秋招面试专栏推荐 ：深度学习算法工程师面试问题总结【百面算法工程师】——点击即可跳转
💡💡💡本专栏所有程序均经过测试，可成功执行💡💡💡
本文介绍了一种新颖的动态稀疏注意力机制，即通过双层路由来实现更灵活的计算分配，并具有内容感知能力。文章在介绍主要的原理后，将手把手教学如何进行模块的代码添加和修改，并将修改后的完整代码放在文章的最后，方便大家一键运行，小白也可轻松上手实践。以帮助您更好地学习深度学习目标检测YOLO系列的挑战。
专栏地址：YOLO11入门 + 改进涨点——点击即可跳转 欢迎订阅
目录
1.论文
2. 将BiFormer 添加到YOLO11中
2.1 BiFormer 的代码实现
2.2 更改init.py文件
2.3 添加yaml文件
2.4 在task.py中进行注册
2.5 执行程序
3.修改后的网络结构图
4. 完整代码分享
5. GFLOPs
6. 进阶
7.总结
1.论文
论文地址：BiFormer: Vision Transformer with Bi-Level Routing Attention——点击即可跳转
官方代码：官方代码仓库——点击即可跳转
2. 将BiFormer 添加到YOLO11中
2.1 BiFormer 的代码实现
关键步骤一: 将下面代码粘贴到在/ultralytics/ultralytics/nn/modules/block.py中
"""
Bi-Level Routing Attention.
"""
from typing import Tuple, Optional
import torch
import torch.nn as nn
import torch.nn.functional as F
from einops import rearrange
from torch import Tensor, LongTensor
__all__ = ['BiLevelRoutingAttention']
class TopkRouting(nn.Module):
"""
differentiable topk routing with scaling
Args:
qk_dim: int, feature dimension of query and key
topk: int, the 'topk'
qk_scale: int or None, temperature (multiply) of softmax activation
with_param: bool, wether inorporate learnable params in routing unit
diff_routing: bool, wether make routing differentiable
soft_routing: bool, wether make output value multiplied by routing weights
"""
def __init__(self, qk_dim, topk=4, qk_scale=None, param_routing=False, diff_routing=False):
super().__init__()
self.topk = topk
self.qk_dim = qk_dim
self.scale = qk_scale or qk_dim ** -0.5
self.diff_routing = diff_routing
# TODO: norm layer before/after linear?
self.emb = nn.Linear(qk_dim, qk_dim) if param_routing else nn.Identity()
# routing activation
self.routing_act = nn.Softmax(dim=-1)
def forward(self, query: Tensor, key: Tensor) -> Tuple[Tensor]:
"""
Args:
q, k: (n, p^2, c) tensor
Return:
r_weight, topk_index: (n, p^2, topk) tensor
"""
if not self.diff_routing:
query, key = query.detach(), key.detach()
query_hat, key_hat = self.emb(query), self.emb(key) # per-window pooling -> (n, p^2, c)
attn_logit = (query_hat * self.scale) @ key_hat.transpose(-2, -1) # (n, p^2, p^2)
topk_attn_logit, topk_index = torch.topk(attn_logit, k=self.topk, dim=-1) # (n, p^2, k), (n, p^2, k)
r_weight = self.routing_act(topk_attn_logit) # (n, p^2, k)
return r_weight, topk_index
class KVGather(nn.Module):
def __init__(self, mul_weight='none'):
super().__init__()
assert mul_weight in ['none', 'soft', 'hard']
self.mul_weight = mul_weight
def forward(self, r_idx: Tensor, r_weight: Tensor, kv: Tensor):
"""
r_idx: (n, p^2, topk) tensor
r_weight: (n, p^2, topk) tensor
kv: (n, p^2, w^2, c_kq+c_v)
Return:
(n, p^2, topk, w^2, c_kq+c_v) tensor
"""
# select kv according to routing index
n, p2, w2, c_kv = kv.size()
topk = r_idx.size(-1)
