YOLO V5（6.0）添加CBAM、SENet、CA注意力机制手把手教程
1.添加CBAM
1)修改commom.py
在代码最后添加
#CBAM
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)
# in_planes // ratio 这里会出现如下警告：
# UserWarning: __floordiv__ is deprecated(被舍弃了), and its behavior will change in a future version of pytorch.
# It currently rounds toward 0 (like the 'trunc' function NOT 'floor').
# This results in incorrect rounding for negative values.
# To keep the current behavior, use torch.div(a, b, rounding_mode='trunc'),
# or for actual floor division, use torch.div(a, b, rounding_mode='floor').
# kernel = torch.DoubleTensor([*(x[0].shape[2:])]) // torch.DoubleTensor(list((m.output_size,))).squeeze()
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)
self.sigmoid = nn.Sigmoid()
def forward(self, x):
# 全局平均池化—>MLP两层卷积
avg_out = self.f2(self.relu(self.f1(self.avg_pool(x))))
# 全局最大池化—>MLP两层卷积
max_out = self.f2(self.relu(self.f1(self.max_pool(x))))
out = self.sigmoid(avg_out + max_out)
return 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):
# 基于channel的全局平均池化(channel=1)
avg_out = torch.mean(x, dim=1, keepdim=True)
# 基于channel的全局最大池化(channel=1)
max_out, _ = torch.max(x, dim=1, keepdim=True)
# channel拼接(channel=2)
x = torch.cat([avg_out, max_out], dim=1)
# channel=1
x = self.conv(x)
return self.sigmoid(x)
class CBAMBottleneck(nn.Module):
# ch_in, ch_out, shortcut, groups, expansion, ratio, kernel_size
def __init__(self, c1, c2, shortcut=True, g=1, e=0.5, ratio=16, kernel_size=7):
super(CBAMBottleneck, self).__init__()
c_ = int(c2 * e) # hidden channels
self.cv1 = Conv(c1, c_, 1, 1)
self.cv2 = Conv(c_, c2, 3, 1, g=g)
self.add = shortcut and c1 == c2
# 加入CBAM模块
self.channel_attention = ChannelAttention(c2, ratio)
self.spatial_attention = SpatialAttention(kernel_size)
def forward(self, x):
# 考虑加入CBAM模块的位置：bottleneck模块刚开始时、bottleneck模块中shortcut之前，这里选择在shortcut之前
x2 = self.cv2(self.cv1(x)) # x和x2的channel数相同
# 在bottleneck模块中shortcut之前加入CBAM模块
out = self.channel_attention(x2) * x2
# print('outchannels:{}'.format(out.shape))
out = self.spatial_attention(out) * out
return x + out if self.add else out
class C3CBAM(C3):
# C3 module with CBAMBottleneck()
def __init__(self, c1, c2, n=1, shortcut=True, g=1, e=0.5):
super().__init__(c1, c2, n, shortcut, g, e) # 引入C3(父类)的属性
c_ = int(c2 * e) # hidden channels
self.m = nn.Sequential(*(CBAMBottleneck(c_, c_, shortcut) for _ in range(n)))
2）修改yolo.py
原代码为：
if m in {
Conv, GhostConv, Bottleneck, GhostBottleneck, SPP, SPPF, DWConv, MixConv2d, Focus, CrossConv,
BottleneckCSP, C3, C3TR, C3SPP, C3Ghost, nn.ConvTranspose2d, DWConvTranspose2d, C3x}:
c1, c2 = ch[f], args[0]在后面添加 CBAMBottleneck, C3CBAM
修改后为：
if m in {
Conv, GhostConv, Bottleneck, GhostBottleneck, SPP, SPPF, DWConv, MixConv2d, Focus, CrossConv,
BottleneckCSP, C3, C3TR, C3SPP, C3Ghost, nn.ConvTranspose2d, DWConvTranspose2d, C3x,CBAMBottleneck, C3CBAM}:
c1, c2 = ch[f], args[0]3）在models文件夹下创建yaml文件，命名为yolov5-cbam.yaml
内容为
# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
# Parameters
nc: 20 # number of classes
depth_multiple: 0.33 # model depth multiple
width_multiple: 0.50 # layer channel multiple
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 v6.0 backbone
# 第二种加入方法 全部替换 C3 模块
backbone:
# [from, number, module, args]
[[-1, 1, Conv, [64, 6, 2, 2]], # 0-P1/2
[-1, 1, Conv, [128, 3, 2]], # 1-P2/4
[-1, 3, C3CBAM, [128]],
[-1, 1, Conv, [256, 3, 2]], # 3-P3/8
[-1, 6, C3CBAM, [256]],
[-1, 1, Conv, [512, 3, 2]], # 5-P4/16
[-1, 9, C3CBAM, [512]],
[-1, 1, Conv, [1024, 3, 2]], # 7-P5/32
[-1, 3, C3CBAM, [1024]],
[-1, 1, SPPF, [1024, 5]], # 9
]
# YOLOv5 v6.0 head
head:
[[-1, 1, Conv, [512, 1, 1]],
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
[[-1, 6], 1, Concat, [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, Concat, [1]], # cat backbone P3
[-1, 3, C3, [256, False]], # 17 (P3/8-small)
[-1, 1, Conv, [256, 3, 2]],
[[-1, 14], 1, Concat, [1]], # cat head P4
[-1, 3, C3, [512, False]], # 20 (P4/16-medium)
[-1, 1, Conv, [512, 3, 2]],
[[-1, 10], 1, Concat, [1]], # cat head P5
[-1, 3, C3, [1024, False]], # 23 (P5/32-large)
[[17, 20, 23], 1, Detect, [nc, anchors]], # Detect(P3, P4, P5)
]
4）在train.py中修改
---cfg中添加yaml文件路径
parser = argparse.ArgumentParser()
parser.add_argument('--weights', type=str, default=ROOT / 'yolov5s.pt', help='initial weights path')
parser.add_argument('--cfg', type=str, default=r'models/yolov5-cbam.yaml', help='model.yaml path')5）运行train.py
2.添加SENet
1)修改commom.py
在代码最后添加
#SENet
class SE(nn.Module):
def __init__(self, c1, c2, ratio=16):
super(SE, self).__init__()
#c*1*1
self.avgpool = nn.AdaptiveAvgPool2d(1)
self.l1 = nn.Linear(c1, c1 // ratio, bias=False)
self.relu = nn.ReLU(inplace=True)
self.l2 = nn.Linear(c1 // ratio, c1, bias=False)
self.sig = nn.Sigmoid()
def forward(self, x):
b, c, _, _ = x.size()
y = self.avgpool(x).view(b, c)
y = self.l1(y)
y = self.relu(y)
y = self.l2(y)
y = self.sig(y)
y = y.view(b, c, 1, 1)
return x * y.expand_as(x)
2）修改yolo.py
原代码为：
if m in {
Conv, GhostConv, Bottleneck, GhostBottleneck, SPP, SPPF, DWConv, MixConv2d, Focus, CrossConv,
BottleneckCSP, C3, C3TR, C3SPP, C3Ghost, nn.ConvTranspose2d, DWConvTranspose2d, C3x}:
c1, c2 = ch[f], args[0]在后面添加 SE
修改后为：
if m in {
Conv, GhostConv, Bottleneck, GhostBottleneck, SPP, SPPF, DWConv, MixConv2d, Focus, CrossConv,
BottleneckCSP, C3, C3TR, C3SPP, C3Ghost, nn.ConvTranspose2d, DWConvTranspose2d, C3x,SE}:
c1, c2 = ch[f], args[0]3）在models文件夹下创建yaml文件，命名为yolov5-se.yaml
内容为
# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
# Parameters
nc: 20 # number of classes 类别数
depth_multiple: 0.33 # model depth multiple 控制模型的深度（BottleneckCSP数）
width_multiple: 0.50 # layer channel multiple 控制Conv通道数（卷积核的数量）
#depth_multiple表示BottleneckCSP模块的层缩放因子，将所有的BottleneckCSP模块的BottleneckCSP乘上该参数得到最终个数
#width_multiple表示卷积通道的缩放因子，就是将配置中的backbone和head部分有关Conv通道的设置，全都乘上该系数
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 v6.0 backbone
backbone:
