一、本文介绍
随着Transformer架构在自然语言处理领域取得巨大成功，其强大的全局上下文建模能力也开始渗透到视觉领域。Vision Transformer (ViT) 及其衍生模型的出现，证明了Transformer在图像识别任务上超越传统卷积神经网络(CNN)的潜力。
然而，标准的ViT模型存在计算复杂度高、缺乏归纳偏置以及难以直接生成多尺度特征图等问题，使其难以直接作为YOLO等密集预测任务的骨干网络(Backbone)。Swin Transformer的提出巧妙地解决了这些问题，它通过引入移位窗口（Shifted Window） 机制，在实现高效计算的同时，构建了类似CNN的金字塔式层次化特征结构，使其成为替代CNN骨干网络的理想选择。
目录
2.2 解决方案：Swin Transformer的核心创新
2.2.1 层次化架构（Hierarchical Architecture）
2.2.2 基于移位窗口的自注意力（Shifted Window based Self-Attention）
二、Swin Transformer模型设计
论文： https://arxiv.org/pdf/2103.14030.pdf
源码： https://github.com/microsoft/Swin-Transformer
2.1 要解决什么问题？（动机）
在Swin Transformer之前，Vision Transformer (ViT) 已经展示了Transformer在图像分类上的强大能力。但ViT有两个主要缺陷，使其难以直接应用于密集预测任务（如目标检测、语义分割）：
-
计算复杂度高：ViT对所有图像块（patches）进行全局自注意力计算，其计算复杂度是图像块数量的平方（O(n²)）。对于高分辨率图像，计算量会变得无法承受。
-
缺乏层次化结构：ViT从输入到输出始终保持单一尺度的特征图，缺乏CNN那种随着网络加深，特征图尺寸逐渐减小、通道数逐渐增多的金字塔特征层次。而这种结构对处理多尺度目标（如大小不同的物体）至关重要。
Swin Transformer的目标就是设计一个既是Transformer（性能强）又像CNN（通用、高效）的骨干网络。
2.2 解决方案：Swin Transformer的核心创新
2.2.1 层次化架构（Hierarchical Architecture）
Swin Transformer模仿CNN，构建了逐步降采样、增加通道数的金字塔结构。
-
Stage 1:
-
输入图片（H×W×3）被分割成不重叠的4×4 patches（ViT是16×16）。更大的patch尺寸允许更精细的初始表示。
-
通过
Patch Partition和Linear Embedding后，特征图变为 (H/4 × W/4 × C)。
-
-
Stage 2, 3, 4:
-
每个阶段开始时，通过
Patch Merging层进行降采样和增维。它将相邻2x2的小patch的特征拼接起来，然后通过一个线性层将通道数从4C投影到2C。这样，特征图尺寸减半（分辨率变为1/2），通道数翻倍。 -
经过几个阶段后，特征图尺度分别为 H/8 × W/8 × 2C, H/16 × W/16 × 4C, H/32 × W/32 × 8C。这为下游任务提供了多尺度特征图。
-
2.2.2 基于移位窗口的自注意力（Shifted Window based Self-Attention）
这是Swin Transformer最核心、最巧妙的创新，解决了全局自注意力计算量大的问题。
-
非重叠窗口自注意力（W-MSA）:
-
不像ViT那样做全局计算，Swin Transformer将特征图划分成多个不重叠的局部窗口（如每个窗口包含7x7个patches）。
-
自注意力计算只在每个窗口内部独立进行。
-
复杂度分析：
-
对于一张有h × w个patches的图，每个窗口有M×M个patches。
-
全局MSA复杂度：
O((h*w)^2) -
窗口MSA复杂度：
O((h*w) * M^2)。由于M是固定值（如7），复杂度变为线性于图像尺寸！计算量大幅降低。
-
-
-
移位窗口自注意力（SW-MSA）:
-
问题：如果一直只在固定的窗口内计算，窗口之间没有信息交流，模型感受野受限，无法建立全局依赖关系。
-
解决方案：Swin Transformer在连续的两个Transformer块中交替使用两种窗口划分配置。
-
第L层使用规则窗口划分。
-
第L+1层使用移位窗口划分，即将窗口向右和下各循环移位
⌊M/2⌋个像素。
-
-
- 效果：移位后的新窗口由上一层中不同窗口的子块组成，从而实现了跨窗口的信息交互，极大地增强了模型的建模能力，而计算成本与W-MSA完全相同。
-
高效计算：循环移位与掩码机制
-
直接实现移位会产生几个大小不一的窗口（如图中最右边），不利于批量计算。
-
论文采用了一种巧妙的循环移位（Cyclic Shift） 方法，将移位后左上、右上、左下三个区域的窗口拼接到右下角，从而得到9个大小相同的窗口（都是MxM）。
-
然后使用注意力掩码（Attention Mask） 来防止不相邻区域之间进行不应该有的注意力计算。计算完注意力后再反向循环移位回去，恢复原来的空间关系。这个过程对用户是透明的。
-
2.3 Swin Transformer模块
2.4 核心优势与实验结果
-
性能卓越：
-
图像分类：在ImageNet-1K上，Swin-T (29M params) 达到81.3%的top-1准确率，超越了同等规模的RegNet和EffNet。
-
目标检测与分割：在COCO数据集上，Swin-L在目标检测 (58.7 box AP) 和实例分割 (51.1 mask AP) 上刷新了记录，显著超越了之前的所有CNN和Transformer模型。
-
-
通用性强：
-
其层次化输出使其可以直接替换任何CNN骨干网络（如ResNet），轻松融入现有的检测框架（如Mask R-CNN, Cascade R-CNN）和分割框架（如U-PerNet）。
