Yolov5改进_Detect篇_ASFF

1、三检测头ASFF

①common.py

在models/common.py文件最下面添加下面的代码：

def add_conv(in_ch, out_ch, ksize, stride, leaky=True):
    """
    Add a conv2d / batchnorm / leaky ReLU block.
    Args:
        in_ch (int): number of input channels of the convolution layer.
        out_ch (int): number of output channels of the convolution layer.
        ksize (int): kernel size of the convolution layer.
        stride (int): stride of the convolution layer.
    Returns:
        stage (Sequential) : Sequential layers composing a convolution block.
    """
    stage = nn.Sequential()
    pad = (ksize - 1) // 2
    stage.add_module('conv', nn.Conv2d(in_channels=in_ch,
                                       out_channels=out_ch, kernel_size=ksize, stride=stride,
                                       padding=pad, bias=False))
    stage.add_module('batch_norm', nn.BatchNorm2d(out_ch))
    if leaky:
        stage.add_module('leaky', nn.LeakyReLU(0.1))
    else:
        stage.add_module('relu6', nn.ReLU6(inplace=True))
    return stage


class ASFF(nn.Module):
    def __init__(self, level, rfb=False, vis=False):
        super(ASFF, self).__init__()
        self.level = level
        # 特征金字塔从上到下三层的channel数
        # 对应特征图大小(以640*640输入为例)分别为20*20, 40*40, 80*80
        self.dim = [512, 256, 128]
        self.inter_dim = self.dim[self.level]
        if level==0: # 特征图最小的一层，channel数512
            self.stride_level_1 = add_conv(256, self.inter_dim, 3, 2)
            self.stride_level_2 = add_conv(128, self.inter_dim, 3, 2)
            self.expand = add_conv(self.inter_dim, 512, 3, 1)
        elif level==1: # 特征图大小适中的一层，channel数256
            self.compress_level_0 = add_conv(512, self.inter_dim, 1, 1)
            self.stride_level_2 = add_conv(128, self.inter_dim, 3, 2)
            self.expand = add_conv(self.inter_dim, 256, 3, 1)
        elif level==2: # 特征图最大的一层，channel数128
            self.compress_level_0 = add_conv(512, self.inter_dim, 1, 1)
            self.compress_level_1 = add_conv(256, self.inter_dim, 1, 1)
            self.expand = add_conv(self.inter_dim, 128, 3, 1)

        compress_c = 8 if rfb else 16  #when adding rfb, we use half number of channels to save memory

        self.weight_level_0 = add_conv(self.inter_dim, compress_c, 1, 1)
        self.weight_level_1 = add_conv(self.inter_dim, compress_c, 1, 1)
        self.weight_level_2 = add_conv(self.inter_dim, compress_c, 1, 1)

        self.weight_levels = nn.Conv2d(compress_c*3, 3, kernel_size=1, stride=1, padding=0)
        self.vis= vis


    def forward(self, x_level_0, x_level_1, x_level_2):
        if self.level==0:
            level_0_resized = x_level_0
            level_1_resized = self.stride_level_1(x_level_1)

            level_2_downsampled_inter =F.max_pool2d(x_level_2, 3, stride=2, padding=1)
            level_2_resized = self.stride_level_2(level_2_downsampled_inter)

        elif self.level==1:
            level_0_compressed = self.compress_level_0(x_level_0)
            level_0_resized =F.interpolate(level_0_compressed, scale_factor=2, mode='nearest')
            level_1_resized =x_level_1
            level_2_resized =self.stride_level_2(x_level_2)
        elif self.level==2:
            level_0_compressed = self.compress_level_0(x_level_0)
            level_0_resized =F.interpolate(level_0_compressed, scale_factor=4, mode='nearest')
            level_1_compressed = self.compress_level_1(x_level_1)
            level_1_resized =F.interpolate(level_1_compressed, scale_factor=2, mode='nearest')
            level_2_resized =x_level_2

        level_0_weight_v = self.weight_level_0(level_0_resized)
        level_1_weight_v = self.weight_level_1(level_1_resized)
        level_2_weight_v = self.weight_level_2(level_2_resized)
        levels_weight_v = torch.cat((level_0_weight_v, level_1_weight_v, level_2_weight_v),1)
        levels_weight = self.weight_levels(levels_weight_v)
        levels_weight = F.softmax(levels_weight, dim=1)

        fused_out_reduced = level_0_resized * levels_weight[:,0:1,:,:]+\
                            level_1_resized * levels_weight[:,1:2,:,:]+\
                            level_2_resized * levels_weight[:,2:,:,:]

        out = self.expand(fused_out_reduced)

        if self.vis:
            return out, levels_weight, fused_out_reduced.sum(dim=1)
        else:
            return out

②yolo.py

在models/yolo.py文件的Detect类后面(注意不是Detect类里面)添加代码如下：

class ASFF_Detect(Detect):
    # ASFF model for improvement
    def __init__(self, nc=80, anchors=(), ch=(), inplace=True):  # detection layer
        super().__init__(nc, anchors, ch, inplace)
        self.nl = len(anchors)
        self.asffs = nn.ModuleList(ASFF(i) for i in range(self.nl))
        self.detect = Detect.forward

    def forward(self, x): # x中的特征图从大到小，与ASFF中顺序相反，因此输入前先反向
        x = x[::-1]
        for i in range(self.nl):
            x[i] = self.asffs[i](*x)
        return self.detect(self, x[::-1])

随后，在yolo.py文件中，出现Detect, Segment这个代码片段的地方加入ASFF_Detect。共三处需更改的地方，可利用Ctrl+F查询该代码片段并进行更改。

③yolov5s_ASFF.yaml

在models文件夹下创建yolov5s-ASFF.yaml文件，内容如下：

# YOLOv5 🚀 by Ultralytics, GPL-3.0 license

# Parameters
nc: 2  # 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, C3, [512, False]],  # 13

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

---

2、添加小目标检测层后的四头ASFF

未完待续......