# print(r_idx.size(), r_weight.size())
# FIXME: gather consumes much memory (topk times redundancy), write cuda kernel?
topk_kv = torch.gather(kv.view(n, 1, p2, w2, c_kv).expand(-1, p2, -1, -1, -1),
# (n, p^2, p^2, w^2, c_kv) without mem cpy
dim=2,
index=r_idx.view(n, p2, topk, 1, 1).expand(-1, -1, -1, w2, c_kv)
# (n, p^2, k, w^2, c_kv)
)
if self.mul_weight == 'soft':
topk_kv = r_weight.view(n, p2, topk, 1, 1) * topk_kv # (n, p^2, k, w^2, c_kv)
elif self.mul_weight == 'hard':
raise NotImplementedError('differentiable hard routing TBA')
# else: #'none'
# topk_kv = topk_kv # do nothing
return topk_kv
class QKVLinear(nn.Module):
def __init__(self, dim, qk_dim, bias=True):
super().__init__()
self.dim = dim
self.qk_dim = qk_dim
self.qkv = nn.Linear(dim, qk_dim + qk_dim + dim, bias=bias)
def forward(self, x):
q, kv = self.qkv(x).split([self.qk_dim, self.qk_dim + self.dim], dim=-1)
return q, kv
# q, k, v = self.qkv(x).split([self.qk_dim, self.qk_dim, self.dim], dim=-1)
# return q, k, v
class BiLevelRoutingAttention(nn.Module):
"""
n_win: number of windows in one side (so the actual number of windows is n_win*n_win)
kv_per_win: for kv_downsample_mode='ada_xxxpool' only, number of key/values per window. Similar to n_win, the actual number is kv_per_win*kv_per_win.
topk: topk for window filtering
param_attention: 'qkvo'-linear for q,k,v and o, 'none': param free attention
param_routing: extra linear for routing
diff_routing: wether to set routing differentiable
soft_routing: wether to multiply soft routing weights
"""
def __init__(self, dim, n_win=7, num_heads=8, qk_dim=None, qk_scale=None,
kv_per_win=4, kv_downsample_ratio=4, kv_downsample_kernel=None, kv_downsample_mode='identity',
topk=4, param_attention="qkvo", param_routing=False, diff_routing=False, soft_routing=False,
side_dwconv=3,
auto_pad=True):
super().__init__()
# local attention setting
self.dim = dim
self.n_win = n_win # Wh, Ww
self.num_heads = num_heads
self.qk_dim = qk_dim or dim
assert self.qk_dim % num_heads == 0 and self.dim % num_heads == 0, 'qk_dim and dim must be divisible by num_heads!'
self.scale = qk_scale or self.qk_dim ** -0.5
################side_dwconv (i.e. LCE in ShuntedTransformer)###########
self.lepe = nn.Conv2d(dim, dim, kernel_size=side_dwconv, stride=1, padding=side_dwconv // 2,
groups=dim) if side_dwconv > 0 else \
lambda x: torch.zeros_like(x)
################ global routing setting #################
self.topk = topk
self.param_routing = param_routing
self.diff_routing = diff_routing
self.soft_routing = soft_routing
# router
assert not (self.param_routing and not self.diff_routing) # cannot be with_param=True and diff_routing=False
self.router = TopkRouting(qk_dim=self.qk_dim,
qk_scale=self.scale,
topk=self.topk,
diff_routing=self.diff_routing,
param_routing=self.param_routing)
if self.soft_routing: # soft routing, always diffrentiable (if no detach)
mul_weight = 'soft'
elif self.diff_routing: # hard differentiable routing
mul_weight = 'hard'
else: # hard non-differentiable routing
mul_weight = 'none'
self.kv_gather = KVGather(mul_weight=mul_weight)
# qkv mapping (shared by both global routing and local attention)
self.param_attention = param_attention
if self.param_attention == 'qkvo':
self.qkv = QKVLinear(self.dim, self.qk_dim)
self.wo = nn.Linear(dim, dim)
elif self.param_attention == 'qkv':
self.qkv = QKVLinear(self.dim, self.qk_dim)
self.wo = nn.Identity()
else:
raise ValueError(f'param_attention mode {self.param_attention} is not surpported!')
