YOLOv5与Swin-Transformer的结合

Swin-Transformer在计算机视觉的各个下游任务上都取得了很好的效果，而YOLO系列（尤其是v5、v7、v8）更是目标检测领域的最常见的检测器。本文将YOLOv5的骨干提取网络换成Swin-Transformer（v7/v8同样）。

Swin-Transformer的详细了解可参考朱老师的Swin-Transformer论文精读和b站大佬霹雳吧啦的网络结构解读。

更换教程(基于官方ultralytics代码实现)

在yolov5/models文件夹下，新建swintransformer.py,将下述实现Swin-Transformer的代码拷贝进去（https://github.com/microsoft/Swin-Transformer）

import torch
import torch.nn as nn
import torch.nn.functional as F
import torch.utils.checkpoint as checkpoint
import numpy as np
from typing import Optional


def drop_path_f(x, drop_prob: float = 0., training: bool = False):
    """Drop paths (Stochastic Depth) per sample (when applied in main path of residual blocks).
    This is the same as the DropConnect impl I created for EfficientNet, etc networks, however,
    the original name is misleading as 'Drop Connect' is a different form of dropout in a separate paper...
    See discussion: https://github.com/tensorflow/tpu/issues/494#issuecomment-532968956 ... I've opted for
    changing the layer and argument names to 'drop path' rather than mix DropConnect as a layer name and use
    'survival rate' as the argument.
    """
    if drop_prob == 0. or not training:
        return x
    keep_prob = 1 - drop_prob
    shape = (x.shape[0],) + (1,) * (x.ndim - 1)  # work with diff dim tensors, not just 2D ConvNets
    random_tensor = keep_prob + torch.rand(shape, dtype=x.dtype, device=x.device)
    random_tensor.floor_()  # binarize
    output = x.div(keep_prob) * random_tensor
    return output


class DropPath(nn.Module):
    """Drop paths (Stochastic Depth) per sample  (when applied in main path of residual blocks).
    """
    def __init__(self, drop_prob=None):
        super(DropPath, self).__init__()
        self.drop_prob = drop_prob

    def forward(self, x):
        return drop_path_f(x, self.drop_prob, self.training)


def window_partition(x, window_size: int):
    """
    将feature map按照window_size划分成一个个没有重叠的window
    Args:
        x: (B, H, W, C)
        window_size (int): window size(M)
    Returns:
        windows: (num_windows*B, window_size, window_size, C)
    """
    B, H, W, C = x.shape
    x = x.view(B, H // window_size, window_size, W // window_size, window_size, C)
    # permute: [B, H//Mh, Mh, W//Mw, Mw, C] -> [B, H//Mh, W//Mh, Mw, Mw, C]
    # view: [B, H//Mh, W//Mw, Mh, Mw, C] -> [B*num_windows, Mh, Mw, C]
    windows = x.permute(0, 1, 3, 2, 4, 5).contiguous().view(-1, window_size, window_size, C)
    return windows


def window_reverse(windows, window_size: int, H: int, W: int):
    """
    将一个个window还原成一个feature map
    Args:
        windows: (num_windows*B, window_size, window_size, C)
        window_size (int): Window size(M)
        H (int): Height of image
        W (int): Width of image
    Returns:
        x: (B, H, W, C)
    """
    B = int(windows.shape[0] / (H * W / window_size / window_size))
    # view: [B*num_windows, Mh, Mw, C] -> [B, H//Mh, W//Mw, Mh, Mw, C]
    x = windows.view(B, H // window_size, W // window_size, window_size, window_size, -1)
    # permute: [B, H//Mh, W//Mw, Mh, Mw, C] -> [B, H//Mh, Mh, W//Mw, Mw, C]
    # view: [B, H//Mh, Mh, W//Mw, Mw, C] -> [B, H, W, C]
    x = x.permute(0, 1, 3, 2, 4, 5).contiguous().view(B, H, W, -1)
    return x


class Mlp(nn.Module):
    """ MLP as used in Vision Transformer, MLP-Mixer and related networks
    """
    def __init__(self, in_features, hidden_features=None, out_features=None, act_layer=nn.GELU, 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.drop1 = nn.Dropout(drop)
        self.fc2 = nn.Linear(hidden_features, out_features)
        self.drop2 = nn.Dropout(drop)

    def forward(self, x):
        x = self.fc1(x)
        x = self.act(x)
        x = self.drop1(x)
        x = self.fc2(x)
        x = self.drop2(x)
        return x


