[yolov5/yolov8修改]替换yolov5/yolov8中的主干网络为EfficientNetv2

yolo系列的网络作为单阶段目标检测网络中的佼佼者，在目标检测方面发挥着很大的作用，而yolov5是其中较好的一代网络，yolov8是其中最新的一代网络。但是作为我们学习和使用来说，原始的yolov5或者yolov8网络并不一定就是最合适的，基于此，在yolov5的基础上，针对主干网络进行了替换，替换成EfficientNetv2网络，yolov8的替换方式也是类似的。主要步骤如下：

首先，我们需要在common.py文件中添加如下代码段：（建议添加在common.py文件的最后

class stem(nn.Module):
    def __init__(self, c1, c2, kernel_size=3, stride=1, groups=1):
        super(stem, self).__init__()
        padding = (kernel_size-1) // 2
        self.conv = nn.Conv2d(c1, c2, kernel_size, stride, padding=padding, groups=groups, bias=False)
        self.bn = nn.BatchNorm2d(c2, eps=1e-3, momentum=0.1)
        self.act = nn.SiLU(True)

    def forward(self, x):
        #print(x.shape)
        x = self.conv(x)
        x = self.bn(x)
        x = self.act(x)
        return x

def drop_path(x, drop_prob: float = 0., training: bool = False):
    if drop_prob == 0. or not training:
        return x
    keep_prob = 1 - drop_prob
    shape = (x.shape[0],) + (1,) * (x.ndim - 1)
    random_tensor = keep_prob + torch.rand(shape, dtype=x.dtype, device=x.device)
    random_tensor.floor_()

    output = x.div(keep_prob) * random_tensor
    return output

class DropPath(nn.Module):
    def __init__(self, drop_prob=None):
        super(DropPath, self).__init__()
        self.drop_prob = drop_prob

    def forward(self, x):
        return drop_path(x, self.drop_prob, self.training)

class SqueezeExcite_efficientv2(nn.Module):
    def __init__(self, c1, c2, se_ratio=0.25, act_layer=nn.ReLU):
        super(SqueezeExcite_efficientv2, self).__init__()
        self.gate_fn = nn.Sigmoid()
        reduced_chs = int(c1 * se_ratio)
        self.avg_pool  = nn.AdaptiveAvgPool2d(1)
        self.conv_reduce = nn.Conv2d(c1, reduced_chs, 1, bias=True)
        self.act1 = act_layer(inplace=True)
        self.conv_expand = nn.Conv2d(reduced_chs, c2, 1, bias=True)

    def forward(self, x):
        x_se = self.avg_pool(x)
        x_se = self.conv_reduce(x_se)
        x_se = self.act1(x_se)
        x_se = self.conv_expand(x_se)
        x_se = self.gate_fn(x_se)
        x = x * (x_se.expand_as(x))
        return x

class FusedMBConv(nn.Module):
    def __init__(self, c1, c2, k=3, s=1, expansion=1, se_ration=0, dropout_rate=0.2, drop_connect_rate=0.2):
        super().__init__()
        self.has_shortcut = (s == 1 and c1 == c2)
        self.has_expansion = expansion != 1
        expanded_c = c1 * expansion
        if self.has_expansion:
            self.expansion_conv = stem(c1, expanded_c, kernel_size=k, stride=s)
            self.project_conv = stem(expanded_c, c2, kernel_size=1, stride=1)
        else:
            self.project_conv = stem(c1, c2, kernel_size=k, stride=s)
        self.drop_connect_rate = dropout_rate
        if self.has_shortcut and drop_connect_rate > 0:
            self.dropout = DropPath(drop_connect_rate)

    def forward(self, x):
        if self.has_expansion:
            result = self.expansion_conv(x)
            result = self.project_conv(result)
        else:
            result = self.project_conv(x)
        if self.has_shortcut:
            if self.drop_connect_rate > 0:
                result = self.dropout(result)
            result += x