self.kv_downsample_mode = kv_downsample_mode
self.kv_per_win = kv_per_win
self.kv_downsample_ratio = kv_downsample_ratio
self.kv_downsample_kenel = kv_downsample_kernel
if self.kv_downsample_mode == 'ada_avgpool':
assert self.kv_per_win is not None
self.kv_down = nn.AdaptiveAvgPool2d(self.kv_per_win)
elif self.kv_downsample_mode == 'ada_maxpool':
assert self.kv_per_win is not None
self.kv_down = nn.AdaptiveMaxPool2d(self.kv_per_win)
elif self.kv_downsample_mode == 'maxpool':
assert self.kv_downsample_ratio is not None
self.kv_down = nn.MaxPool2d(self.kv_downsample_ratio) if self.kv_downsample_ratio > 1 else nn.Identity()
elif self.kv_downsample_mode == 'avgpool':
assert self.kv_downsample_ratio is not None
self.kv_down = nn.AvgPool2d(self.kv_downsample_ratio) if self.kv_downsample_ratio > 1 else nn.Identity()
elif self.kv_downsample_mode == 'identity': # no kv downsampling
self.kv_down = nn.Identity()
elif self.kv_downsample_mode == 'fracpool':
# assert self.kv_downsample_ratio is not None
# assert self.kv_downsample_kenel is not None
# TODO: fracpool
# 1. kernel size should be input size dependent
# 2. there is a random factor, need to avoid independent sampling for k and v
raise NotImplementedError('fracpool policy is not implemented yet!')
elif kv_downsample_mode == 'conv':
# TODO: need to consider the case where k != v so that need two downsample modules
raise NotImplementedError('conv policy is not implemented yet!')
else:
raise ValueError(f'kv_down_sample_mode {self.kv_downsaple_mode} is not surpported!')
# softmax for local attention
self.attn_act = nn.Softmax(dim=-1)
self.auto_pad = auto_pad
def forward(self, x, ret_attn_mask=False):
"""
x: NHWC tensor
Return:
NHWC tensor
"""
x = rearrange(x, "n c h w -> n h w c")
# NOTE: use padding for semantic segmentation
###################################################
if self.auto_pad:
N, H_in, W_in, C = x.size()
pad_l = pad_t = 0
pad_r = (self.n_win - W_in % self.n_win) % self.n_win
pad_b = (self.n_win - H_in % self.n_win) % self.n_win
x = F.pad(x, (0, 0, # dim=-1
pad_l, pad_r, # dim=-2
pad_t, pad_b)) # dim=-3
_, H, W, _ = x.size() # padded size
else:
N, H, W, C = x.size()
assert H % self.n_win == 0 and W % self.n_win == 0 #
###################################################
# patchify, (n, p^2, w, w, c), keep 2d window as we need 2d pooling to reduce kv size
x = rearrange(x, "n (j h) (i w) c -> n (j i) h w c", j=self.n_win, i=self.n_win)
#################qkv projection###################
