一、加入CBAM注意力机制
1、在common.py中添加可调用的CBAM模块
1)打开models文件夹中的common.py文件
2)将下面的CBAMC3代码复制粘贴到common.py文件中
class ChannelAttention(nn.Module):
def __init__(self, in_planes, ratio=16):
super(ChannelAttention, self).__init__()
self.avg_pool = nn.AdaptiveAvgPool2d(1)
self.max_pool = nn.AdaptiveMaxPool2d(1)
self.f1 = nn.Conv2d(in_planes, in_planes // ratio, 1, bias=False)
self.relu = nn.ReLU()
self.f2 = nn.Conv2d(in_planes // ratio, in_planes, 1, bias=False)
# 写法二,亦可使用顺序容器
# self.sharedMLP = nn.Sequential(
# nn.Conv2d(in_planes, in_planes // ratio, 1, bias=False), nn.ReLU(),
# nn.Conv2d(in_planes // rotio, in_planes, 1, bias=False))
self.sigmoid = nn.Sigmoid()
def forward(self, x):
avg_out = self.f2(self.relu(self.f1(self.avg_pool(x))))
max_out = self.f2(self.relu(self.f1(self.max_pool(x))))
out = self.sigmoid(avg_out + max_out)
return torch.mul(x, out)
class SpatialAttention(nn.Module):
def __init__(self, kernel_size=7):
super(SpatialAttention, self).__init__()
assert kernel_size in (3, 7), 'kernel size must be 3 or 7'
padding = 3 if kernel_size == 7 else 1
self.conv = nn.Conv2d(2, 1, kernel_size, padding=padding, bias=False)
self.sigmoid = nn.Sigmoid()
def forward(self, x):
avg_out = torch.mean(x, dim=1, keepdim=True)
max_out, _ = torch.max(x, dim=1, keepdim=True)
out = torch.cat([avg_out, max_out], dim=1)
out = self.sigmoid(self.conv(out))
return torch.mul(x, out)
class CBAMC3(nn.Module):
# CSP Bottleneck with 3 convolutions
def __init__(self, c1, c2, n=1, shortcut=True, g=1, e=0.5): # ch_in, ch_out, number, shortcut, groups, expansion
super(CBAMC3, self).__init__()
c_ = int(c2 * e) # hidden channels
self.cv1 = Conv(c1, c_, 1, 1)
self.cv2 = Conv(c1, c_, 1, 1)
self.cv3 = Conv(2 * c_, c2, 1)
self.m = nn.Sequential(*[Bottleneck(c_, c_, shortcut, g, e=1.0) for _ in range(n)])
self.channel_attention = ChannelAttention(c2, 16)
self.spatial_attention = SpatialAttention(7)
# self.m = nn.Sequential(*[CrossConv(c_, c_, 3, 1, g, 1.0, shortcut) for _ in range(n)])
def forward(self, x):
# 将最后的标准卷积模块改为了注意力机制提取特征
return self.spatial_attention(
self.channel_attention(self.cv3(torch.cat((self.m(self.cv1(x)), self.cv2(x)), dim=1))))
2、向yolo.py文件添加CBAMC3判断语句
1).打开models文件夹中的yolo.py文件
2).分别在239行和245行添加CBAMC3
同样改完之后记得点保存
3、修改yaml文件
注意力机制可以添加在backbone,Neck,Head等部分,大家可以在yaml文件中修改网络的结构、添加其他模块等等,接下来本文将以向主干网络(backbone)添加CBAM模块为例,本文介绍的只是其中一种添加方式
二、改损失函数为SIoU
****源代码的bbox_iou为
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 nx4
box2 = box2.T
# Get the coordinates of bounding boxes
if x1y1x2y2: # x1, y1, x2, y2 = box1
b1_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 xyxy
b1_x1, b1_x2 = box1[0] - box1[2] / 2, box1[0] + box1[2] / 2
b1_y1, b1_y2 = box1[1] - box1[3] / 2, box1[1] + box1[3] / 2
b2_x1, b2_x2 = box2[0] - box2[2] / 2, box2[0] + box2[2] / 2
b2_y1, b2_y2 = box2[1] - box2[3] / 2, box2[1] + box2[3] / 2
# Intersection area
inter = (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 Area
w1, h1 = b1_x2 - b1_x1, b1_y2 - b1_y1 + eps
w2, h2 = b2_x2 - b2_x1, b2_y2 - b2_y1 + eps
union = w1 * h1 + w2 * h2 - inter + eps
iou = inter / union
if GIoU or DIoU or CIoU:
cw = torch.max(b1_x2, b2_x2) - torch.min(b1_x1, b2_x1) # convex (smallest enclosing box) width
ch = torch.max(b1_y2, b2_y2) - torch.min(b1_y1, 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 distance squared
if DIoU:
return iou - rho2 / c2 # DIoU
elif CIoU: # https://github.com/Zzh-tju/DIoU-SSD-pytorch/blob/master/utils/box/box_utils.py#L47
v = (4 / math.pi ** 2) * torch.pow(torch.atan(w2 / h2) - torch.atan(w1 / h1), 2)
with torch.no_grad():
alpha = v / (v - iou + (1 + eps))
return iou - (rho2 / c2 + v * alpha) # CIoU
else: # GIoU https://arxiv.org/pdf/1902.09630.pdf
c_area = cw * ch + eps # convex area
return iou - (c_area - union) / c_area # GIoU
else:
return iou # IoU
替换代码为
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