class WindowAttention(nn.Module):
    r""" Window based multi-head self attention (W-MSA) module with relative position bias.
    It supports both of shifted and non-shifted window.
    Args:
        dim (int): Number of input channels.
        window_size (tuple[int]): The height and width of the window.
        num_heads (int): Number of attention heads.
        qkv_bias (bool, optional):  If True, add a learnable bias to query, key, value. Default: True
        attn_drop (float, optional): Dropout ratio of attention weight. Default: 0.0
        proj_drop (float, optional): Dropout ratio of output. Default: 0.0
    """

    def __init__(self, dim, window_size, num_heads, qkv_bias=True, attn_drop=0., proj_drop=0.):

        super().__init__()
        self.dim = dim
        self.window_size = window_size  # [Mh, Mw]
        self.num_heads = num_heads
        head_dim = dim // num_heads
        self.scale = 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*Mh-1 * 2*Mw-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, Mh, Mw]
        coords_flatten = torch.flatten(coords, 1)  # [2, Mh*Mw]
        # [2, Mh*Mw, 1] - [2, 1, Mh*Mw]
        relative_coords = coords_flatten[:, :, None] - coords_flatten[:, None, :]  # [2, Mh*Mw, Mh*Mw]
        relative_coords = relative_coords.permute(1, 2, 0).contiguous()  # [Mh*Mw, Mh*Mw, 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)  # [Mh*Mw, Mh*Mw]
        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.trunc_normal_(self.relative_position_bias_table, std=.02)
        self.softmax = nn.Softmax(dim=-1)

    def forward(self, x, mask: Optional[torch.Tensor] = None):
        """
        Args:
            x: input features with shape of (num_windows*B, Mh*Mw, C)
            mask: (0/-inf) mask with shape of (num_windows, Wh*Ww, Wh*Ww) or None
        """
        # [batch_size*num_windows, Mh*Mw, total_embed_dim]
        B_, N, C = x.shape
        # qkv(): -> [batch_size*num_windows, Mh*Mw, 3 * total_embed_dim]
        # reshape: -> [batch_size*num_windows, Mh*Mw, 3, num_heads, embed_dim_per_head]
        # permute: -> [3, batch_size*num_windows, num_heads, Mh*Mw, embed_dim_per_head]
        qkv = self.qkv(x).reshape(B_, N, 3, self.num_heads, C // self.num_heads).permute(2, 0, 3, 1, 4).contiguous()
        # [batch_size*num_windows, num_heads, Mh*Mw, embed_dim_per_head]
        q, k, v = qkv.unbind(0)  # make torchscript happy (cannot use tensor as tuple)

        # transpose: -> [batch_size*num_windows, num_heads, embed_dim_per_head, Mh*Mw]
        # @: multiply -> [batch_size*num_windows, num_heads, Mh*Mw, Mh*Mw]
        q = q * self.scale
        attn = (q @ k.transpose(-2, -1))

        # relative_position_bias_table.view: [Mh*Mw*Mh*Mw,nH] -> [Mh*Mw,Mh*Mw,nH]
        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)
        relative_position_bias = relative_position_bias.permute(2, 0, 1).contiguous()  # [nH, Mh*Mw, Mh*Mw]
        attn = attn + relative_position_bias.unsqueeze(0)

        if mask is not None:
            # mask: [nW, Mh*Mw, Mh*Mw]
            nW = mask.shape[0]  # num_windows
            # attn.view: [batch_size, num_windows, num_heads, Mh*Mw, Mh*Mw]
            # mask.unsqueeze: [1, nW, 1, Mh*Mw, Mh*Mw]
            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)

        # @: multiply -> [batch_size*num_windows, num_heads, Mh*Mw, embed_dim_per_head]
        # transpose: -> [batch_size*num_windows, Mh*Mw, num_heads, embed_dim_per_head]
        # reshape: -> [batch_size*num_windows, Mh*Mw, total_embed_dim]
        x = (attn @ v).transpose(1, 2).reshape(B_, N, C).to(torch.float)
        x = self.proj(x)
        x = self.proj_drop(x)
        return x


class SwinTransformerBlock(nn.Module):
    r""" Swin Transformer Block.
    Args:
        dim (int): Number of input channels.
        num_heads (int): Number of attention heads.
        window_size (int): Window size.
        shift_size (int): Shift size for SW-MSA.
        mlp_ratio (float): Ratio of mlp hidden dim to embedding dim.
        qkv_bias (bool, optional): If True, add a learnable bias to query, key, value. Default: True
        drop (float, optional): Dropout rate. Default: 0.0
        attn_drop (float, optional): Attention dropout rate. Default: 0.0
        drop_path (float, optional): Stochastic depth rate. Default: 0.0
        act_layer (nn.Module, optional): Activation layer. Default: nn.GELU
        norm_layer (nn.Module, optional): Normalization layer.  Default: nn.LayerNorm
    """

