Yolov5-v7.0使用CBAM注意力机制记录
一、CBAM实现代码
在model/common.py文件中加入如下代码：
#############CBAM注意力机制##############
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)
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 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
# (特征图的大小-算子的size+2*padding)/步长+1
self.conv = nn.Conv2d(2, 1, kernel_size, padding=padding, bias=False)
self.sigmoid = nn.Sigmoid()
def forward(self, x):
# 1*h*w
avg_out = torch.mean(x, dim=1, keepdim=True)
max_out, _ = torch.max(x, dim=1, keepdim=True)
x = torch.cat([avg_out, max_out], dim=1)
# 2*h*w
x = self.conv(x)
# 1*h*w
return self.sigmoid(x)
class CBAM(nn.Module):
# CSP Bottleneck with 3 convolutions
def __init__(self, c1, c2, ratio=16, kernel_size=7): # ch_in, ch_out, number, shortcut, groups, expansion
super(CBAM, self).__init__()
self.channel_attention = ChannelAttention(c1, ratio)
self.spatial_attention = SpatialAttention(kernel_size)
def forward(self, x):
out = self.channel_attention(x) * x
# c*h*w
# c*h*w * 1*h*w
out = self.spatial_attention(out) * out
return out
加在代码最后就行。
二、注册CBAM机制
在model/yolo.py文件中修改。
第一处：
from models.common import
引入CBAM。
第二处：
def parse_model(d, ch):
继续增加CBAM
三、更改yolov5s.yaml文件
yolov5s.yaml文件是模型结构文件，增加CBAM机制
# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
# Parameters
nc: 80 # 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
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, 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]],
[-1, 1, CBAM, [1024]],
[-1, 1, SPPF, [1024, 5]], # 10
]
# 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]], # 14
[-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]], # 18 (P3/8-small)
[-1, 1, Conv, [256, 3, 2]],
[[-1, 15], 1, Concat, [1]], # cat head P4
[-1, 3, C3, [512, False]], # 21 (P4/16-medium)
[-1, 1, Conv, [512, 3, 2]],
[[-1, 11], 1, Concat, [1]], # cat head P5
[-1, 3, C3, [1024, False]], # 24 (P5/32-large)
[[18, 21, 24], 1, Detect, [nc, anchors]], # Detect(P3, P4, P5)
]
四、修改train.py文件
增加注意力机制后，运行train.py文件会报错：
RuntimeError: adaptive_max_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. You can also file an issue at https://github.com/pytorch/pytorch/issues to help us prioritize adding deterministic support for this operation.
需要修改train.py文件。在代码：
scaler.scale(loss).backward()
前面加上：
torch.use_deterministic_algorithms(False)
修改后如下：
五、训练
训练时留意一下CBAM是否生效