# q: (n, p^2, w, w, c_qk)
# kv: (n, p^2, w, w, c_qk+c_v)
# NOTE: separte kv if there were memory leak issue caused by gather
q, kv = self.qkv(x)
# pixel-wise qkv
# q_pix: (n, p^2, w^2, c_qk)
# kv_pix: (n, p^2, h_kv*w_kv, c_qk+c_v)
q_pix = rearrange(q, 'n p2 h w c -> n p2 (h w) c')
kv_pix = self.kv_down(rearrange(kv, 'n p2 h w c -> (n p2) c h w'))
kv_pix = rearrange(kv_pix, '(n j i) c h w -> n (j i) (h w) c', j=self.n_win, i=self.n_win)
q_win, k_win = q.mean([2, 3]), kv[..., 0:self.qk_dim].mean(
[2, 3]) # window-wise qk, (n, p^2, c_qk), (n, p^2, c_qk)
##################side_dwconv(lepe)##################
# NOTE: call contiguous to avoid gradient warning when using ddp
lepe = self.lepe(rearrange(kv[..., self.qk_dim:], 'n (j i) h w c -> n c (j h) (i w)', j=self.n_win,
i=self.n_win).contiguous())
lepe = rearrange(lepe, 'n c (j h) (i w) -> n (j h) (i w) c', j=self.n_win, i=self.n_win)
############ gather q dependent k/v #################
r_weight, r_idx = self.router(q_win, k_win) # both are (n, p^2, topk) tensors
kv_pix_sel = self.kv_gather(r_idx=r_idx, r_weight=r_weight, kv=kv_pix) # (n, p^2, topk, h_kv*w_kv, c_qk+c_v)
k_pix_sel, v_pix_sel = kv_pix_sel.split([self.qk_dim, self.dim], dim=-1)
# kv_pix_sel: (n, p^2, topk, h_kv*w_kv, c_qk)
# v_pix_sel: (n, p^2, topk, h_kv*w_kv, c_v)
######### do attention as normal ####################
k_pix_sel = rearrange(k_pix_sel, 'n p2 k w2 (m c) -> (n p2) m c (k w2)',
m=self.num_heads) # flatten to BMLC, (n*p^2, m, topk*h_kv*w_kv, c_kq//m) transpose here?
v_pix_sel = rearrange(v_pix_sel, 'n p2 k w2 (m c) -> (n p2) m (k w2) c',
m=self.num_heads) # flatten to BMLC, (n*p^2, m, topk*h_kv*w_kv, c_v//m)
q_pix = rearrange(q_pix, 'n p2 w2 (m c) -> (n p2) m w2 c',
m=self.num_heads) # to BMLC tensor (n*p^2, m, w^2, c_qk//m)
# param-free multihead attention
attn_weight = (
q_pix * self.scale) @ k_pix_sel # (n*p^2, m, w^2, c) @ (n*p^2, m, c, topk*h_kv*w_kv) -> (n*p^2, m, w^2, topk*h_kv*w_kv)
attn_weight = self.attn_act(attn_weight)
out = attn_weight @ v_pix_sel # (n*p^2, m, w^2, topk*h_kv*w_kv) @ (n*p^2, m, topk*h_kv*w_kv, c) -> (n*p^2, m, w^2, c)
out = rearrange(out, '(n j i) m (h w) c -> n (j h) (i w) (m c)', j=self.n_win, i=self.n_win,
h=H // self.n_win, w=W // self.n_win)
out = out + lepe
# output linear
out = self.wo(out)
# NOTE: use padding for semantic segmentation
# crop padded region
if self.auto_pad and (pad_r > 0 or pad_b > 0):
out = out[:, :H_in, :W_in, :].contiguous()
if ret_attn_mask:
return out, r_weight, r_idx, attn_weight
else:
return rearrange(out, "n h w c -> n c h w")
2.2 更改init.py文件