    def __init__(self, dim, num_heads, window_size=7, shift_size=0,
                 mlp_ratio=4., qkv_bias=True, drop=0., attn_drop=0., drop_path=0.,
                 act_layer=nn.GELU, 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
        assert 0 <= 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,
            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)

    def forward(self, x, attn_mask):
        H, W = self.H, self.W
        B, L, C = x.shape
        assert L == H * W, "input feature has wrong size"

        shortcut = x
        x = self.norm1(x)
        x = x.view(B, H, W, C)

        # pad feature maps to multiples of window size
        # 把feature map给pad到window size的整数倍
        pad_l = pad_t = 0
        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, 0, pad_l, pad_r, pad_t, pad_b))
        _, Hp, Wp, _ = x.shape

        # cyclic shift
        if self.shift_size > 0:
            shifted_x = torch.roll(x, shifts=(-self.shift_size, -self.shift_size), dims=(1, 2))
        else:
            shifted_x = x
            attn_mask = None

        # partition windows
        x_windows = window_partition(shifted_x, self.window_size)  # [nW*B, Mh, Mw, C]
        x_windows = x_windows.view(-1, self.window_size * self.window_size, C)  # [nW*B, Mh*Mw, C]

        # W-MSA/SW-MSA
        attn_windows = self.attn(x_windows, mask=attn_mask)  # [nW*B, Mh*Mw, C]

        # merge windows
        attn_windows = attn_windows.view(-1, self.window_size, self.window_size, C)  # [nW*B, Mh, Mw, C]
        shifted_x = window_reverse(attn_windows, self.window_size, Hp, Wp)  # [B, H', W', C]

        # reverse cyclic shift
        if self.shift_size > 0:
            x = torch.roll(shifted_x, shifts=(self.shift_size, self.shift_size), dims=(1, 2))
        else:
            x = shifted_x

        if pad_r > 0 or pad_b > 0:
            # 把前面pad的数据移除掉
            x = x[:, :H, :W, :].contiguous()

        x = x.view(B, H * W, C)

        # FFN
        x = shortcut + self.drop_path(x)
        x = x + self.drop_path(self.mlp(self.norm2(x)))

        return x


class SwinStage(nn.Module):
    """
    A basic Swin Transformer layer for one stage.
    Args:
        dim (int): Number of input channels.
        depth (int): Number of blocks.
        num_heads (int): Number of attention heads.
        window_size (int): Local window size.
        mlp_ratio (float): Ratio of mlp hidden dim to embedding dim.
        qkv_bias (bool, optional): If True, add a learnable bias to query, key, value. Default: True
        drop (float, optional): Dropout rate. Default: 0.0
        attn_drop (float, optional): Attention dropout rate. Default: 0.0
        drop_path (float | tuple[float], optional): Stochastic depth rate. Default: 0.0
        norm_layer (nn.Module, optional): Normalization layer. Default: nn.LayerNorm
        downsample (nn.Module | None, optional): Downsample layer at the end of the layer. Default: None
        use_checkpoint (bool): Whether to use checkpointing to save memory. Default: False.
    """

    def __init__(self, dim, c2, depth, num_heads, window_size,
                 mlp_ratio=4., qkv_bias=True, drop=0., attn_drop=0.,
                 drop_path=0., norm_layer=nn.LayerNorm, use_checkpoint=False):
        super().__init__()
        assert dim==c2, r"no. in/out channel should be same"
        self.dim = dim
        self.depth = depth
        self.window_size = window_size
        self.use_checkpoint = use_checkpoint
        self.shift_size = window_size // 2

