一、C3模块
在原版YOLOv5网络中，C3模块的结构如图1-1所示，C3结构中的ConvBNSiLU和BottleNeck的结构如图1-2所示：
Conv、BottleNeck、C3的代码如下：
class Conv(nn.Module):
# Standard convolution 通用卷积模块,包括1卷积1BN1激活,激活默认SiLU,可用变量指定,不激活时用nn.Identity()占位,直接返回输入
def __init__(self, c1, c2, k=1, s=1, p=None, g=1, act=True): # ch_in, ch_out, kernel, stride, padding, groups
super(Conv, self).__init__()
self.conv = nn.Conv2d(c1, c2, k, s, autopad(k, p), groups=g, bias=False)
self.bn = nn.BatchNorm2d(c2)
self.act = nn.SiLU() if act is True else (act if isinstance(act, nn.Module) else nn.Identity())
def forward(self, x):
return self.act(self.bn(self.conv(x)))
def fuseforward(self, x):
return self.act(self.conv(x))
class Bottleneck(nn.Module):
# Standard bottleneck 残差块
def __init__(self, c1, c2, shortcut=True, g=1, e=0.5): # ch_in, ch_out, shortcut, groups, expansion
super(Bottleneck, 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
def forward(self, x): # 如果shortcut并且输入输出通道相同则跳层相加
return x + self.cv2(self.cv1(x)) if self.add else self.cv2(self.cv1(x))
class C3(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(C3, 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) # act=FReLU(c2)
self.m = nn.Sequential(*[Bottleneck(c_, c_, shortcut, g, e=1.0) for _ in range(n)]) # n个残差组件(Bottleneck)
# self.m = nn.Sequential(*[CrossConv(c_, c_, 3, 1, g, 1.0, shortcut) for _ in range(n)])
def forward(self, x):
return self.cv3(torch.cat((self.m(self.cv1(x)), self.cv2(x)), dim=1))
二、轻量化C3模块
轻量化C3的改进思路是将原C3模块中使用的普通卷积，全部替换为深度可分离卷积，其余结构不变，改进后的DP_Conv、DP_BottleNeck、DP_C3的代码如下：
class DP_Conv(nn.Module):
def __init__(self, c1, c2, s=1, k=1, p=None, g=1, act=True): # ch_in, ch_out, kernel, stride, padding, groups
super(DP_Conv, self).__init__()
self.conv = nn.Conv2d(c1, c1, kernel_size=3, stride=1, padding=1, groups=c1)
self.conv = nn.Conv2d(c1, c2, kernel_size=1, stride=s)
self.bn = nn.BatchNorm2d(c2)
self.act = nn.SiLU() if act is True else (act if isinstance(act, nn.Module) else nn.Identity())
def forward(self, x):
return self.act(self.bn(self.conv(x)))
def fuseforward(self, x):
return self.act(self.conv(x))
class DP_Bottleneck(nn.Module):
def __init__(self, c1, c2, shortcut=True, g=1, e=0.5): # ch_in, ch_out, shortcut, groups, expansion
super(DP_Bottleneck, self).__init__()
c_ = int(c2 * e) # hidden channels
self.cv1 = DP_Conv(c1, c_, 1)
self.cv2 = DP_Conv(c_, c2, 1)
self.add = shortcut and c1 == c2
def forward(self, x): # 如果shortcut并且输入输出通道相同则跳层相加
return x + self.cv2(self.cv1(x)) if self.add else self.cv2(self.cv1(x))
class DP_C3(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(DP_C3, self).__init__()
c_ = int(c2 * e) # hidden channels
self.cv1 = DP_Conv(c1, c_, 1)
self.cv2 = DP_Conv(c1, c_, 1)
self.cv3 = DP_Conv(2 * c_, c2, 1) # act=FReLU(c2)
self.m = nn.Sequential(*[DP_Bottleneck(c_, c_, shortcut, g, e=1.0) for _ in range(n)]) # n个残差组件(Bottleneck)
# self.m = nn.Sequential(*[CrossConv(c_, c_, 3, 1, g, 1.0, shortcut) for _ in range(n)])
def forward(self, x):
return self.cv3(torch.cat((self.m(self.cv1(x)), self.cv2(x)), dim=1))
修改后的网络结构如下：
# parameters
nc: 20 # 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, DP_Conv, [64, 2]], # 0-P1/2
[-1, 1, DP_Conv, [128, 2]], # 1-P2/4
[-1, 3, DP_C3, [128]],
[-1, 1, DP_Conv, [256, 2]], # 3-P3/8
[-1, 9, DP_C3, [256]],
[-1, 1, DP_Conv, [512, 2]], # 5-P4/16
[-1, 9, DP_C3, [512]],
[-1, 1, DP_Conv, [1024, 2]], # 7-P5/32
[-1, 3, DP_C3, [1024]],
[-1, 1, SPPF, [1024, 5]], # 9
]
# YOLOv5 head
head:
[[-1, 1, DP_Conv, [512, 1]],
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
[[-1, 6], 1, Concat, [1]], # cat backbone P4 # PANet是add, yolov5是concat
[-1, 3, C3, [512, False]], # 13
[-1, 1, DP_Conv, [256, 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, DP_Conv, [256, 2]],
[[-1, 14], 1, Concat, [1]], # cat head P4
[-1, 3, C3, [512, False]], # 20 (P4/16-medium)
[-1, 1, DP_Conv, [512, 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) 必须在最后一层, 原代码很多默认了Detect是最后, 并没有全改
]