        return result

class MBConv(nn.Module):
    def __init__(self, c1, c2, k=3, s=1, expansion=1, se_ration=0, dropout_rate=0.2, drop_connect_rate=0.2):
        super(MBConv, self).__init__()
        self.has_shortcut = (s == 1 and c1 == c2)
        expanded_c = c1 * expansion
        self.expansion_conv = stem(c1, expanded_c, kernel_size=1, stride=1)
        self.dw_conv = stem(expanded_c, expanded_c, kernel_size=k, stride=s, groups=expanded_c)
        self.se = SqueezeExcite_efficientv2(expanded_c, expanded_c, se_ration) if se_ration > 0 else nn.Identity()
        self.project_conv = stem(expanded_c, c2, kernel_size=1, stride=1)
        self.drop_connect_rate = drop_connect_rate
        if self.has_shortcut and drop_connect_rate > 0:
            self.dropout = DropPath(drop_connect_rate)

    def forward(self, x):
        result = self.expansion_conv(x)
        result = self.dw_conv(result)
        result = self.se(result)
        result = self.project_conv(result)
        if self.has_shortcut:
            if self.drop_connect_rate > 0:
                result = self.dropout(result)
            result += x
        return result

这部分代码需要全复制到common.py文件中。

接下来是要对上诉代码中的关键函数进行声明，在yolo.py文件中加入以下两个类名，具体的添加位置可以通过Ctrl+F的形式搜索关键词找到。添加的部分为图片中红框圈起来的几个。

最后就是在配置文件里面修改原始网络的主干网络了。最好的方式是复制一份原本的yolov5s.yaml文件，然后将其重新命名，将里面的代码全部换成以下部分：

# 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, stem, [24, 3, 2]],  # 0-P1/2
   [-1, 2, FusedMBConv, [24, 3, 1, 1, 0]],  # 1-P2/4

   [-1, 1, FusedMBConv, [48, 3, 2, 4, 0]],
   [-1, 3, FusedMBConv, [48, 3, 1, 4, 0]],  # 3-P3/8

   [-1, 1, FusedMBConv, [64, 3, 2, 4, 0]],
   [-1, 3, FusedMBConv, [64, 3, 1, 4, 0]],  # 5-P4/16

   [-1, 1, MBConv, [128, 3, 2, 4, 0.25]],
   [-1, 5, MBConv, [128, 3, 1, 4, 0.25]],  # 7-P5/32

   [-1, 1, MBConv, [160, 3, 2, 6, 0.25]],
   [-1, 8, MBConv, [160, 3, 1, 6, 0.25]],  # 9

   [-1, 1, MBConv, [256, 3, 2, 4, 0.25]],  #10
   [-1, 14, MBConv, [256, 3, 1, 4, 0.25]],  #11

   [-1, 1, SPPF, [1024, 5]],   #12
  ]

# YOLOv5 v6.0 head
head:
  [[-1, 1, Conv, [512, 1, 1]],
   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
   [[-1, 9], 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, 7], 1, Concat, [1]],  # cat backbone P3
   [-1, 3, C3, [256, False]],  # 17 (P3/8-small)

   [-1, 1, Conv, [256, 3, 2]],
   [[-1, 17], 1, Concat, [1]],  # cat head P4
   [-1, 3, C3, [512, False]],  # 20 (P4/16-medium)

   [-1, 1, Conv, [512, 3, 2]],
   [[-1, 13], 1, Concat, [1]],  # cat head P5
   [-1, 3, C3, [1024, False]],  # 23 (P5/32-large)

   [[20, 23, 26], 1, Detect, [nc, anchors]],  # Detect(P3, P4, P5)
  ]

至此，所有的修改全部完成了，但是需要注意的一点是，在训练时，一定要将训练中的yolov5s.yaml配置文件替换成修改过后的配置文件。

学不了一点