        # build blocks
        self.blocks = nn.ModuleList([
            SwinTransformerBlock(
                dim=dim,
                num_heads=num_heads,
                window_size=window_size,
                shift_size=0 if (i % 2 == 0) else self.shift_size,
                mlp_ratio=mlp_ratio,
                qkv_bias=qkv_bias,
                drop=drop,
                attn_drop=attn_drop,
                drop_path=drop_path[i] if isinstance(drop_path, list) else drop_path,
                norm_layer=norm_layer)
            for i in range(depth)])


    def create_mask(self, x, H, W):
        # calculate attention mask for SW-MSA
        # 保证Hp和Wp是window_size的整数倍
        Hp = int(np.ceil(H / self.window_size)) * self.window_size
        Wp = int(np.ceil(W / self.window_size)) * self.window_size
        # 拥有和feature map一样的通道排列顺序，方便后续window_partition
        img_mask = torch.zeros((1, Hp, Wp, 1), device=x.device)  # [1, Hp, Wp, 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 = 0
        for 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, Mh, Mw, 1]
        mask_windows = mask_windows.view(-1, self.window_size * self.window_size)  # [nW, Mh*Mw]
        attn_mask = mask_windows.unsqueeze(1) - mask_windows.unsqueeze(2)  # [nW, 1, Mh*Mw] - [nW, Mh*Mw, 1]
        # [nW, Mh*Mw, Mh*Mw]
        attn_mask = attn_mask.masked_fill(attn_mask != 0, float(-100.0)).masked_fill(attn_mask == 0, float(0.0))
        return attn_mask

    def forward(self, x):
        B, C, H, W = x.shape
        x = x.permute(0, 2, 3, 1).contiguous().view(B, H*W, C)
        attn_mask = self.create_mask(x, H, W)  # [nW, Mh*Mw, Mh*Mw]
        for blk in self.blocks:
            blk.H, blk.W = H, W
            if not torch.jit.is_scripting() and self.use_checkpoint:
                x = checkpoint.checkpoint(blk, x, attn_mask)
            else:
                x = blk(x, attn_mask)

        x = x.view(B, H, W, C)
        x = x.permute(0, 3, 1, 2).contiguous()

        return x


class PatchEmbed(nn.Module):
    """
    2D Image to Patch Embedding
    """
    def __init__(self, in_c=3, embed_dim=96, patch_size=4, norm_layer=None):
        super().__init__()
        patch_size = (patch_size, patch_size)
        self.patch_size = patch_size
        self.in_chans = in_c
        self.embed_dim = embed_dim
        self.proj = nn.Conv2d(in_c, embed_dim, kernel_size=patch_size, stride=patch_size)
        self.norm = norm_layer(embed_dim) if norm_layer else nn.Identity()

    def forward(self, x):
        _, _, H, W = x.shape

        # padding
        # 如果输入图片的H，W不是patch_size的整数倍，需要进行padding
        pad_input = (H % self.patch_size[0] != 0) or (W % self.patch_size[1] != 0)
        if pad_input:
            # to pad the last 3 dimensions,
            # (W_left, W_right, H_top,H_bottom, C_front, C_back)
            x = F.pad(x, (0, self.patch_size[1] - W % self.patch_size[1],
                          0, self.patch_size[0] - H % self.patch_size[0],
                          0, 0))

        # 下采样patch_size倍
        x = self.proj(x)
        B, C, H, W = x.shape
        # flatten: [B, C, H, W] -> [B, C, HW]
        # transpose: [B, C, HW] -> [B, HW, C]
        x = x.flatten(2).transpose(1, 2)
        x = self.norm(x)
        # view: [B, HW, C] -> [B, H, W, C]
        # permute: [B, H, W, C] -> [B, C, H, W]
        x = x.view(B, H, W, C)
        x = x.permute(0, 3, 1, 2).contiguous()
        return x


class PatchMerging(nn.Module):
    r""" Patch Merging Layer.
    Args:
        dim (int): Number of input channels.
        norm_layer (nn.Module, optional): Normalization layer.  Default: nn.LayerNorm
    """

    def __init__(self, dim, c2, norm_layer=nn.LayerNorm):
        super().__init__()
        assert c2==(2 * dim), r"no. out channel should be 2 * no. in channel "
        self.dim = dim
        self.reduction = nn.Linear(4 * dim, 2 * dim, bias=False)
        self.norm = norm_layer(4 * dim)

    def forward(self, x):
        """
        x: B, C, H, W
        """
        B, C, H, W = x.shape
        # assert L == H * W, "input feature has wrong size"
        x = x.permute(0, 2, 3, 1).contiguous()
        # x = x.view(B, H*W, C)

