【yolo系列：yolov7改进wise-iou】

yolo系列文章目录

学习视频：
YOLOV7改进-Wise IoU_哔哩哔哩_bilibili

代码地址：
objectdetection_script/yolov7-iou.py at master · z1069614715/objectdetection_script (github.com)

文章目录

yolo系列文章目录
一、在yolov7之上进行替换
二、在loss.py的ComputeLoss，ComputeLossOTA修改如下
三、设置版本
总结

一、在yolov7之上进行替换

utils/general.py替换bbiox

class 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 Exception("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

二、在loss.py的ComputeLoss，ComputeLossOTA修改如下

在这里插入图片描述

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.squeeze()).mean()  # iou loss