本文主要是介绍目标检测算法改进系列之添加EIOU,SIOU,AlphaIOU,FocalEIOU等，希望对大家解决编程问题提供一定的参考价值，需要的开发者们随着小编来一起学习吧！
YOLOv8添加EIoU,SIoU,AlphaIoU,FocalEIoU,Wise-IoU等
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
原始代码
def bbox_iou(box1, box2, x1y1x2y2=True, GIoU=False, DIoU=False, CIoU=False, eps=1e-7):# Returns the IoU of box1 to box2. box1 is 4, box2 is nx4box2 = box2.T# Get the coordinates of bounding boxesif x1y1x2y2: # x1, y1, x2, y2 = box1b1_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 xyxyb1_x1, b1_x2 = box1[0] - box1[2] / 2, box1[0] + box1[2] / 2b1_y1, b1_y2 = box1[1] - box1[3] / 2, box1[1] + box1[3] / 2b2_x1, b2_x2 = box2[0] - box2[2] / 2, box2[0] + box2[2] / 2b2_y1, b2_y2 = box2[1] - box2[3] / 2, box2[1] + box2[3] / 2# Intersection areainter = (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 Areaw1, h1 = b1_x2 - b1_x1, b1_y2 - b1_y1 + epsw2, h2 = b2_x2 - b2_x1, b2_y2 - b2_y1 + epsunion = w1 * h1 + w2 * h2 - inter + epsiou = inter / unionif GIoU or DIoU or CIoU:cw = torch.max(b1_x2, b2_x2) - torch.min(b1_x1, b2_x1) # convex (smallest enclosing box) widthch = torch.max(b1_y2, b2_y2) - torch.min(b1_y1, b2_y1) # convex heightif CIoU or DIoU: # Distance or Complete IoU https://arxiv.org/abs/1911.08287v1c2 = cw ** 2 + ch ** 2 + eps # convex diagonal squaredrho2 = ((b2_x1 + b2_x2 - b1_x1 - b1_x2) ** 2 +(b2_y1 + b2_y2 - b1_y1 - b1_y2) ** 2) / 4 # center distance squaredif DIoU:return iou - rho2 / c2 # DIoUelif CIoU: # https://github.com/Zzh-tju/DIoU-SSD-pytorch/blob/master/utils/box/box_utils.py#L47v = (4 / math.pi ** 2) * torch.pow(torch.atan(w2 / (h2 + eps)) - torch.atan(w1 / (h1 + eps)), 2)with torch.no_grad():alpha = v / (v - iou + (1 + eps))return iou - (rho2 / c2 + v * alpha) # CIoUelse: # GIoU https://arxiv.org/pdf/1902.09630.pdfc_area = cw * ch + eps # convex areareturn iou - (c_area - union) / c_area # GIoUelse:return iou # IoU
代码替换
只需要把上面提及到的这个函数替换成以下代码。
import numpy as np
import torch, mathclass WIoU_Scale:''' monotonous: {None: origin v1True: monotonic FM v2False: non-monotonic FM v3}momentum: The momentum of running mean'''iou_mean = 1.monotonous = False_momentum = 1 - 0.5 ** (1 / 7000)_is_train = Truedef __init__(self, iou):self.iou = iouself._update(self)@classmethoddef _update(cls, self):if cls._is_train: cls.iou_mean = (1 - cls._momentum) * cls.iou_mean + \cls._momentum * self.iou.detach().mean().item()@classmethoddef _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_meanalpha = delta * torch.pow(gamma, beta - delta)return beta / alphareturn 1def 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 boxesif 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 / 2b1_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 = box1b1_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 areainter = (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 Areaunion = w1 * h1 + w2 * h2 - inter + epsif scale:self = WIoU_Scale(1 - (inter / union))# IoU# iou = inter / union # ori iouiou = torch.pow(inter/(union + eps), alpha) # alpha iouif 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) widthch = b1_y2.maximum(b2_y2) - b1_y1.minimum(b2_y1) # convex heightif CIoU or DIoU or EIoU or SIoU or WIoU: # Distance or Complete IoU https://arxiv.org/abs/1911.08287v1c2 = (cw ** 2 + ch ** 2) ** alpha + eps # convex diagonal squaredrho2 = (((b2_x1 + b2_x2 - b1_x1 - b1_x2) ** 2 + (b2_y1 + b2_y2 - b1_y1 - b1_y2) ** 2) / 4) ** alpha # center dist ** 2if CIoU: # https://github.com/Zzh-tju/DIoU-SSD-pytorch/blob/master/utils/box/box_utils.py#L47v = (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_CIoUelse:return iou - (rho2 / c2 + torch.pow(v * alpha_ciou + eps, alpha)) # CIoUelif EIoU:rho_w2 = ((b2_x2 - b2_x1) - (b1_x2 - b1_x1)) ** 2rho_h2 = ((b2_y2 - b2_y1) - (b1_y2 - b1_y1)) ** 2cw2 = 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_EIouelse:return iou - (rho2 / c2 + rho_w2 / cw2 + rho_h2 / ch2) # EIouelif SIoU:# SIoU Loss https://arxiv.org/pdf/2205.12740.pdfs_cw = (b2_x1 + b2_x2 - b1_x1 - b1_x2) * 0.5 + epss_ch = (b2_y1 + b2_y2 - b1_y1 - b1_y2) * 0.5 + epssigma = torch.pow(s_cw ** 2 + s_ch ** 2, 0.5)sin_alpha_1 = torch.abs(s_cw) / sigmasin_alpha_2 = torch.abs(s_ch) / sigmathreshold = pow(2, 0.5) / 2sin_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) ** 2rho_y = (s_ch / ch) ** 2gamma = angle_cost - 2distance_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_SIouelse:return iou - torch.pow(0.5 * (distance_cost + shape_cost) + eps, alpha) # SIouelif 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/2301.10051else:return iou, torch.exp((rho2 / c2)) # WIoU v1if Focal:return iou - rho2 / c2, torch.pow(inter/(union + eps), gamma) # Focal_DIoUelse:return iou - rho2 / c2 # DIoUc_area = cw * ch + eps # convex areaif 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.pdfelse:return iou - torch.pow((c_area - union) / c_area + eps, alpha) # GIoU https://arxiv.org/pdf/1902.09630.pdfif Focal:return iou, torch.pow(inter/(union + eps), gamma) # Focal_IoUelse:return iou # IoU### yolov8
if type(iou) is tuple:if len(iou) == 2:loss_iou = ((1.0 - iou[0]) * iou[1].detach() * weight).sum() / target_scores_sumelse:loss_iou = (iou[0] * iou[1] * weight).sum() / target_scores_sum
else:loss_iou = ((1.0 - iou) * weight).sum() / target_scores_sum### yolov5
iou = bbox_iou(pbox, tbox[i], CIoU=True)
if type(iou) is tuple:if len(iou) == 2:lbox += (iou[1].detach().squeeze() * (1 - iou[0].squeeze())).mean()iou = iou[0].squeeze()else:lbox += (iou[0] * iou[1]).mean()iou = iou[2].squeeze()
else:lbox += (1.0 - iou.squeeze()).mean() # iou lossiou = iou.squeeze()
注意事项
1、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。
BboxLoss Class中的forward函数修改
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。
原始代码
具体修改
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可以修改为
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，具体路径为：ultralytics/yolo/utils/tal.py的TaskAlignedAssigner class中的get_box_metrics函数
对于这个，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。
这篇关于目标检测算法改进系列之添加EIOU,SIOU,AlphaIOU,FocalEIOU等的文章就介绍到这儿，希望我们推荐的文章对编程师们有所帮助！
