YOLOv5改进添加解耦头、ASFF

网上有很多添加解耦头的博客，在此记录下我使用解耦头对YOLOv5改进，若侵权删

解耦头的介绍过段时间再写，先直接上添加方法（这篇文章写的很好，解释了解耦头的作用）

ASFF我没有使用过，但是按照下边的方法添加后也能够运行

我是在YOLOv5-7.0版本上进行修改，如果有什么不对的地方欢迎大佬指教

一、common.py文件中加入代码

这部分是解耦头的代码

对着图去看代码能更好的理解结构

#======================= 解耦头=============================#
class DecoupledHead(nn.Module):
    def __init__(self, ch=256, nc=80,  anchors=()):
        super().__init__()
        self.nc = nc  # number of classes
        self.nl = len(anchors)  # number of detection layers
        self.na = len(anchors[0]) // 2  # number of anchors
        self.merge = Conv(ch, 256 , 1, 1)
        self.cls_convs1 = Conv(256 , 256 , 3, 1, 1)
        self.cls_convs2 = Conv(256 , 256 , 3, 1, 1)
        self.reg_convs1 = Conv(256 , 256 , 3, 1, 1)
        self.reg_convs2 = Conv(256 , 256 , 3, 1, 1)
        self.cls_preds = nn.Conv2d(256 , self.nc * self.na, 1) # 一个1x1的卷积，把通道数变成类别数，比如coco 80类（主要对目标框的类别，预测分数）
        self.reg_preds = nn.Conv2d(256 , 4 * self.na, 1)       # 一个1x1的卷积，把通道数变成4通道，因为位置是xywh
        self.obj_preds = nn.Conv2d(256 , 1 * self.na, 1)       # 一个1x1的卷积，把通道数变成1通道，通过一个值即可判断有无目标（置信度）

    def forward(self, x):
        x = self.merge(x)
        x1 = self.cls_convs1(x)
        x1 = self.cls_convs2(x1)
        x1 = self.cls_preds(x1)
        x2 = self.reg_convs1(x)
        x2 = self.reg_convs2(x2)
        x21 = self.reg_preds(x2)
        x22 = self.obj_preds(x2)
        out = torch.cat([x21, x22, x1], 1) # 把分类和回归结果按channel维度，即dim=1拼接
        return out

class Decoupled_Detect(nn.Module):
    stride = None  # strides computed during build
    onnx_dynamic = False  # ONNX export parameter
    export = False  # export mode

    def __init__(self, nc=80, anchors=(), ch=(), inplace=True):  # detection layer
        super().__init__()

        self.nc = nc  # number of classes
        self.no = nc + 5  # number of outputs per anchor
        self.nl = len(anchors)  # number of detection layers
        self.na = len(anchors[0]) // 2  # number of anchors
        self.grid = [torch.zeros(1)] * self.nl  # init grid
        self.anchor_grid = [torch.zeros(1)] * self.nl  # init anchor grid
        self.register_buffer('anchors', torch.tensor(anchors).float().view(self.nl, -1, 2))  # shape(nl,na,2)
        self.m = nn.ModuleList(DecoupledHead(x, nc, anchors) for x in ch)
        self.inplace = inplace  # use in-place ops (e.g. slice assignment)

    def forward(self, x):
        z = []  # inference output
        for i in range(self.nl):
            x[i] = self.m[i](x[i])  # conv
            bs, _, ny, nx = x[i].shape  # x(bs,255,20,20) to x(bs,3,20,20,85)
            x[i] = x[i].view(bs, self.na, self.no, ny, nx).permute(0, 1, 3, 4, 2).contiguous()

            if not self.training:  # inference
                if self.onnx_dynamic or self.grid[i].shape[2:4] != x[i].shape[2:4]:
                    self.grid[i], self.anchor_grid[i] = self._make_grid(nx, ny, i)

                y = x[i].sigmoid()
                if self.inplace:
                    y[..., 0:2] = (y[..., 0:2] * 2 + self.grid[i]) * self.stride[i]  # xy
                    y[..., 2:4] = (y[..., 2:4] * 2) ** 2 * self.anchor_grid[i]  # wh
                else:  # for YOLOv5 on AWS Inferentia https://github.com/ultralytics/yolov5/pull/2953
                    xy, wh, conf = y.split((2, 2, self.nc + 1), 4)  # y.tensor_split((2, 4, 5), 4)  # torch 1.8.0
                    xy = (xy * 2 + self.grid[i]) * self.stride[i]  # xy
                    wh = (wh * 2) ** 2 * self.anchor_grid[i]  # wh
                    y = torch.cat((xy, wh, conf), 4)
                z.append(y.view(bs, -1, self.no))

        return x if self.training else (torch.cat(z, 1),) if self.export else (torch.cat(z, 1), x)