-
-
计算高效：
-
线性计算复杂度使其能够处理高分辨率图像，实际推理速度也更快。
-
三、模型修改
步骤一（新增模块）
① 在ultralytics/nn/目录下新建 JH_models(可自命名)文件夹用于存放模块代码。
② 创建SwinTransformer.py文件。
import torch
import torch.nn as nn
import torch.nn.functional as F
import torch.utils.checkpoint as checkpoint
import numpy as np
from timm.models.layers import DropPath, to_2tuple, trunc_normal_
class Mlp(nn.Module):
""" Multilayer perceptron."""
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.fc2 = nn.Linear(hidden_features, out_features)
self.drop = nn.Dropout(drop)
def forward(self, x):
x = self.fc1(x)
x = self.act(x)
x = self.drop(x)
x = self.fc2(x)
x = self.drop(x)
return x
def window_partition(x, window_size):
"""
Args:
x: (B, H, W, C)
window_size (int): window size
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)
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, H, W):
"""
Args:
windows: (num_windows*B, window_size, window_size, C)
window_size (int): Window size
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))
x = windows.view(B, H // window_size, W // window_size, window_size, window_size, -1)
x = x.permute(0, 1, 3, 2, 4, 5).contiguous().view(B, H, W, -1)
return x
class WindowAttention(nn.Module):
""" 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
qk_scale (float | None, optional): Override default qk scale of head_dim ** -0.5 if set
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, 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)
trunc_normal_(self.relative_position_bias_table, std=.02)
self.softmax = nn.Softmax(dim=-1)
def forward(self, x, mask=None):
""" Forward function.
Args:
x: input features with shape of (num_windows*B, N, C)
mask: (0/-inf) mask with shape of (num_windows, Wh*Ww, Wh*Ww) or 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 is not None:
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)
x = (attn @ v).transpose(1, 2).reshape(B_, N, C)
x = self.proj(x)
x = self.proj_drop(x)
return x
class SwinTransformerBlock(nn.Module):
""" 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
qk_scale (float | None, optional): Override default qk scale of head_dim ** -0.5 if set.
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, qk_scale=None, 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=to_2tuple(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)
self.H = None
self.W = None
def forward(self, x, mask_matrix):
""" Forward function.
Args:
x: Input feature, tensor size (B, H*W, C).
H, W: Spatial resolution of the input feature.
mask_matrix: Attention mask for cyclic shift.