关键步骤二：修改modules文件夹下的__init__.py文件，先导入函数
然后在下面的__all__中声明函数
2.3 添加yaml文件
关键步骤三：在/ultralytics/ultralytics/cfg/models/11下面新建文件yolo11_BiFormer.yaml文件，粘贴下面的内容
- 目标检测
# 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: 80 # 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, Conv, [64, 3, 2]] # 0-P1/2
- [-1, 1, Conv, [128, 3, 2]] # 1-P2/4
- [-1, 2, C3k2, [256, False, 0.25]]
- [-1, 1, Conv, [256, 3, 2]] # 3-P3/8
- [-1, 2, C3k2, [512, False, 0.25]]
- [-1, 1, Conv, [512, 3, 2]] # 5-P4/16
- [-1, 2, C3k2, [512, True]]
- [-1, 1, Conv, [1024, 3, 2]] # 7-P5/32
- [-1, 2, C3k2, [1024, True]]
- [-1, 1, SPPF, [1024, 5]] # 9
- [-1, 2, C2PSA, [1024]] # 10
# YOLO11n head
head:
- [-1, 1, nn.Upsample, [None, 2, "nearest"]]
- [[-1, 6], 1, Concat, [1]] # cat backbone P4
- [-1, 2, C3k2, [512, False]] # 13
- [-1, 1, nn.Upsample, [None, 2, "nearest"]]
- [[-1, 4], 1, Concat, [1]] # cat backbone P3
- [-1, 1, BiLevelRoutingAttention, []]
- [-1, 2, C3k2, [256, False]] # 16 (P3/8-small)
- [-1, 1, Conv, [256, 3, 2]]
- [[-1, 13], 1, Concat, [1]] # cat head P4
- [-1, 1, BiLevelRoutingAttention, []]
- [-1, 2, C3k2, [512, False]] # 19 (P4/16-medium)
- [-1, 1, Conv, [512, 3, 2]]
- [[-1, 10], 1, Concat, [1]] # cat head P5
- [-1, 1, BiLevelRoutingAttention, []]
- [-1, 2, C3k2, [1024, True]] # 22 (P5/32-large)
- [[17, 21, 25], 1, Detect, [nc]] # Detect(P3, P4, P5)
- 语义分割
# 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: 80 # 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, Conv, [64, 3, 2]] # 0-P1/2
- [-1, 1, Conv, [128, 3, 2]] # 1-P2/4
- [-1, 2, C3k2, [256, False, 0.25]]
- [-1, 1, Conv, [256, 3, 2]] # 3-P3/8
- [-1, 2, C3k2, [512, False, 0.25]]
- [-1, 1, Conv, [512, 3, 2]] # 5-P4/16
- [-1, 2, C3k2, [512, True]]
- [-1, 1, Conv, [1024, 3, 2]] # 7-P5/32
- [-1, 2, C3k2, [1024, True]]
- [-1, 1, SPPF, [1024, 5]] # 9
- [-1, 2, C2PSA, [1024]] # 10
# YOLO11n head
head:
- [-1, 1, nn.Upsample, [None, 2, "nearest"]]
- [[-1, 6], 1, Concat, [1]] # cat backbone P4
- [-1, 2, C3k2, [512, False]] # 13
- [-1, 1, nn.Upsample, [None, 2, "nearest"]]
- [[-1, 4], 1, Concat, [1]] # cat backbone P3
- [-1, 1, BiLevelRoutingAttention, []]
- [-1, 2, C3k2, [256, False]] # 16 (P3/8-small)
- [-1, 1, Conv, [256, 3, 2]]
- [[-1, 13], 1, Concat, [1]] # cat head P4
- [-1, 1, BiLevelRoutingAttention, []]
- [-1, 2, C3k2, [512, False]] # 19 (P4/16-medium)
- [-1, 1, Conv, [512, 3, 2]]
- [[-1, 10], 1, Concat, [1]] # cat head P5
- [-1, 1, BiLevelRoutingAttention, []]
- [-1, 2, C3k2, [1024, True]] # 22 (P5/32-large)
- [[17, 21, 25], 1, Segment, [nc, 32, 256]] # Segment(P3, P4, P5)
