目录

提出背景

子解法1: 稀疏注意力引入:

子解法2: 区域级路由:

子解法3: 令牌级注意力应用:

2.YOLOv10加入BRA

2.1新建models/attention/BiLevelRoutingAttention.py 

 2.2修改task.py

 2.3 yolov10n-BRA.yaml

 2.4 yolov10n-PSBRA.yaml

---

提出背景

论文：https://arxiv.org/pdf/2303.08810.pdf

代码：GitHub - rayleizhu/BiFormer: [CVPR 2023] Official code release of our paper "BiFormer: Vision Transformer with Bi-Level Routing Attention"

 代码：

######################  BiLevelRoutingAttention  ####  AI&CV   start ###############################
# https://blog.csdn.net/m0_63774211?type=blog
import torch
import torch.nn as nn
from einops import rearrange
import torch.nn.functional as F
from torch import Tensorfrom ul