YOLOv5改进（CoordConv）

1.CoodConev原文地址：

 https://arxiv.org/pdf/1807.03247v2.pdf

2.改进策略，在原有卷积上增加了i、j坐标

3.方法：

（1）将下面代码放到models/commen.py中

lass AddCoords(nn.Module):

    def __init__(self, with_r=False):
        super().__init__()
        self.with_r = with_r

    def forward(self, input_tensor):
        """
        Args:
            input_tensor: shape(batch, channel, x_dim, y_dim)
        """
        batch_size, _, x_dim, y_dim = input_tensor.size()

        xx_channel = torch.arange(x_dim).repeat(1, y_dim, 1)
        yy_channel = torch.arange(y_dim).repeat(1, x_dim, 1).transpose(1, 2)

        xx_channel = xx_channel.float() / (x_dim - 1)
        yy_channel = yy_channel.float() / (y_dim - 1)

        xx_channel = xx_channel * 2 - 1
        yy_channel = yy_channel * 2 - 1

        xx_channel = xx_channel.repeat(batch_size, 1, 1, 1).transpose(2, 3)
        yy_channel = yy_channel.repeat(batch_size, 1, 1, 1).transpose(2, 3)

        ret = torch.cat([
            input_tensor,
            xx_channel.type_as(input_tensor),
            yy_channel.type_as(input_tensor)], dim=1)

        if self.with_r:
            rr = torch.sqrt(torch.pow(xx_channel.type_as(input_tensor) - 0.5, 2) + torch.pow(yy_channel.type_as(input_tensor) - 0.5, 2))
            ret = torch.cat([ret, rr], dim=1)

        return ret


class CoordConv(nn.Module):

    def __init__(self, in_channels, out_channels, kernel_size=1, stride=1, with_r=False):
        super().__init__()
        self.addcoords = AddCoords(with_r=with_r)
        in_channels += 2
        if with_r:
            in_channels += 1
        self.conv = Conv(in_channels, out_channels, k=kernel_size, s=stride)

    def forward(self, x):
        x = self.addcoords(x)
        x = self.conv(x)
        return x

2.将CoordConv加到models/yolo.py的parse_model中

3.构建yaml文件

# Parameters
nc: 1  # 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, CoordConv, [512, 1, 1]],
   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
   [[-1, 6], 1, Concat, [1]],  # cat backbone P4
   [-1, 3, C3, [512, False]],  # 13

   [-1, 1, CoordConv, [256, 1, 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, Conv, [256, 3, 2]],
   [[-1, 14], 1, Concat, [1]],  # cat head P4
   [-1, 3, C3, [512, False]],  # 20 (P4/16-medium)

   [-1, 1, Conv, [512, 3, 2]],
   [[-1, 10], 1, Concat, [1]],  # cat head P5
   [-1, 3, C3, [1024, False]],  # 23 (P5/32-large)

   [17, 1, CoordConv, [256, 1 ]], # 24
   [20, 1, CoordConv, [512, 1]], # 25
   [23, 1, CoordConv, [1024, 1]], # 26

   [[24, 25, 26], 1, Detect, [nc, anchors]],  # Detect(P3, P4, P5)
  ]

4.运行