"""
B, L, C = x.shape
H, W = self.H, self.W
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
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))
attn_mask = mask_matrix.type(x.dtype)
else:
shifted_x = x
attn_mask = None
# 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, 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:
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 PatchMerging(nn.Module):
""" Patch Merging Layer
Args:
dim (int): Number of input channels.
norm_layer (nn.Module, optional): Normalization layer. Default: nn.LayerNorm
"""
def __init__(self, dim, norm_layer=nn.LayerNorm):
super().__init__()
self.dim = dim
self.reduction = nn.Linear(4 * dim, 2 * dim, bias=False)
self.norm = norm_layer(4 * dim)
def forward(self, x, H, W):
""" Forward function.
Args:
x: Input feature, tensor size (B, H*W, C).
H, W: Spatial resolution of the input feature.
"""
B, L, C = x.shape
assert L == H * W, "input feature has wrong size"
x = x.view(B, H, W, C)
# padding
pad_input = (H % 2 == 1) or (W % 2 == 1)
if pad_input:
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)
return x
class BasicLayer(nn.Module):
""" A basic Swin Transformer layer for one stage.
Args:
dim (int): Number of feature channels
depth (int): Depths of this stage.
num_heads (int): Number of attention head.
window_size (int): Local window size. Default: 7.
mlp_ratio (float): Ratio of mlp hidden dim to embedding dim. Default: 4.
qkv_bias (bool, optional): If True, add a learnable bias to query, key, value. Default: True
qk_scale (float | None, optional): Override default qk scale of head_dim ** -0.5 if set.
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,
depth,
num_heads,
window_size=7,
mlp_ratio=4.,
qkv_bias=True,
qk_scale=None,
drop=0.,
attn_drop=0.,
drop_path=0.,
norm_layer=nn.LayerNorm,
downsample=None,
use_checkpoint=False):
super().__init__()
self.window_size = window_size
self.shift_size = window_size // 2
self.depth = depth
self.use_checkpoint = use_checkpoint
# 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 window_size // 2,
mlp_ratio=mlp_ratio,
qkv_bias=qkv_bias,
qk_scale=qk_scale,
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)])
# patch merging layer
if downsample is not None:
self.downsample = downsample(dim=dim, norm_layer=norm_layer)
else:
self.downsample = None
def forward(self, x, H, W):
""" Forward function.
Args:
x: Input feature, tensor size (B, H*W, C).
H, W: Spatial resolution of the input feature.
"""
# calculate attention mask for SW-MSA
Hp = int(np.ceil(H / self.window_size)) * self.window_size
Wp = int(np.ceil(W / self.window_size)) * self.window_size
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, 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))
for blk in self.blocks:
blk.H, blk.W = H, W
if self.use_checkpoint:
x = checkpoint.checkpoint(blk, x, attn_mask)
else:
x = blk(x, attn_mask)
if self.downsample is not None:
x_down = self.downsample(x, H, W)
Wh, Ww = (H + 1) // 2, (W + 1) // 2
return x, H, W, x_down, Wh, Ww
else:
return x, H, W, x, H, W
class PatchEmbed(nn.Module):
""" Image to Patch Embedding
Args:
patch_size (int): Patch token size. Default: 4.
in_chans (int): Number of input image channels. Default: 3.
embed_dim (int): Number of linear projection output channels. Default: 96.
norm_layer (nn.Module, optional): Normalization layer. Default: None
"""
def __init__(self, patch_size=4, in_chans=3, embed_dim=96, norm_layer=None):
super().__init__()
patch_size = to_2tuple(patch_size)
self.patch_size = patch_size
self.in_chans = in_chans
self.embed_dim = embed_dim
self.proj = nn.Conv2d(in_chans, embed_dim, kernel_size=patch_size, stride=patch_size)
if norm_layer is not None:
self.norm = norm_layer(embed_dim)
else:
self.norm = None
def forward(self, x):
"""Forward function."""