- 旋转目标检测
# 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: 80 # 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, Conv, [64, 3, 2]] # 0-P1/2
- [-1, 1, Conv, [128, 3, 2]] # 1-P2/4
- [-1, 2, C3k2, [256, False, 0.25]]
- [-1, 1, Conv, [256, 3, 2]] # 3-P3/8
- [-1, 2, C3k2, [512, False, 0.25]]
- [-1, 1, Conv, [512, 3, 2]] # 5-P4/16
- [-1, 2, C3k2, [512, True]]
- [-1, 1, Conv, [1024, 3, 2]] # 7-P5/32
- [-1, 2, C3k2, [1024, True]]
- [-1, 1, SPPF, [1024, 5]] # 9
- [-1, 2, C2PSA, [1024]] # 10
# YOLO11n head
head:
- [-1, 1, nn.Upsample, [None, 2, "nearest"]]
- [[-1, 6], 1, Concat, [1]] # cat backbone P4
- [-1, 2, C3k2, [512, False]] # 13
- [-1, 1, nn.Upsample, [None, 2, "nearest"]]
- [[-1, 4], 1, Concat, [1]] # cat backbone P3
- [-1, 1, BiLevelRoutingAttention, []]
- [-1, 2, C3k2, [256, False]] # 16 (P3/8-small)
- [-1, 1, Conv, [256, 3, 2]]
- [[-1, 13], 1, Concat, [1]] # cat head P4
- [-1, 1, BiLevelRoutingAttention, []]
- [-1, 2, C3k2, [512, False]] # 19 (P4/16-medium)
- [-1, 1, Conv, [512, 3, 2]]
- [[-1, 10], 1, Concat, [1]] # cat head P5
- [-1, 1, BiLevelRoutingAttention, []]
- [-1, 2, C3k2, [1024, True]] # 22 (P5/32-large)
- [[17, 21, 25], 1, OBB, [nc, 1]] # Detect(P3, P4, P5)
温馨提示：本文只是对yolo11基础上添加模块，如果要对yolo11n/l/m/x进行添加则只需要指定对应的depth_multiple 和 width_multiple。
# YOLO11n
depth_multiple: 0.50 # model depth multiple
width_multiple: 0.25 # layer channel multiple
max_channel：1024
# YOLO11s
depth_multiple: 0.50 # model depth multiple
width_multiple: 0.50 # layer channel multiple
max_channel：1024
# YOLO11m
depth_multiple: 0.50 # model depth multiple
width_multiple: 1.00 # layer channel multiple
max_channel：512
# YOLO11l
depth_multiple: 1.00 # model depth multiple
width_multiple: 1.00 # layer channel multiple
max_channel：512
# YOLO11x
depth_multiple: 1.00 # model depth multiple
width_multiple: 1.50 # layer channel multiple
max_channel：5122.4 在task.py中进行注册
关键步骤四：在task.py的parse_model函数中进行注册，
先在task.py导入函数
然后在task.py文件下找到parse_model这个函数，如下图，添加BiLevelRoutingAttention
elif m in {BiLevelRoutingAttention}:
c2 = ch[f]
args = [c2, *args]2.5 执行程序
关键步骤五：在ultralytics文件中新建train.py，将model的参数路径设置为yolo11_BiFormer.yaml的路径即可
from ultralytics import YOLO
import warnings
warnings.filterwarnings('ignore')
from pathlib import Path
if __name__ == '__main__':
# 加载模型
model = YOLO("ultralytics/cfg/11/yolo11.yaml") # 你要选择的模型yaml文件地址
# Use the model
results = model.train(data=r"你的数据集的yaml文件地址",
epochs=100, batch=16, imgsz=640, workers=4, name=Path(model.cfg).stem) # 训练模型🚀运行程序，如果出现下面的内容则说明添加成功🚀