    def _make_grid(self, nx=20, ny=20, i=0):
        d = self.anchors[i].device
        t = self.anchors[i].dtype
        shape = 1, self.na, ny, nx, 2  # grid shape
        y, x = torch.arange(ny, device=d, dtype=t), torch.arange(nx, device=d, dtype=t)
        if check_version(torch.__version__, '1.10.0'):  # torch>=1.10.0 meshgrid workaround for torch>=0.7 compatibility
            yv, xv = torch.meshgrid(y, x, indexing='ij')
        else:
            yv, xv = torch.meshgrid(y, x)
        grid = torch.stack((xv, yv), 2).expand(shape) - 0.5  # add grid offset, i.e. y = 2.0 * x - 0.5
        anchor_grid = (self.anchors[i] * self.stride[i]).view((1, self.na, 1, 1, 2)).expand(shape)
        return grid, anchor_grid

这部分是ASFF代码

首先需要在common.py导入该段代码

import torch.nn.functional as F

然后在common.py最下方加入ASFF的代码

#====================================== ASFF ===========================================#
class ASFFV5(nn.Module):
    def __init__(self, level, multiplier=1, rfb=False, vis=False, act_cfg=True):
        """
        ASFF version for YoloV5 .
        different than YoloV3
        multiplier should be 1, 0.5
        which means, the channel of ASFF can be 
        512, 256, 128 -> multiplier=1
        256, 128, 64 -> multiplier=0.5
        For even smaller, you need change code manually.
        """
        super(ASFFV5, self).__init__()
        self.level = level
        self.dim = [int(1024*multiplier), int(512*multiplier),
                    int(256*multiplier)]
        # print(self.dim)
        
        self.inter_dim = self.dim[self.level]
        if level == 0:
            self.stride_level_1 = Conv(int(512*multiplier), self.inter_dim, 3, 2)
                
            self.stride_level_2 = Conv(int(256*multiplier), self.inter_dim, 3, 2)
                
            self.expand = Conv(self.inter_dim, int(
                1024*multiplier), 3, 1)
        elif level == 1:
            self.compress_level_0 = Conv(
                int(1024*multiplier), self.inter_dim, 1, 1)
            self.stride_level_2 = Conv(
                int(256*multiplier), self.inter_dim, 3, 2)
            self.expand = Conv(self.inter_dim, int(512*multiplier), 3, 1)
        elif level == 2:
            self.compress_level_0 = Conv(
                int(1024*multiplier), self.inter_dim, 1, 1)
            self.compress_level_1 = Conv(
                int(512*multiplier), self.inter_dim, 1, 1)
            self.expand = Conv(self.inter_dim, int(
                256*multiplier), 3, 1)

        # when adding rfb, we use half number of channels to save memory
        compress_c = 8 if rfb else 16
        self.weight_level_0 = Conv(
            self.inter_dim, compress_c, 1, 1)
        self.weight_level_1 = Conv(
            self.inter_dim, compress_c, 1, 1)
        self.weight_level_2 = Conv(
            self.inter_dim, compress_c, 1, 1)

        self.weight_levels = Conv(
            compress_c*3, 3, 1, 1)
        self.vis = vis

    def forward(self, x): #l,m,s
        """
        # 128, 256, 512
        512, 256, 128
        from small -> large
        """
        x_level_0=x[2] #l
        x_level_1=x[1] #m
        x_level_2=x[0] #s
        # print('x_level_0: ', x_level_0.shape)
        # print('x_level_1: ', x_level_1.shape)
        # print('x_level_2: ', x_level_2.shape)
        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')
            x_level_1_compressed = self.compress_level_1(x_level_1)
            level_1_resized = F.interpolate(
                x_level_1_compressed, scale_factor=2, mode='nearest')
            level_2_resized = x_level_2

        # print('level: {}, l1_resized: {}, l2_resized: {}'.format(self.level,
        #      level_1_resized.shape, level_2_resized.shape))
        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)
        # print('level_0_weight_v: ', level_0_weight_v.shape)
        # print('level_1_weight_v: ', level_1_weight_v.shape)
        # print('level_2_weight_v: ', level_2_weight_v.shape)

        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 
class ASFF_Detect(nn.Module):   #add ASFFV5 layer and Rfb 
    stride = None  # strides computed during build
    onnx_dynamic = False  # ONNX export parameter
    export = False  # export mode