# padding
_, _, H, W = x.size()
if W % self.patch_size[1] != 0:
x = F.pad(x, (0, self.patch_size[1] - W % self.patch_size[1]))
if H % self.patch_size[0] != 0:
x = F.pad(x, (0, 0, 0, self.patch_size[0] - H % self.patch_size[0]))
x = self.proj(x) # B C Wh Ww
if self.norm is not None:
Wh, Ww = x.size(2), x.size(3)
x = x.flatten(2).transpose(1, 2)
x = self.norm(x)
x = x.transpose(1, 2).view(-1, self.embed_dim, Wh, Ww)
return x
class SwinTransformer(nn.Module):
""" Swin Transformer backbone.
A PyTorch impl of : `Swin Transformer: Hierarchical Vision Transformer using Shifted Windows` -
https://arxiv.org/pdf/2103.14030
Args:
pretrain_img_size (int): Input image size for training the pretrained model,
used in absolute postion embedding. Default 224.
patch_size (int | tuple(int)): Patch size. Default: 4.
in_chans (int): Number of input image channels. Default: 3.
embed_dim (int): Number of linear projection output channels. Default: 96.
depths (tuple[int]): Depths of each Swin Transformer stage.
num_heads (tuple[int]): Number of attention head of each stage.
window_size (int): Window size. Default: 7.
mlp_ratio (float): Ratio of mlp hidden dim to embedding dim. Default: 4.
qkv_bias (bool): If True, add a learnable bias to query, key, value. Default: True
qk_scale (float): Override default qk scale of head_dim ** -0.5 if set.
drop_rate (float): Dropout rate.
attn_drop_rate (float): Attention dropout rate. Default: 0.
drop_path_rate (float): Stochastic depth rate. Default: 0.2.
norm_layer (nn.Module): Normalization layer. Default: nn.LayerNorm.
ape (bool): If True, add absolute position embedding to the patch embedding. Default: False.
patch_norm (bool): If True, add normalization after patch embedding. Default: True.
out_indices (Sequence[int]): Output from which stages.
frozen_stages (int): Stages to be frozen (stop grad and set eval mode).
-1 means not freezing any parameters.
use_checkpoint (bool): Whether to use checkpointing to save memory. Default: False.
"""
def __init__(self,
pretrain_img_size=224,
patch_size=4,
in_chans=3,
embed_dim=96,
depths=[2, 2, 6, 2],
num_heads=[3, 6, 12, 24],
window_size=7,
mlp_ratio=4.,
qkv_bias=True,
qk_scale=None,
drop_rate=0.,
attn_drop_rate=0.,
drop_path_rate=0.2,
norm_layer=nn.LayerNorm,
ape=False,
patch_norm=True,
out_indices=(0, 1, 2, 3),
frozen_stages=-1,
use_checkpoint=False):
super().__init__()
self.pretrain_img_size = pretrain_img_size
self.num_layers = len(depths)
self.embed_dim = embed_dim
self.ape = ape
self.patch_norm = patch_norm
self.out_indices = out_indices
self.frozen_stages = frozen_stages
# split image into non-overlapping patches
self.patch_embed = PatchEmbed(
patch_size=patch_size, in_chans=in_chans, embed_dim=embed_dim,
norm_layer=norm_layer if self.patch_norm else None)
# absolute position embedding
if self.ape:
pretrain_img_size = to_2tuple(pretrain_img_size)
patch_size = to_2tuple(patch_size)
patches_resolution = [pretrain_img_size[0] // patch_size[0], pretrain_img_size[1] // patch_size[1]]
self.absolute_pos_embed = nn.Parameter(
torch.zeros(1, embed_dim, patches_resolution[0], patches_resolution[1]))
trunc_normal_(self.absolute_pos_embed, std=.02)
self.pos_drop = nn.Dropout(p=drop_rate)
# stochastic depth
dpr = [x.item() for x in torch.linspace(0, drop_path_rate, sum(depths))] # stochastic depth decay rule
# build layers
self.layers = nn.ModuleList()
for i_layer in range(self.num_layers):
layer = BasicLayer(
dim=int(embed_dim * 2 ** i_layer),
depth=depths[i_layer],
num_heads=num_heads[i_layer],
window_size=window_size,
mlp_ratio=mlp_ratio,
qkv_bias=qkv_bias,
qk_scale=qk_scale,
drop=drop_rate,
attn_drop=attn_drop_rate,
drop_path=dpr[sum(depths[:i_layer]):sum(depths[:i_layer + 1])],
norm_layer=norm_layer,
downsample=PatchMerging if (i_layer < self.num_layers - 1) else None,
use_checkpoint=use_checkpoint)
self.layers.append(layer)
num_features = [int(embed_dim * 2 ** i) for i in range(self.num_layers)]
self.num_features = num_features
# add a norm layer for each output
for i_layer in out_indices:
layer = norm_layer(num_features[i_layer])
layer_name = f'norm{i_layer}'
self.add_module(layer_name, layer)
self.width_list = [i.size(1) for i in self.forward(torch.randn(1, 3, 640, 640))]
def forward(self, x):
"""Forward function."""