from n params module arguments
0 -1 1 464 ultralytics.nn.modules.conv.Conv [3, 16, 3, 2]
1 -1 1 4672 ultralytics.nn.modules.conv.Conv [16, 32, 3, 2]
2 -1 1 6640 ultralytics.nn.modules.block.C3k2 [32, 64, 1, False, 0.25]
3 -1 1 36992 ultralytics.nn.modules.conv.Conv [64, 64, 3, 2]
4 -1 1 26080 ultralytics.nn.modules.block.C3k2 [64, 128, 1, False, 0.25]
5 -1 1 147712 ultralytics.nn.modules.conv.Conv [128, 128, 3, 2]
6 -1 1 87040 ultralytics.nn.modules.block.C3k2 [128, 128, 1, True]
7 -1 1 295424 ultralytics.nn.modules.conv.Conv [128, 256, 3, 2]
8 -1 1 346112 ultralytics.nn.modules.block.C3k2 [256, 256, 1, True]
9 -1 1 164608 ultralytics.nn.modules.block.SPPF [256, 256, 5]
10 -1 1 249728 ultralytics.nn.modules.block.C2PSA [256, 256, 1]
11 -1 1 0 torch.nn.modules.upsampling.Upsample [None, 2, 'nearest']
12 [-1, 6] 1 0 ultralytics.nn.modules.conv.Concat [1]
13 -1 1 111296 ultralytics.nn.modules.block.C3k2 [384, 128, 1, False]
14 -1 1 0 torch.nn.modules.upsampling.Upsample [None, 2, 'nearest']
15 [-1, 4] 1 0 ultralytics.nn.modules.conv.Concat [1]
16 -1 1 265728 ultralytics.nn.modules.block.BiLevelRoutingAttention[256]
17 -1 1 32096 ultralytics.nn.modules.block.C3k2 [256, 64, 1, False]
18 -1 1 36992 ultralytics.nn.modules.conv.Conv [64, 64, 3, 2]
19 [-1, 13] 1 0 ultralytics.nn.modules.conv.Concat [1]
20 -1 1 150144 ultralytics.nn.modules.block.BiLevelRoutingAttention[192]
21 -1 1 86720 ultralytics.nn.modules.block.C3k2 [192, 128, 1, False]
22 -1 1 147712 ultralytics.nn.modules.conv.Conv [128, 128, 3, 2]
23 [-1, 10] 1 0 ultralytics.nn.modules.conv.Concat [1]
24 -1 1 595200 ultralytics.nn.modules.block.BiLevelRoutingAttention[384]
25 -1 1 378880 ultralytics.nn.modules.block.C3k2 [384, 256, 1, True]
26 [17, 21, 25] 1 464912 ultralytics.nn.modules.head.Detect [80, [64, 128, 256]]
YOLO11_Biformer summary: 352 layers, 3,635,152 parameters, 3,635,136 gradients, 46.1 GFLOPs3.修改后的网络结构图
看不懂的可以问我，偷个懒
4. 完整代码分享
这个后期补充吧~，先按照步骤来即可
5. GFLOPs
关于GFLOPs的计算方式可以查看：百面算法工程师 | 卷积基础知识——Convolution
未改进的YOLO11n GFLOPs
改进后的GFLOPs
6. 进阶
可以与其他的注意力机制或者损失函数等结合，进一步提升检测效果
7.总结
通过以上的改进方法，我们成功提升了模型的表现。这只是一个开始，未来还有更多优化和技术深挖的空间。在这里，我想隆重向大家推荐我的专栏——《YOLO11改进有效涨点》。这个专栏专注于前沿的深度学习技术，特别是目标检测领域的最新进展，不仅包含对YOLO11的深入解析和改进策略，还会定期更新来自各大顶会（如CVPR、NeurIPS等）的论文复现和实战分享。
为什么订阅我的专栏？ ——《YOLO11改进有效涨点》
-
前沿技术解读：专栏不仅限于YOLO系列的改进，还会涵盖各类主流与新兴网络的最新研究成果，帮助你紧跟技术潮流。
-
详尽的实践分享：所有内容实践性也极强。每次更新都会附带代码和具体的改进步骤，保证每位读者都能迅速上手。
-
问题互动与答疑：订阅我的专栏后，你将可以随时向我提问，获取及时的答疑。
-
实时更新，紧跟行业动态：不定期发布来自全球顶会的最新研究方向和复现实验报告，让你时刻走在技术前沿。
专栏适合人群：
-
对目标检测、YOLO系列网络有深厚兴趣的同学
-
希望在用YOLO算法写论文的同学
-
对YOLO算法感兴趣的同学等
