们发表了 YOLO，一种新的目标检测方法。先前关于目标检测的工作重新利用分类器来执行检测。取而代之的是，我们将目标检测构建成一个回归问题，该回归问题指向空间上分离的边界框和相关的类概率。单个神经网络可在一次评估中直接从完整图像预测边界框和类别概率。由于整个检测pipeline是单一网络，因此可以直接在检测性能上进行端到端的优化。我们的统一架构在执行上速度极快。我们的base YOLO 模型以45 帧/秒的速度实时处理图像。
YOLOv8改进 | 检测头 | 融合渐进特征金字塔的检测头【AFPN3】
kay_545
07-15 824
yolov8改进，yolov8，AFPN检测头
Yolov8网络结构学习
最新发布
Linxiaojiejieya的博客
07-17 677
首先，使用1x1卷积核将输入通道数减少到原来的1/2，以减少计算量和内存消耗。yolov5中的C3模块在yolov8中被替换为了C2f，C2f则采用了yolov7中ELAN 多层堆叠的结构，增加了更多类似resnet残差块中的跳跃连接,丰富了模型的梯度流。在C2f模块中用到的DarknetBottleneck模块，使用多个3x3卷积核进行卷积操作，提取特征信息，同时其具有add是否进行残差链接的选项。与yolov5一样，每个卷积层的模块都采用步长为2的卷积核进行降采样操作，减少特征图的尺寸同时增加通道数。
【Yolov8】1、anaconda下载安装创建独立环境
ladymorgana的博客
07-17 339
当我们做其他项目的时候，也应该新建独立环境安装，这样就不容易起冲突导致环境无法使用，是选择y/n时默认选择yes。解读：（下面参数可以修改）推荐安装在非C盘区域。
yolo格式数据集之狗类120种数据集已划分好|可以直接使用|yolov5|v6|v7|v8|v9|v10通用
qq_15060477的博客
07-14 209
yolo格式数据集之狗类120种数据集已划分好|可以直接使用|yolov5|v6|v7|v8|v9|v10通用。总共有:19983张。训练集：16001张。
WSL-Ubuntu20.04环境使用YOLOv8 TensorRT推理加速
ice
07-15 353
在阅读本章内容之前，需要把部署环境以及训练环境都安装好。
YOLOv5分类任务——手势识别
Winkyyyyyy的博客
07-15 1081
使用YOLOv5的分类功能实现手势识别
YOLOV5的输出[1,25200,85]如何理解和解析
chenyuan1111的博客
07-17 166
1、25200代表着检测框的数量，比如我们取出第一个检测框a，也就是[1,1，85]，取出来之后我们解析85，前五个为box的中点坐标、长宽值以及置信，后面80我们取Max（80个类别）中最大值，类别的处于多少行对应于label class.txt别中的类是哪一类别。
YOLOv8白皮书-第Y7周：训练自己的数据集
lihuhelihu的博客
07-15 870
ImageSets文件夹下面有个Main子文件夹，其下面存放了train.txt、val.txt、test.txt 和 trainval.txt 四个文件，它们是通过split_train val.py 文件来生成的.在YOLOv8中，需要自己创建train.py文件，训练默认参数保存在 default.yaml 文件中，关键参数是可以在训练命令行 /train.py 文件中进行修改。运行voc_label.py文件生成 train.txt、test.txt、val.txt 文件，先看看要生成的文件位置。
YOLOv8-OBB训练时报错：ValueError: not enough values to unpack (expected 3, got 0)
qq_65356682的博客
07-15 283
X-AnyLabeling标注软件安装及使用dota数据集，voc数据集，coco数据集。以及报错No module named‘anylabeling‘的解决_x-anylabeling标注的多变形标签yolov8为什么使用不了-CSDN博客。如果你是用X-anylabeling 标注的生成的dota数据集的话，那么是因为你配置的问题。yolov8-obb训练自己的数据集（标注，训练，推理，转化模型）-CSDN博客。obb是一种旋转框的检测这种报错是因为数据集的问题。请严格按照如下流程进行数据集的配置。
yolov8ciou改为wiou
09-18
YoloV8改进后的策略是将CIoU替换成Wise-IoU，这个改进使得YoloV8在准确度方面有所提升。除了Wise-IoU，YoloV8还支持EIoU、GIoU、DIoU、SIoU的无缝替换，这些都是不同的IoU改进算法。通过替换bbox_iou函数中的参数，你可以将yolov8ciou改为wiou，即将CIoU替换为Wise-IoU。

“相关推荐”对你有帮助么？

  • 非常没帮助
  • 没帮助
  • 一般
  • 有帮助
  • 非常有帮助
提交
评论
添加红包

请填写红包祝福语或标题

个

红包个数最小为10个

元

红包金额最低5元

当前余额3.43元 前往充值 >
需支付：10.00元
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付元
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明：

1.余额是钱包充值的虚拟货币，按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载，可以购买VIP、付费专栏及课程。

余额充值