改进YOLOv5系列：增加Swin-Transformer小目标检测头

• 💡统一使用 YOLOv5 代码框架，结合不同模块来构建不同的YOLO目标检测模型。
• 🌟本项目包含大量的改进方式,降低改进难度,改进点包含【Backbone特征主干】、【Neck特征融合】、【Head检测头】、【注意力机制】、【IoU损失函数】、【NMS】、【Loss计算方式】、【自注意力机制】、【数据增强部分】、【标签分配策略】、【激活函数】等各个部分。

本篇是《增加一个Swin检测头结构🚀》的代码演示

最新创新点改进博客推荐

（🔥 博客内 附有多种模型改进方式，均适用于

YOLOv5系列

以及

YOLOv7系列

改进！！！）

• 💡🎈☁️：改进YOLOv7系列：首发最新结合多种X-Transformer结构新增小目标检测层，让YOLO目标检测任务中的小目标无处遁形
• 💡🎈☁️：改进YOLOv7系列：结合Adaptively Spatial Feature Fusion自适应空间特征融合结构，提高特征尺度不变性
• 💡🎈☁️：改进YOLOv5系列：首发结合最新Extended efficient Layer Aggregation Networks结构，高效的聚合网络设计，提升性能
• 💡🎈☁️：改进YOLOv7系列：首发结合最新CSPNeXt主干结构(适用YOLOv7)，高性能，低延时的单阶段目标检测器主干，通过COCO数据集验证高效涨点
• 💡🎈☁️：改进YOLOv7系列：最新结合DO-DConv卷积、Slim范式提高性能涨点，打造高性能检测器
• 💡🎈☁️：改进YOLOv7系列：结合最新即插即用的动态卷积ODConv
• 💡🎈☁️：改进YOLOv7系列：首发结合最新Transformer视觉模型MOAT结构：交替移动卷积和注意力带来强大的Transformer视觉模型，超强的提升
• 💡🎈☁️：改进YOLOv7系列：首发结合最新Centralized Feature Pyramid集中特征金字塔，通过COCO数据集验证强势涨点
• 💡🎈☁️：改进YOLOv7系列：首发结合 RepLKNet 构建 最新 RepLKDeXt 结构｜CVPR2022 超大卷积核, 越大越暴力,大到31x31, 涨点高效
• 💡🎈☁️：改进YOLOv5系列：4.YOLOv5_最新MobileOne结构换Backbone修改，超轻量型架构，移动端仅需1ms推理！苹果最新移动端高效主干网络
• 💡🎈☁️：改进YOLOv7系列：最新HorNet结合YOLOv7应用！ | 新增 HorBc结构，多种搭配，即插即用 | Backbone主干、递归门控卷积的高效高阶空间交互

文章目录

YOLOv5网络

1.YOLOv5s标准网络配置

# YOLOv5 🚀 by Ultralytics, 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, 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, Detect,[nc, anchors]],# Detect(P3, P4, P5)]

2.增加Swin Transformer小目标检测头配置

增加yolov5s6_swin.yaml文件

# YOLOv5 🚀 by Ultralytics, 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:-[19,27,44,40,38,94]# P3/8-[96,68,86,152,180,137]# P4/16-[140,301,303,264,238,542]# P5/32-[436,615,739,380,925,792]# P6/64# 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,[768,3,2]],# 7-P5/32[-1,3, C3,[768]],[-1,1, Conv,[1024,3,2]],# 9-P6/64[-1,3, C3,[1024]],[-1,1, SPPF,[1024,5]],# 11]# YOLOv5 v6.0 head
head:[[-1,1, Conv,[768,1,1]],[-1,1, nn.Upsample,[None,2,'nearest']],[[-1,8],1, Concat,[1]],# cat backbone P5[-1,3, C3,[768,False]],# 15[-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]],# 19[-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]],# 23 (P3/8-small)[-1,1, Conv,[256,3,2]],[[-1,20],1, Concat,[1]],# cat head P4[-1,3, C3,[512,False]],# 26 (P4/16-medium)[-1,1, Conv,[512,3,2]],[[-1,16],1, Concat,[1]],# cat head P5[-1,3, C3,[768,False]],# 29 (P5/32-large)[-1,1, Conv,[768,3,2]],[[-1,12],1, Concat,[1]],# cat head P6[-1,3, C3STR,[512]],# 32 (P6/64-xlarge)[[23,26,29,32],1, Detect,[nc, anchors]],# Detect(P3, P4, P5, P6)]

