YOLOV8改进-添加EIoU,SIoU,AlphaIoU,FocalEIoU,Wise-IoU

魔鬼面具 2024-06-26 14:05:15 阅读 99

在YoloV8中添加EIoU,SIoU,AlphaIoU,FocalEIoU,Wise-IoU.

2023-2-7 更新 yolov8添加Wise-IoUB站链接

重磅!!!!! YOLO模型改进集合指南-CSDN

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

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).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

# IoU

iou = inter / union

if CIoU or DIoU or GIoU:

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: # 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.atan(w2 / h2) - torch.atan(w1 / h1)).pow(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

我们可以看到函数顶部,有GIoU,DIoU,CIoU的bool参数可以选择,如果全部为False的时候,其会返回最普通的Iou,如果其中一个为True的时候,即返回设定为True的那个Iou。

那么重点来了,我们怎么在这个函数里面添加EIoU,SIoU,AlphaIoU,FocalEIoU呢?

我们只需要把上面提及到的这个函数替换成以下,代码出自:github链接,这个github上还有一些yolov5的改进源码和一些常用的脚本,有兴趣可以去看看,请各位也帮忙点个star支持下,谢谢!

def bbox_iou(box1, box2, xywh=True, GIoU=False, DIoU=False, CIoU=False, SIoU=False, EIoU=False, Focal=False, alpha=1, gamma=0.5, 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

# 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:

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: # 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

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

注意事项

我认为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。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。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)。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。想用那个IoU变种,就直接设置参数为True即可。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。

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:

原本的forward函数如下:

在这里插入图片描述

主要对红框部分替换为以下代码:

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那么你可以修改为下:

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,具体在:ultralytics/yolo/utils/tal.py的TaskAlignedAssigner class中的get_box_metrics函数:

在这里插入图片描述

对于这个我个人修改建议就是跟你计算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。

最后希望这篇文章可以帮助到大家。博文求点赞,github求star,谢谢啦!



声明

本文内容仅代表作者观点,或转载于其他网站,本站不以此文作为商业用途
如有涉及侵权,请联系本站进行删除
转载本站原创文章,请注明来源及作者。