1、修改general.py
将上述代码进行替换
2、修改loss.py
将第一行替换为第二行
当alpha=1时,损失函数为SIoU
当alpha>1时(网传3最好),损失函数为alpha-SIoU
三、加入BiFPN
1、在Common.py中添加定义模块(Concat)
# 结合BiFPN 设置可学习参数 学习不同分支的权重
# 两个分支concat操作
class BiFPN_Concat2(nn.Module):
def __init__(self, dimension=1):
super(BiFPN_Concat2, self).__init__()
self.d = dimension
self.w = nn.Parameter(torch.ones(2, dtype=torch.float32), requires_grad=True)
self.epsilon = 0.0001
# 设置可学习参数 nn.Parameter的作用是:将一个不可训练的类型Tensor转换成可以训练的类型
parameter
# 并且会向宿主模型注册该参数 成为其一部分 即model.parameters()会包含这个parameter
# 从而在参数优化的时候可以自动一起优化
def forward(self, x):
w = self.w
weight = w / (torch.sum(w, dim=0) + self.epsilon) # 将权重进行归一化
# Fast normalized fusion
x = [weight[0] * x[0], weight[1] * x[1]]
return torch.cat(x, self.d)
# 三个分支concat操作
class BiFPN_Concat3(nn.Module):
def __init__(self, dimension=1):
super(BiFPN_Concat3, self).__init__()
self.d = dimension
self.w = nn.Parameter(torch.ones(3, dtype=torch.float32), requires_grad=True)
self.epsilon = 0.0001
def forward(self, x):
w = self.w
weight = w / (torch.sum(w, dim=0) + self.epsilon) # 将权重进行归一化
# Fast normalized fusion
x = [weight[0] * x[0], weight[1] * x[1], weight[2] * x[2]]
return torch.cat(x, self.d)
2、将类名加入进去,修改yolo.py
# 添加bifpn_concat结构
elif m in [Concat, BiFPN_Concat2, BiFPN_Concat3]:
c2 = sum(ch[x] for x in f)
3、修改train.py
1)调用模块
from models.common import BiFPN_Concat2, BiFPN_Concat3
2)向优化器器中添加BiFPN的权重参数
pg0, pg1, pg2 = [], [], [] # optimizer parameter groups
for k, v in model.named_modules():
# hasattr: 测试指定的对象是否具有给定的属性,返回一个布尔值
if hasattr(v, 'bias') and isinstance(v.bias, nn.Parameter):
pg2.append(v.bias) # biases
if isinstance(v, nn.BatchNorm2d):
pg0.append(v.weight) # no decay
elif hasattr(v, 'weight') and isinstance(v.weight, nn.Parameter):
pg1.append(v.weight) # apply decay
elif isinstance(v, BiFPN_Concat2) and hasattr(v, 'w') and isinstance(v.w, nn.Parameter):
pg1.append(v.w)
elif isinstance(v, BiFPN_Concat3) and hasattr(v, 'w') and isinstance(v.w, nn.Parameter):
pg1.append(v.w)
if opt.adam:
optimizer = optim.Adam(pg0, lr=hyp['lr0'], betas=(hyp['momentum'], 0.999)) # adjust beta1 to momentum
else:
optimizer = optim.SGD(pg0, lr=hyp['lr0'], momentum=hyp['momentum'], nesterov=True)
optimizer.add_param_group({'params': pg1, 'weight_decay': hyp['weight_decay']}) # add pg1 with weight_decay
optimizer.add_param_group({'params': pg2}) # add pg2 (biases)
logger.info('Optimizer groups: %g .bias, %g conv.weight, %g other' % (len(pg2), len(pg1), len(pg0)))
del pg0, pg1, pg2
4、修改配置文件yolov5.yaml
# parameters
nc: 80 # number of classes
depth_multiple: 0.33 # model depth multiple
width_multiple: 0.50 # layer channel multiple
# anchors
anchors:
- [10,13, 16,30, 33,23] # P3/8
- [30,61, 62,45, 59,119] # P4/16
- [116,90, 156,198, 373,326] # P5/32
# YOLOv5 backbone
backbone:
# [from, number, module, args]
[[-1, 1, Focus, [64, 3]], # 0-P1/2
[-1, 1, Conv, [128, 3, 2]], # 1-P2/4
[-1, 3, C3, [128]],
[-1, 1, Conv, [256, 3, 2]], # 3-P3/8
[-1, 9, C3, [256]],
[-1, 1, Conv, [512, 3, 2]], # 5-P4/16
[-1, 9, C3, [512]],
[-1, 1, Conv, [1024, 3, 2]], # 7-P5/32
[-1, 1, SPP, [1024, [5, 9, 13]]],
[-1, 3, C3, [1024, False]], # 9
]
# YOLOv5 head
head:
[[-1, 1, Conv, [512, 1, 1]],
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
[[-1, 6], 1, BiFPN_Concat2, [1]], # cat backbone P4
[-1, 3, C3, [512, False]], # 13
[-1, 1, Conv, [256, 1, 1]],
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
[[-1, 4], 1, BiFPN_Concat2, [1]], # cat backbone P3
[-1, 3, C3, [256, False]], # 17 (P3/8-small)
[-1, 1, Conv, [256, 3, 2]],
[[-1, 14,6], 1,BiFPN_Concat3, [1]], # cat head P4
[-1, 3, C3, [512, False]], # 20 (P4/16-medium)
[-1, 1, Conv, [512, 3, 2]],
[[-1, 10], 1, BiFPN_Concat2, [1]], # cat head P5
[-1, 3, C3, [1024, False]], # 23 (P5/32-large)
[[17, 20, 23], 1, Detect, [nc, anchors]], # Detect(P3, P4, P5)
]