3.核心代码

参考本博主的这篇：👉改进YOLOv5系列：3.YOLOv5结合Swin Transformer结构，ICCV 2021最佳论文 使用 Shifted Windows 的分层视觉转换器
里面的common.py配置部分

classSwinTransformerBlock(nn.Module):def__init__(self, c1, c2, num_heads, num_layers, window_size=8):super().__init__()
        self.conv =Noneif c1 != c2:
            self.conv = Conv(c1, c2)# remove input_resolution
        self.blocks = nn.Sequential(*[SwinTransformerLayer(dim=c2, num_heads=num_heads, window_size=window_size,
                                 shift_size=0if(i %2==0)else window_size //2)for i inrange(num_layers)])defforward(self, x):if self.conv isnotNone:
            x = self.conv(x)
        x = self.blocks(x)return x
classWindowAttention(nn.Module):def__init__(self, dim, window_size, num_heads, qkv_bias=True, qk_scale=None, attn_drop=0., proj_drop=0.):super().__init__()
        self.dim = dim
        self.window_size = window_size  # Wh, Ww
        self.num_heads = num_heads
        head_dim = dim // num_heads
        self.scale = qk_scale or head_dim **-0.5# define a parameter table of relative position bias
        self.relative_position_bias_table = nn.Parameter(
            torch.zeros((2* window_size[0]-1)*(2* window_size[1]-1), num_heads))# 2*Wh-1 * 2*Ww-1, nH# get pair-wise relative position index for each token inside the window
        coords_h = torch.arange(self.window_size[0])
        coords_w = torch.arange(self.window_size[1])
        coords = torch.stack(torch.meshgrid([coords_h, coords_w]))# 2, Wh, Ww
        coords_flatten = torch.flatten(coords,1)# 2, Wh*Ww
        relative_coords = coords_flatten[:,:,None]- coords_flatten[:,None,:]# 2, Wh*Ww, Wh*Ww
        relative_coords = relative_coords.permute(1,2,0).contiguous()# Wh*Ww, Wh*Ww, 2
        relative_coords[:,:,0]+= self.window_size[0]-1# shift to start from 0
        relative_coords[:,:,1]+= self.window_size[1]-1
        relative_coords[:,:,0]*=2* self.window_size[1]-1
        relative_position_index = relative_coords.sum(-1)# Wh*Ww, Wh*Ww
        self.register_buffer("relative_position_index", relative_position_index)

        self.qkv = nn.Linear(dim, dim *3, bias=qkv_bias)
        self.attn_drop = nn.Dropout(attn_drop)
        self.proj = nn.Linear(dim, dim)
        self.proj_drop = nn.Dropout(proj_drop)

        nn.init.normal_(self.relative_position_bias_table, std=.02)
        self.softmax = nn.Softmax(dim=-1)defforward(self, x, mask=None):

        B_, N, C = x.shape
        qkv = self.qkv(x).reshape(B_, N,3, self.num_heads, C // self.num_heads).permute(2,0,3,1,4)
        q, k, v = qkv[0], qkv[1], qkv[2]# make torchscript happy (cannot use tensor as tuple)

        q = q * self.scale
        attn =(q @ k.transpose(-2,-1))

        relative_position_bias = self.relative_position_bias_table[self.relative_position_index.view(-1)].view(
            self.window_size[0]* self.window_size[1], self.window_size[0]* self.window_size[1],-1)# Wh*Ww,Wh*Ww,nH
        relative_position_bias = relative_position_bias.permute(2,0,1).contiguous()# nH, Wh*Ww, Wh*Ww
        attn = attn + relative_position_bias.unsqueeze(0)if mask isnotNone:
            nW = mask.shape[0]
            attn = attn.view(B_ // nW, nW, self.num_heads, N, N)+ mask.unsqueeze(1).unsqueeze(0)
            attn = attn.view(-1, self.num_heads, N, N)
            attn = self.softmax(attn)else:
            attn = self.softmax(attn)

        attn = self.attn_drop(attn)# print(attn.dtype, v.dtype)try:
            x =(attn @ v).transpose(1,2).reshape(B_, N, C)except:#print(attn.dtype, v.dtype)
            x =(attn.half() @ v).transpose(1,2).reshape(B_, N, C)
        x = self.proj(x)
        x = self.proj_drop(x)return x

classMlp(nn.Module):def__init__(self, in_features, hidden_features=None, out_features=None, act_layer=nn.SiLU, drop=0.):super().__init__()
        out_features = out_features or in_features
        hidden_features = hidden_features or in_features
        self.fc1 = nn.Linear(in_features, hidden_features)
        self.act = act_layer()
        self.fc2 = nn.Linear(hidden_features, out_features)
        self.drop = nn.Dropout(drop)defforward(self, x):
        x = self.fc1(x)
        x = self.act(x)
        x = self.drop(x)
        x = self.fc2(x)
        x = self.drop(x)return x