        # padding
        # 如果输入feature map的H，W不是2的整数倍，需要进行padding
        pad_input = (H % 2 == 1) or (W % 2 == 1)
        if pad_input:
            # to pad the last 3 dimensions, starting from the last dimension and moving forward.
            # (C_front, C_back, W_left, W_right, H_top, H_bottom)
            # 注意这里的Tensor通道是[B, H, W, C]，所以会和官方文档有些不同
            x = F.pad(x, (0, 0, 0, W % 2, 0, H % 2))

        x0 = x[:, 0::2, 0::2, :]  # [B, H/2, W/2, C]
        x1 = x[:, 1::2, 0::2, :]  # [B, H/2, W/2, C]
        x2 = x[:, 0::2, 1::2, :]  # [B, H/2, W/2, C]
        x3 = x[:, 1::2, 1::2, :]  # [B, H/2, W/2, C]
        x = torch.cat([x0, x1, x2, x3], -1)  # [B, H/2, W/2, 4*C]
        x = x.view(B, -1, 4 * C)  # [B, H/2*W/2, 4*C]

        x = self.norm(x)
        x = self.reduction(x)  # [B, H/2*W/2, 2*C]
        x = x.view(B, int(H/2), int(W/2), C*2)
        x = x.permute(0, 3, 1, 2).contiguous()
        return x

接着在models/yolo.py中导入相关模块

from models.swintransformer import SwinStage, PatchMerging, PatchEmbed

在 models/yolo.py的318行左右还需要插入相关模块

 （注意，除了新建swintransformer.py外，还可以将Swin-Transformer的代码全部拷贝到models/common.py中，此时不需要在yolo.py中导入相关模块，源代码中common.py已经由"from models.common import * " 全部导入）

然后配置自己的yaml文件，我们直接在yolov5l.yaml中配置

# YOLOv5  by Ultralytics, GPL-3.0 license

# Parameters
nc: 6  # number of classes
depth_multiple: 1  # model depth multiple
width_multiple: 1  # layer channel multiple
anchors:
  - [19,14, 32,42, 190,16]  # P3/8
  - [59,57, 45,105, 408,15]  # P4/16
  - [65,155, 117,161, 252,153]  # 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)
#  ]
#backbone shuffle
#backbone:
#  # [from, number, module, args]
#  [[-1, 1, CBRM, [32]],  # 0-P1/4
#   [-1, 1, Shuffle_Block, [128, 2]],  # 1-P2/8
#   [-1, 3, Shuffle_Block, [128, 1]],
#   [-1, 1, Shuffle_Block, [256, 2]],  # 3-P3/16
#   [-1, 7, Shuffle_Block, [256, 1]],
#   [-1, 1, Shuffle_Block, [512, 2]],  # 5-P4/32
#   [-1, 3, Shuffle_Block, [512, 1]],
#  ]
#
## YOLOv5 v6.0 head
#head:
#  [[-1, 1, Conv, [256, 1, 1]],
#   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
#   [[-1, 4], 1, Concat, [1]],  # cat backbone P4
#   [-1, 1, C2f, [256, False]],  # 10
#
#   [-1, 1, Conv, [128, 1, 1]],
#   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
#   [[-1, 2], 1, Concat, [1]],  # cat backbone P3
#   [-1, 1, C2f, [128, False]],  # 14 (P3/8-small)
#
#   [-1, 1, Conv, [128, 3, 2]],
#   [[-1, 11], 1, Concat, [1]],  # cat head P4
#   [-1, 1, C2f, [256, False]],  # 17 (P4/16-medium)
#
#   [-1, 1, Conv, [256, 3, 2]],
#   [[-1, 7], 1, Concat, [1]],  # cat head P5
#   [-1, 1, C2f, [512, False]],  # 20 (P5/32-large)
#
#   [[14, 17, 20], 1, Detect, [nc, anchors]],  # Detect(P3, P4, P5)
#  ]

