涨点神器：Yolov5/Yolov7加入ConvNeXt即插即用的注意力模块CNeB（一）

1.ConvNeXt 简介
《A ConvNet for the 2020s》
论文地址：https://arxiv.org/abs/2201.03545
pytorch代码：GitHub - facebookresearch/ConvNeXt: Code release for ConvNeXt model
借鉴Swin-T的结构设计思路来重新改进CNN。作者将所提出的卷积网络结构ConvNeXt称为“2020年代的卷积网络”

ConvNeXts完全由标准ConvNet模块构建，在精度和可扩展性方面与transformer竞争，实现了87.8%的ImageNet top-1精度，在COCO检测和ADE20K分割方面优于Swin transformer，同时保持了标准ConvNets的简单性和效率。

  每个Transformer块中的一个重要设计是它创建了一个反向瓶颈，即MLP块的隐藏维度是输入维度的四倍宽(图4)。这个Transformer设计连接到ConvNets中使用的扩展比为4的反向瓶颈设计。该想法由MobileNetV2推广，随后在几个先进的ConvNet架构中获得了支持。

2.yolov5加入CNeB，大幅度提升小目标检测性能

 2.1 CNeB加入common.py中：

class CNeB(nn.Module):
    # CSP ConvNextBlock 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().__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(*(ConvNextBlock(c_) for _ in range(n)))

    def forward(self, x):
        return self.cv3(torch.cat((self.m(self.cv1(x)), self.cv2(x)), dim=1))

2.2 CNeB加入yolo.py中：

        if m in {
                Conv, GhostConv, Bottleneck, GhostBottleneck, SPP, SPPF, DWConv, MixConv2d, Focus, CrossConv,
                BottleneckCSP, C3, C3TR, C3SPP, C3Ghost, CNeB, nn.ConvTranspose2d, DWConvTranspose2d, C3x, C2f,CARAFE
                }:
            c1, c2 = ch[f], args[0]
            if c2 != no:  # if not output
                c2 = make_divisible(c2 * gw, 8)

            args = [c1, c2, *args[1:]]
            if m in {BottleneckCSP, C3, C3TR, CNeB, C3Ghost, C3x, C2f}:
                args.insert(2, n)  # number of repeats
                n = 1

2.3 修改yolo5s_CNeB_neck.yaml

# YOLOAir  by , 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, 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, CNeB, [512]],  # 13

   [-1, 1, Conv, [256, 1, 1]],
   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
   [[-1, 4], 1, Concat, [1]],  # cat backbone P3
   [-1, 3, CNeB, [256]],  # 17 (P3/8-small)

   [-1, 1, Conv, [256, 3, 2]],
   [[-1, 14], 1, Concat, [1]],  # cat head P4
   [-1, 3, CNeB, [512]],  # 20 (P4/16-medium)

   [-1, 1, Conv, [512, 3, 2]],
   [[-1, 10], 1, Concat, [1]],  # cat head P5
   [-1, 3, CNeB, [1024]],  # 23 (P5/32-large)

   [[17, 20, 23], 1, Detect, [nc, anchors]],  # Detect(P3, P4, P5)
  ]

下一篇链接：

涨点神器：Yolov5/Yolov7加入ConvNeXt提升小目标检测能力，适用yolo各个系列_AI&CV的博客-CSDN博客