classSwinTransformerLayer(nn.Module):def__init__(self, dim, num_heads, window_size=8, shift_size=0,
                 mlp_ratio=4., qkv_bias=True, qk_scale=None, drop=0., attn_drop=0., drop_path=0.,
                 act_layer=nn.SiLU, norm_layer=nn.LayerNorm):super().__init__()
        self.dim = dim
        self.num_heads = num_heads
        self.window_size = window_size
        self.shift_size = shift_size
        self.mlp_ratio = mlp_ratio
        # if min(self.input_resolution) <= self.window_size:#     # if window size is larger than input resolution, we don't partition windows#     self.shift_size = 0#     self.window_size = min(self.input_resolution)assert0<= self.shift_size < self.window_size,"shift_size must in 0-window_size"

        self.norm1 = norm_layer(dim)
        self.attn = WindowAttention(
            dim, window_size=(self.window_size, self.window_size), num_heads=num_heads,
            qkv_bias=qkv_bias, qk_scale=qk_scale, attn_drop=attn_drop, proj_drop=drop)

        self.drop_path = DropPath(drop_path)if drop_path >0.else nn.Identity()
        self.norm2 = norm_layer(dim)
        mlp_hidden_dim =int(dim * mlp_ratio)
        self.mlp = Mlp(in_features=dim, hidden_features=mlp_hidden_dim, act_layer=act_layer, drop=drop)defcreate_mask(self, H, W):# calculate attention mask for SW-MSA
        img_mask = torch.zeros((1, H, W,1))# 1 H W 1
        h_slices =(slice(0,-self.window_size),slice(-self.window_size,-self.shift_size),slice(-self.shift_size,None))
        w_slices =(slice(0,-self.window_size),slice(-self.window_size,-self.shift_size),slice(-self.shift_size,None))
        cnt =0for h in h_slices:for w in w_slices:
                img_mask[:, h, w,:]= cnt
                cnt +=1

        mask_windows = window_partition(img_mask, self.window_size)# nW, window_size, window_size, 1
        mask_windows = mask_windows.view(-1, self.window_size * self.window_size)
        attn_mask = mask_windows.unsqueeze(1)- mask_windows.unsqueeze(2)
        attn_mask = attn_mask.masked_fill(attn_mask !=0,float(-100.0)).masked_fill(attn_mask ==0,float(0.0))return attn_mask

    defforward(self, x):# reshape x[b c h w] to x[b l c]
        _, _, H_, W_ = x.shape

        Padding =Falseifmin(H_, W_)< self.window_size or H_ % self.window_size!=0or W_ % self.window_size!=0:
            Padding =True# print(f'img_size {min(H_, W_)} is less than (or not divided by) window_size {self.window_size}, Padding.')
            pad_r =(self.window_size - W_ % self.window_size)% self.window_size
            pad_b =(self.window_size - H_ % self.window_size)% self.window_size
            x = F.pad(x,(0, pad_r,0, pad_b))# print('2', x.shape)
        B, C, H, W = x.shape
        L = H * W
        x = x.permute(0,2,3,1).contiguous().view(B, L, C)# b, L, c# create mask from init to forwardif self.shift_size >0:
            attn_mask = self.create_mask(H, W).to(x.device)else:
            attn_mask =None

        shortcut = x
        x = self.norm1(x)
        x = x.view(B, H, W, C)# cyclic shiftif self.shift_size >0:
            shifted_x = torch.roll(x, shifts=(-self.shift_size,-self.shift_size), dims=(1,2))else:
            shifted_x = x

        # partition windows
        x_windows = window_partition(shifted_x, self.window_size)# nW*B, window_size, window_size, C
        x_windows = x_windows.view(-1, self.window_size * self.window_size, C)# nW*B, window_size*window_size, C# W-MSA/SW-MSA
        attn_windows = self.attn(x_windows, mask=attn_mask)# nW*B, window_size*window_size, C# merge windows
        attn_windows = attn_windows.view(-1, self.window_size, self.window_size, C)
        shifted_x = window_reverse(attn_windows, self.window_size, H, W)# B H' W' C# reverse cyclic shiftif self.shift_size >0:
            x = torch.roll(shifted_x, shifts=(self.shift_size, self.shift_size), dims=(1,2))else:
            x = shifted_x
        x = x.view(B, H * W, C)# FFN
        x = shortcut + self.drop_path(x)
        x = x + self.drop_path(self.mlp(self.norm2(x)))

        x = x.permute(0,2,1).contiguous().view(-1, C, H, W)# b c h wif Padding:
            x = x[:,:,:H_,:W_]# reverse paddingreturn x

classC3STR(C3):# C3 module with SwinTransformerBlock()def__init__(self, c1, c2, n=1, shortcut=True, g=1, e=0.5):super().__init__(c1, c2, c2, n, shortcut, g, e)
        c_ =int(c2 * e)
        num_heads = c_ //32
        self.m = SwinTransformerBlock(c_, c_, num_heads, n)

4.运行

python train.py --cfg yolov5s6_swin.yaml