x = self.patch_embed(x)
Wh, Ww = x.size(2), x.size(3)
if self.ape:
# interpolate the position embedding to the corresponding size
absolute_pos_embed = F.interpolate(self.absolute_pos_embed, size=(Wh, Ww), mode='bicubic')
x = (x + absolute_pos_embed).flatten(2).transpose(1, 2) # B Wh*Ww C
else:
x = x.flatten(2).transpose(1, 2)
x = self.pos_drop(x)
outs = []
for i in range(self.num_layers):
layer = self.layers[i]
x_out, H, W, x, Wh, Ww = layer(x, Wh, Ww)
if i in self.out_indices:
norm_layer = getattr(self, f'norm{i}')
x_out = norm_layer(x_out)
out = x_out.view(-1, H, W, self.num_features[i]).permute(0, 3, 1, 2).contiguous()
outs.append(out)
return outs③ 创建__init__.py文件。
from .SwinTransformer import *步骤二（代码修改）
① 在ultralytics/nn/modules/tasks.py文件中导入模块。
② 在tasks.py中搜索parse_model函数，增添标志位。
③ 新增代码块，引入Swin Transformer。
④ 将图像红框内容整体替换
替换为
if isinstance(c2, list):
is_backbone = True
m_ = m
m_.backbone = True
else:
m_ = nn.Sequential(*(m(*args) for _ in range(n))) if n > 1 else m(*args) # module
t = str(m)[8:-2].replace('__main__.', '') # module type
m.np = sum(x.numel() for x in m_.parameters()) # number params
m_.i, m_.f, m_.type = i + 4 if is_backbone else i, f, t # attach index, 'from' index, type
if verbose:
LOGGER.info(f'{i:>3}{str(f):>20}{n_:>3}{m.np:10.0f} {t:<45}{str(args):<30}') # print
save.extend(x % (i + 4 if is_backbone else i) for x in ([f] if isinstance(f, int) else f) if
x != -1) # append to savelist
layers.append(m_)
if i == 0:
ch = []
if isinstance(c2, list):
ch.extend(c2)
for _ in range(5 - len(ch)):
ch.insert(0, 0)
else:
ch.append(c2)⑤ 搜索_predict_once，使用如下代码整体替换_predict_once函数。
def _predict_once(self, x, profile=False, visualize=False, embed=None):
y, dt, embeddings = [], [], [] # outputs
for m in self.model:
if m.f != -1: # if not from previous layer
x = (
y[m.f]
if isinstance(m.f, int)
else [x if j == -1 else y[j] for j in m.f]
) # from earlier layers
if profile:
self._profile_one_layer(m, x, dt)
if hasattr(m, "backbone"):
x = m(x)
for _ in range(5 - len(x)):
x.insert(0, None)
for i_idx, i in enumerate(x):
if i_idx in self.save:
y.append(i)
else:
y.append(None)
x = x[-1]
else:
x = m(x) # run
y.append(x if m.i in self.save else None) # save output
if visualize:
feature_visualization(x, m.type, m.i, save_dir=visualize)
if embed and m.i in embed:
embeddings.append(
nn.functional.adaptive_avg_pool2d(x, (1, 1)).squeeze(-1).squeeze(-1)
) # flatten
if m.i == max(embed):
return torch.unbind(torch.cat(embeddings, 1), dim=0)
return x四、模型配置
