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 v1True: monotonic FM v2False: 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 = 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, 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 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 + 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
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 v1True: monotonic FM v2False: 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 = 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, 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 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 + 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
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 v1True: monotonic FM v2False: 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 = 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, 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 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 + 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
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!