YOLOv5改进实战 | 更换损失函数（二）之WIOU（Wise IoU）篇

---

---

前言

本文使用的YOLOv5版本为v7.0，该版本为YOLOv5最新版本，默认损失函数采用的是CIoU。若对损失函数IOU、GIOU、DIOU等并不熟悉的同学，可移步：IOU系列：IOU、GIOU、DIOU、CIOU、SIOU、Alpha-IoU、WIOU详解

---

YOLOv5改进损失函数系列：

YOLOv5改进实战（1）| 更换损失函数（一）之EIoU、Alpha-IoU、SIoU篇
YOLOv5改进实战（2）| 更换损失函数（二）之WIOU（Wise IoU）篇
YOLOv5改进实战（3）| 更换损失函数（三）之MPDIOU（2023最新IOU）篇
YOLOv5改进实战（6）| 更换损失函数（四）之NWD（小目标检测）篇

---

一、⭐ 添加损失函数

1. 更换损失函数主要修改metrics.py文件中的bbox_iou函数
   • 源代码如下：

     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 + eps
            w2, h2 = b2_x2 - b2_x1, b2_y2 - b2_y1 + eps
     
        # 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
        union = w1 * h1 + w2 * h2 - inter + eps
     
        # IoU
        iou = inter / union
        if CIoU or DIoU or GIoU:
            cw = torch.max(b1_x2, b2_x2) - torch.min(b1_x1, b2_x1)  # convex (smallest enclosing box) width
            ch = torch.max(b1_y2, b2_y2) - torch.min(b1_y1, 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.pow(torch.atan(w2 / h2) - torch.atan(w1 / h1), 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
     

   • 替换成以下代码：

     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
         _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, xywh=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 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
         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
     

二、WIOU

WIOU 损失函数相关代码可查看wiou

• 在utils/loss.py中，找到ComputeLoss类中的__call__()函数
  
  ⭐将红框部分替换为以下代码：

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

• WIOU有三个版本，分别是v1 v2 v3，默认使用的是v3版本，可通过更改WIoU_Scale类中的monotonous参数，None表示v1版本，True表示v2版本，False表示v3版本。