复制一份ultralytics/cfg/models/11/yolov11.yaml在同目录中，并重命名为yolov11-swintransformer.yaml。 将内容替换为如下所示。将nc修改为自己的类别数。
# Ultralytics YOLO 🚀, AGPL-3.0 license
# YOLO11 object detection model with P3-P5 outputs. For Usage examples see https://docs.ultralytics.com/tasks/detect
# Parameters
nc: 11 # number of classes
scales: # model compound scaling constants, i.e. 'model=yolo11n.yaml' will call yolo11.yaml with scale 'n'
# [depth, width, max_channels]
n: [0.50, 0.25, 1024] # summary: 319 layers, 2624080 parameters, 2624064 gradients, 6.6 GFLOPs
s: [0.50, 0.50, 1024] # summary: 319 layers, 9458752 parameters, 9458736 gradients, 21.7 GFLOPs
m: [0.50, 1.00, 512] # summary: 409 layers, 20114688 parameters, 20114672 gradients, 68.5 GFLOPs
l: [1.00, 1.00, 512] # summary: 631 layers, 25372160 parameters, 25372144 gradients, 87.6 GFLOPs
x: [1.00, 1.50, 512] # summary: 631 layers, 56966176 parameters, 56966160 gradients, 196.0 GFLOPs
# YOLO11n backbone
backbone:
# [from, repeats, module, args]
- [-1, 1, SwinTransformer, []] # 0-4 P1/2
- [-1, 1, SPPF, [1024, 5]] # 5
- [-1, 2, C2PSA, [1024]] # 6
# YOLO11n head
head:
- [-1, 1, nn.Upsample, [None, 2, "nearest"]]
- [[-1, 3], 1, Concat, [1]] # cat backbone P4
- [-1, 2, C3k2, [512, False]] # 9
- [-1, 1, nn.Upsample, [None, 2, "nearest"]]
- [[-1, 2], 1, Concat, [1]] # cat backbone P3
- [-1, 2, C3k2, [256, False]] # 12 (P3/8-small)
- [-1, 1, Conv, [256, 3, 2]]
- [[-1, 9], 1, Concat, [1]] # cat head P4
- [-1, 2, C3k2, [512, False]] # 15 (P4/16-medium)
- [-1, 1, Conv, [512, 3, 2]]
- [[-1, 6], 1, Concat, [1]] # cat head P5
- [-1, 2, C3k2, [1024, True]] # 18 (P5/32-large)
- [[12, 15, 18], 1, Detect, [nc]] # Detect(P3, P4, P5)基于之前博客所讲述的训练代码进行配置train.py。YOLOv11训练自己的数据集-优快云博客
import warnings
warnings.filterwarnings('ignore')
from ultralytics import YOLO
if __name__ == '__main__':
model = YOLO('ultralytics/cfg/models/11/yolo11n-swintransformer.yaml')
model.load('weights/yolo11n.pt') #注释则不加载
results = model.train(
data='ultralytics/cfg/datasets/CeyMo.yaml', #数据集配置文件的路径
epochs=10, #训练轮次总数
batch=32, #批量大小，即单次输入多少图片训练
imgsz=640, #训练图像尺寸
workers=8, #加载数据的工作线程数
device= 0, #指定训练的计算设备，无nvidia显卡则改为 'cpu'
optimizer='SGD', #训练使用优化器，可选 auto,SGD,Adam,AdamW 等
amp= True, #True 或者 False, 解释为：自动混合精度(AMP) 训练
cache=False # True 在内存中缓存数据集图像，服务器推荐开启
)成功运行。
五、总结
本文带大家了解了 Swin Transformer 的核心原理，并展示了如何将其应用到 YOLOv11 中，从而提升目标检测的特征建模能力。
接下来，我会继续分享 更多 YOLOv11 的改进思路，例如引入轻量化注意力机制、优化损失函数、改进特征融合结构等，帮助大家在不同应用场景下都能实现更优的检测效果。
如果你对这些内容感兴趣，可以持续关注本专栏，后续的改进方法都会逐一拆解与实战演示。
扫一扫
636
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