# [from, number, module, args]
#from列参数：当前模块输入来自哪一层的输出；-1代表从上一层得到的输入
#number列参数：本模块的重复次数；1表示只有一个，3表示有三个相同模块
[[-1, 1, Conv, [64, 6, 2, 2]], # 0-P1/2
[-1, 1, Conv, [128, 3, 2]], # 1-P2/4 #128个卷积核（128个通道），3代表3×3的卷积核，2表示步长为2
[-1, 3, C3, [128]],
[-1, 1, Conv, [256, 3, 2]], # 3-P3/8
[-1, 6, 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, 3, C3, [1024]], #这里的C3代表BottleneckCSP
[-1, 1, SE, [1024]],
[-1, 1, SPPF, [1024, 5]], # 9
]
# YOLOv5 v6.0 head
#head=PANet+Detect
head:
[[-1, 1, Conv, [512, 1, 1]],
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
[[-1, 6], 1, Concat, [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, Concat, [1]], # cat backbone P3
[-1, 3, C3, [256, False]], # 17 (P3/8-small)
[-1, 1, Conv, [256, 3, 2]],
[[-1, 15], 1, Concat, [1]], # cat head P4，在backbone第九层添加SE后，第九层之后的编号都要加1，14+1
[-1, 3, C3, [512, False]], # 20 (P4/16-medium)
[-1, 1, Conv, [512, 3, 2]],
[[-1, 11], 1, Concat, [1]], # cat head P5，在backbone第九层添加SE后，第九层之后的编号都要加1，10+1
[-1, 3, C3, [1024, False]], # 23 (P5/32-large)
[[18, 21, 24], 1, Detect, [nc, anchors]], # Detect(P3, P4, P5)，在backbone第九层添加SE后，第九层之后的编号都要加1，17+1，20+1，23+1
]
4）在train.py中修改
---cfg中添加yaml文件路径(与CBAM添加路径一致)
parser = argparse.ArgumentParser()
parser.add_argument('--weights', type=str, default=ROOT / 'yolov5s.pt', help='initial weights path')
parser.add_argument('--cfg', type=str, default=r'models/yolov5-se.yaml', help='model.yaml path')5）运行train.py
3.添加CA
1)修改commom.py
在代码最后添加
#CA
class h_sigmoid(nn.Module):
def __init__(self, inplace=True):
super(h_sigmoid, self).__init__()
self.relu = nn.ReLU6(inplace=inplace)
def forward(self, x):
return self.relu(x + 3) / 6
class h_swish(nn.Module):
def __init__(self, inplace=True):
super(h_swish, self).__init__()
self.sigmoid = h_sigmoid(inplace=inplace)
def forward(self, x):
return x * self.sigmoid(x)
class CoordAtt(nn.Module):
def __init__(self, inp, oup, reduction=32):
super(CoordAtt, self).__init__()
self.pool_h = nn.AdaptiveAvgPool2d((None, 1))
self.pool_w = nn.AdaptiveAvgPool2d((1, None))
mip = max(8, inp // reduction)
self.conv1 = nn.Conv2d(inp, mip, kernel_size=1, stride=1, padding=0)
self.bn1 = nn.BatchNorm2d(mip)
self.act = h_swish()
self.conv_h = nn.Conv2d(mip, oup, kernel_size=1, stride=1, padding=0)
self.conv_w = nn.Conv2d(mip, oup, kernel_size=1, stride=1, padding=0)
def forward(self, x):
identity = x
n, c, h, w = x.size()
x_h = self.pool_h(x)
x_w = self.pool_w(x).permute(0, 1, 3, 2)
y = torch.cat([x_h, x_w], dim=2)
y = self.conv1(y)
y = self.bn1(y)
y = self.act(y)
x_h, x_w = torch.split(y, [h, w], dim=2)
x_w = x_w.permute(0, 1, 3, 2)
a_h = self.conv_h(x_h).sigmoid()
a_w = self.conv_w(x_w).sigmoid()
out = identity * a_w * a_h
return out
2）修改yolo.py
原代码为：
if m in {
Conv, GhostConv, Bottleneck, GhostBottleneck, SPP, SPPF, DWConv, MixConv2d, Focus, CrossConv,
BottleneckCSP, C3, C3TR, C3SPP, C3Ghost, nn.ConvTranspose2d, DWConvTranspose2d, C3x}:
c1, c2 = ch[f], args[0]在后面添加 CoordAtt
修改后为：
if m in {