    def __init__(self, nc=80, anchors=(), ch=(), multiplier=0.5,rfb=False,inplace=True):  # detection layer
        super().__init__()
        self.nc = nc  # number of classes
        self.no = nc + 5  # number of outputs per anchor
        self.nl = len(anchors)  # number of detection layers
        self.na = len(anchors[0]) // 2  # number of anchors
        self.grid = [torch.zeros(1)] * self.nl  # init grid
        self.l0_fusion = ASFFV5(level=0, multiplier=multiplier,rfb=rfb)
        self.l1_fusion = ASFFV5(level=1, multiplier=multiplier,rfb=rfb)
        self.l2_fusion = ASFFV5(level=2, multiplier=multiplier,rfb=rfb)
        self.anchor_grid = [torch.zeros(1)] * self.nl  # init anchor grid
        self.register_buffer('anchors', torch.tensor(anchors).float().view(self.nl, -1, 2))  # shape(nl,na,2)
        self.m = nn.ModuleList(nn.Conv2d(x, self.no * self.na, 1) for x in ch)  # output conv
        self.inplace = inplace  # use in-place ops (e.g. slice assignment)

    def forward(self, x):
        z = []  # inference output
        result=[]
       
        result.append(self.l2_fusion(x))
        result.append(self.l1_fusion(x))
        result.append(self.l0_fusion(x))
        x=result      
        for i in range(self.nl):
            x[i] = self.m[i](x[i])  # conv
            bs, _, ny, nx = x[i].shape  # x(bs,255,20,20) to x(bs,3,20,20,85)
            x[i] = x[i].view(bs, self.na, self.no, ny, nx).permute(0, 1, 3, 4, 2).contiguous()

            if not self.training:  # inference
                if self.onnx_dynamic or self.grid[i].shape[2:4] != x[i].shape[2:4]:
                    self.grid[i], self.anchor_grid[i] = self._make_grid(nx, ny, i)

                y = x[i].sigmoid() # https://github.com/iscyy/yoloair
                if self.inplace:
                    y[..., 0:2] = (y[..., 0:2] * 2 + self.grid[i]) * self.stride[i]  # xy
                    y[..., 2:4] = (y[..., 2:4] * 2) ** 2 * self.anchor_grid[i]  # wh
                else:  # for YOLOv5 on AWS Inferentia https://github.com/ultralytics/yolov5/pull/2953
                    xy, wh, conf = y.split((2, 2, self.nc + 1), 4)  # y.tensor_split((2, 4, 5), 4)  # torch 1.8.0
                    xy = (xy * 2 + self.grid[i]) * self.stride[i]  # xy
                    wh = (wh * 2) ** 2 * self.anchor_grid[i]  # wh
                    y = torch.cat((xy, wh, conf), 4)
                z.append(y.view(bs, -1, self.no))

        return x if self.training else (torch.cat(z, 1),) if self.export else (torch.cat(z, 1), x)
    
    def _make_grid(self, nx=20, ny=20, i=0):
        d = self.anchors[i].device
        t = self.anchors[i].dtype
        shape = 1, self.na, ny, nx, 2  # grid shape
        y, x = torch.arange(ny, device=d, dtype=t), torch.arange(nx, device=d, dtype=t)
        if check_version(torch.__version__, '1.10.0'):  # torch>=1.10.0 meshgrid workaround for torch>=0.7 compatibility
            yv, xv = torch.meshgrid(y, x, indexing='ij')
        else:
            yv, xv = torch.meshgrid(y, x)
        grid = torch.stack((xv, yv), 2).expand(shape) - 0.5  # add grid offset, i.e. y = 2.0 * x - 0.5
        anchor_grid = (self.anchors[i] * self.stride[i]).view((1, self.na, 1, 1, 2)).expand(shape)
        #print(anchor_grid)
        return grid, anchor_grid

二、修改yolo.py

1）修改这部分，用下边的代码直接替换红框这行代码就行，注意看我代码所在的行数

if isinstance(m, (Detect, Segment,Decoupled_Detect,ASFF_Detect)):

2） 在这里添加红框中的代码

        if isinstance(m, Decoupled_Detect) or isinstance(m, ASFF_Detect):
            s = 256  # 2x min stride
            m.inplace = self.inplace
            m.stride = torch.tensor([s / x.shape[-2] for x in self.forward(torch.zeros(1, ch, s, s))])  # forward
            m.anchors /= m.stride.view(-1, 1, 1)
            check_anchor_order(m)
            self.stride = m.stride
            try:
                self._initialize_biases()  # only run once
                LOGGER.info('initialize_biases done')
            except:
                LOGGER.info('decoupled no biase ')

3）这里添加红框代码

        elif m is ASFF_Detect:
            args.append([ch[x] for x in f])
            if isinstance(args[1], int):  # number of anchors
                args[1] = [list(range(args[1] * 2))] * len(f)
        elif m is Decoupled_Detect:
            args.append([ch[x] for x in f])
            if isinstance(args[1], int):  # number of anchors
                args[1] = [list(range(args[1] * 2))] * len(f)

 三、配置文件

只需要更改最后一层的Detect，使用解耦头的时候用 Decoupled_Detect，使用ASFF的时候用ASFF_Detect

# 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, 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, Decoupled_Detect, [nc, anchors]],  # Detect(P3, P4, P5),解耦
  ]

我在电脑上可以运行，有什么错误可以在评论区指出