##backbone shuffle SE
#backbone:
#  # [from, number, module, args]
#  [[-1, 1, CBRM, [32]],  # 0-P1/4
#   [-1, 1, Shuffle_Block, [128, 2]],  # 1-P2/8
#   [-1, 3, Shuffle_Block, [128, 1]],
#   [-1, 1, Shuffle_Block, [256, 2]],  # 3-P3/16
#   [-1, 7, Shuffle_Block, [256, 1]],
#   [-1, 1, Shuffle_Block, [512, 2]],  # 5-P4/32
#   [-1, 3, Shuffle_Block, [512, 1]],
#  ]
#
## YOLOv5 v6.0 head
#head:
#  [[-1, 1, Conv, [256, 1, 1]],
#   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
#   [[-1, 4], 1, Concat, [1]],  # cat backbone P4
#   [-1, 1, CoordAtt, [512]],
#   [-1, 1, C2f, [256, False]],  # 10
#
#   [-1, 1, Conv, [128, 1, 1]],
#   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
#   [[-1, 2], 1, Concat, [1]],  # cat backbone P3
#   [-1, 1, CoordAtt, [256]],
#   [-1, 1, C2f, [128, False]],  # 14 (P3/8-small)
#
#   [-1, 1, Conv, [128, 3, 2]],
#   [[-1, 12], 1, Concat, [1]],  # cat head P4
#   [-1, 1, CoordAtt, [256]],
#   [-1, 1, C2f, [256, False]],  # 17 (P4/16-medium)
#
#   [-1, 1, Conv, [256, 3, 2]],
#   [[-1, 7], 1, Concat, [1]],  # cat head P5
#   [-1, 1, CoordAtt, [512]],
#   [-1, 1, C2f, [512, False]],  # 20 (P5/32-large)
#
#   [[16, 20, 24], 1, Detect, [nc, anchors]],  # Detect(P3, P4, P5)
#  ]


# Swin-Transformer-Tiny backbone
backbone:
  # [from, number, module, args]
  # input [b, 1, 640, 640]
  [[-1, 1, PatchEmbed, [96, 4]],  # 0 [b, 96, 160, 160]
   [-1, 1, SwinStage, [96, 2, 3, 7]],  # 1 [b, 96, 160, 160]
   [-1, 1, PatchMerging, [192]],    # 2 [b, 192, 80, 80]
   [-1, 1, SwinStage, [192, 2, 6, 7]],  # 3 --F0-- [b, 192, 80, 80]
   [ -1, 1, PatchMerging, [384]],   # 4 [b, 384, 40, 40]
   [ -1, 1, SwinStage, [384, 6, 12, 7]], # 5 --F1-- [b, 384, 40, 40]
   [ -1, 1, PatchMerging, [768]],   # 6 [b, 768, 20, 20]
   [ -1, 1, SwinStage, [768, 2, 24, 7]], # 7 --F2-- [b, 768, 20, 20]
  ]

# YOLOv5 v6.0 head
head:
  [[-1, 1, Conv, [512, 1, 1]],
   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
   [[-1, 5], 1, Concat, [1]],  # cat backbone P4
   [-1, 3, C3, [512, False]],  # 11

   [-1, 1, Conv, [256, 1, 1]],
   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
   [[-1, 3], 1, Concat, [1]],  # cat backbone P3
   [-1, 3, C3, [256, False]],  # 15 (P3/8-small)

   [-1, 1, Conv, [256, 3, 2]],
   [[-1, 12], 1, Concat, [1]],  # cat head P4
   [-1, 3, C3, [512, False]],  # 18 (P4/16-medium)

   [-1, 1, Conv, [512, 3, 2]],
   [[-1, 8], 1, Concat, [1]],  # cat head P5
   [-1, 3, C3, [1024, False]],  # 21 (P5/32-large)

   [[15, 18, 21], 1, Detect, [nc, anchors]],  # Detect(P3, P4, P5)
  ]

在backbone中，参数[from, number, module, args]分别表示：

• from-该层的输入来自哪一层，（从0开始编号），-1表示来自上一层
• number-该层的重复次数
• module-当前使用模块名称
• args-模块的参数

对于SwinStage模块参数如下

 yaml文件中的[-1, 1, SwinStage, [96, 2, 3, 7]]表示：

• -1-输入来自上一层
• 1-SwinStage重复1次
• SwinStage-使用的模块
• [96, 2, 3, 7]-分别代表输入通道dim之后的c2,depth,num_heads,window_size

对于PatchMerging模块参数如下：

 yaml文件中的[-1, 1, PatchMerging, [192]]中的192代表dim后面的c2

打印模型

 运行models/yolo.py，将yaml文件换为更改的yolov5l.yaml,打印模型的信息

 训练过程与原始YOLOv5的训练过程相同，不在赘述。下面是可能遇到的一些错误

错误1：

TypeError: meshgrid() got an unexpected keyword argument ‘indexing‘

torch版本原因，解决办法

coords = torch.stack(torch.meshgrid([coords_h, coords_w]),indexing="ij")#原先代码
coords = torch.stack(torch.meshgrid([coords_h, coords_w]))#删除indexing="ij"

错误2：

RuntimeError: expected scalar type Half but found Float

训练过程val阶段会使用half评估，把train.py里面353行的half=amp改成half=False，这样就可以训练起来了。训练结束后还有一次验证，把414行的half()去掉。

 

网络结构图