Conv, GhostConv, Bottleneck, GhostBottleneck, SPP, SPPF, DWConv, MixConv2d, Focus, CrossConv,
BottleneckCSP, C3, C3TR, C3SPP, C3Ghost, nn.ConvTranspose2d, DWConvTranspose2d, C3x,CoordAtt}:
c1, c2 = ch[f], args[0]3）在models文件夹下创建yaml文件，命名为yolov5-ca.yaml
内容为
# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
# Parameters
nc: 20 # number of classes 类别数
depth_multiple: 0.33 # model depth multiple 控制模型的深度（BottleneckCSP数）
width_multiple: 0.50 # layer channel multiple 控制Conv通道数（卷积核的数量）
#depth_multiple表示BottleneckCSP模块的层缩放因子，将所有的BottleneckCSP模块的BottleneckCSP乘上该参数得到最终个数
#width_multiple表示卷积通道的缩放因子，就是将配置中的backbone和head部分有关Conv通道的设置，全都乘上该系数
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 v6.0 backbone
backbone:
# [from, number, module, args]
#from列参数：当前模块输入来自哪一层的输出；-1代表从上一层得到的输入
#number列参数：本模块的重复次数；1表示只有一个，3表示有三个相同模块
[[-1, 1, Conv, [64, 6, 2, 2]], # 0-P1/2
[-1, 1, Conv, [128, 3, 2]], # 1-P2/4 #128个卷积核（128个通道），3代表3×3的卷积核，2表示步长为2
[-1, 3, C3, [128]],
[-1, 1, Conv, [256, 3, 2]], # 3-P3/8
[-1, 6, 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, 3, C3, [1024]], #这里的C3代表BottleneckCSP
[-1, 1, CoordAtt, [1024]],
[-1, 1, SPPF, [1024, 5]], # 9
]
# YOLOv5 v6.0 head
#head=PANet+Detect
head:
[[-1, 1, Conv, [512, 1, 1]],
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
[[-1, 6], 1, Concat, [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, Concat, [1]], # cat backbone P3
[-1, 3, C3, [256, False]], # 17 (P3/8-small)
[-1, 1, Conv, [256, 3, 2]],
[[-1, 15], 1, Concat, [1]], # cat head P4，在backbone第九层添加SE后，第九层之后的编号都要加1，14+1
[-1, 3, C3, [512, False]], # 20 (P4/16-medium)
[-1, 1, Conv, [512, 3, 2]],
[[-1, 11], 1, Concat, [1]], # cat head P5，在backbone第九层添加SE后，第九层之后的编号都要加1，10+1
[-1, 3, C3, [1024, False]], # 23 (P5/32-large)
[[18, 21, 24], 1, Detect, [nc, anchors]], # Detect(P3, P4, P5)，在backbone第九层添加SE后，第九层之后的编号都要加1，17+1，20+1，23+1
]
4）在train.py中修改
---cfg中添加yaml文件路径(与CBAM添加路径一致)
parser = argparse.ArgumentParser()
parser.add_argument('--weights', type=str, default=ROOT / 'yolov5s.pt', help='initial weights path')
parser.add_argument('--cfg', type=str, default=r'models/yolov5-ca.yaml', help='model.yaml path')5）运行train.py
我的代码在运行时显示CoordAtt插入正常，但是反向传播异常
报错：adaptive_avg_pool2d_backward_cuda does not have a deterministic implementation, but you set 'torch.use_deterministic_algorithms(True)'. You can turn off determinism just for this operation, or you can use the 'warn_only=True' option, if that's acceptable for your application.
adaptive_avg_pool2d_backward_cuda does not have a deterministic implementation, but you set 'torch.use_deterministic_algorithms(True)'. You can turn off determinism just for this operation, or you can use the 'warn_only=True' option, if that's acceptable for your application.参考https://blog.csdn.net/qq_39696563/article/details/126339400后做出了修改，可以正常训练
添加内容如上
参考：
https://blog.csdn.net/qq_39740357/article/details/124084158
https://blog.csdn.net/weixin_43799388/article/details/123603131