文章目录
1、前言
YOLOv5默认使用损失函数为CIoU，本文主要针对损失函数进行修改，主要将bbox_iou函数进行修改，添加 EIoU、Alpha-IoU、SIoU、Focal-IOU等边界框回归损失。
2、损失函数代码实现
2.1、修改metrics.py
（1）首先找到utils/metrics.py文件，然后找到该python文件下的bbox_iou函数，其实在yolov5源码中设置是有GIoU, DIoU, CIoU 这些边界框iou损失，但是默认值都为False。
（2）将原始的bbox_iou函数代码注释掉，替换成如下代码，这段代码是将EIoU、Alpha-IoU、SIoU、Focal-EIOU这几个功能集中在一起，如果想要使用不同的Iou计算边界框损失，只需要修改utils/loss.py下的iou方法即可。
python
# 优化后的代码
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要点
gamma参数：是Focal EloU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Alpha-IOU中的alpha参数，默认为1，即使用原始I0U。若需要使用Alpha-IOU，只需将其设置为任意值(论文中默认设置为3)
2.2、修改loss.py
找到utils/loss.py损失函数计算文件，修改ComputeLoss类下面的__call__函数，通过修改iou = bbox_iou(pbox, tbox[i],x1y1x2y2=False, CIoU=True)里面第4个参数实现不同的损失函数。
将红框内容替换成如下代码：
python
iou = bbox_iou(pbox, tbox[i], CIoU=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()
3、替换EIOU
如果想要使用EIOU，只需要将CIoU替换成EIOU:
python
iou = bbox_iou(pbox, tbox[i], EIoU=True) 4、替换SIoU
如果想要使用SIoU，只需要将CIoU替换成SIoU：
python
iou = bbox_iou(pbox, tbox[i], SIoU=True) 5、替换Alpha-IoU
如果想要使用Alpha-IoU，只需要添加alpha=3这个参数项开启Alpha，如果不设置该参数，alpha默认为1:
python
iou = bbox_iou(pbox, tbox[i], CIoU=True, alpha=3) 6、替换Focal-EIOU
Focal-EIOU相对于EIOU只多了一个Focal项，这两个iou损失都是出自同一篇论文，只需要设置Focal=True即可。
python
iou = bbox_iou(pbox, tbox[i], EIoU=True, Focal=True) 当然Focal项也可以用于CIoU、SIoU，至于效果需要根据不同数据集进行测试，修改如下:
Focal-CIoU
python
iou = bbox_iou(pbox, tbox[i], CIOU=True, Focal=True) Focal-SIoU
python
iou = bbox_iou(pbox, tbox[i], SIOU=True, Focal=True) 7、目标检测系列文章
- YOLOv5s网络模型讲解(一看就会)
- 生活垃圾数据集（YOLO版）
- YOLOv5如何训练自己的数据集
- 双向控制舵机（树莓派版）
- 树莓派部署YOLOv5目标检测（详细篇）
- YOLO_Tracking 实践 （环境搭建 & 案例测试）
- 目标检测：数据集划分 & XML数据集转YOLO标签
- DeepSort行人车辆识别系统（实现目标检测+跟踪+统计）
- YOLOv5参数大全(parse_opt篇)
- YOLOv5改进（一）-- 轻量化YOLOv5s模型
- YOLOv5改进（二）-- 目标检测优化点（添加小目标头检测）
- YOLOv5改进（三）-- 引进Focaler-IoU损失函数
- YOLOv5改进（四）--轻量化模型ShuffleNetv2
- YOLOv5改进（五）-- 轻量化模型MobileNetv3
- YOLOv5改进（六）--引入YOLOv8中C2F模块