三分钟学会使用系列（YOLOv5）|ECA轻量注意力机制，涨点神器！

三分钟学会使用系列（YOLOv5）|ECA轻量注意力机制，涨点神器！

---

本文旨在让读者快速了解相关技术并运用,欢迎关注。

1. 原文链接：《ECA-Net: Efficient Channel Attention for Deep Convolutional Neural Networks》
2. 代码链接：https://github.com/BangguWu/ECANet

---

1. ECA通道注意力导读

​ ECA一种有效的轻量化通道注意力模块，在只增加少量的参数的情况下，明显的提高性能。作者的认为避免降维对于学习通道注意力非常重要，适当的跨信道交互可以在显著降低模型复杂度的同时保持性能。因此，作者提出了ECA这种通过一维卷积实现的不降维局部跨信道交互策略。

---

2. 代码

​ ECA代码。

class ECA(nn.Module):
    def __init__(self, kernel_size=3):
        super(ECA, self).__init__()
        self.avg_pool = nn.AdaptiveAvgPool2d(1)
        self.conv = nn.Conv1d(1, 1, kernel_size=kernel_size, padding=kernel_size // 2, bias=False)
        self.sigmoid = nn.Sigmoid()

    def forward(self, x):
        y = self.avg_pool(x)
        y = self.conv(y.squeeze(-1).transpose(-1, -2)).transpose(-1, -2).unsqueeze(-1)
        y = self.sigmoid(y)

        return x * y.expand_as(x)

---

3. 使用教程

​ 以YOLOv5为例，加入ECA注意力机制。

# YOLOv5 🚀 by Ultralytics, AGPL-3.0 license

# Parameters
nc: 80  # number of classes
depth_multiple: 0.33  # model depth multiple
width_multiple: 0.25  # 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, ECA, []],
   [-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, 14], 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)
  ]

4. 参考

1. 原文链接：《ECA-Net: Efficient Channel Attention for Deep Convolutional Neural Networks》
2. 代码链接：https://github.com/BangguWu/ECANet

---