在YOLOv7中不同地方简易添加BiFormer注意力机制（其他机制也受用）

已于 2023-12-25 21:59:22 修改
阅读量822 收藏 22
点赞数 5
文章标签： YOLO python 深度学习
于 2023-04-27 23:05:12 首次发布
版权声明：本文为博主原创文章，遵循 CC 4.0 BY-SA 版权协议，转载请附上原文出处链接和本声明。
本文链接：https://blog.csdn.net/weixin_45314480/article/details/130414172
版权

先创建BiFormer.py

from typing import Tuple

import torch
import torch.nn as nn
import torch.nn.functional as F
from einops import rearrange
from torch import Tensor


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")


class Attention(nn.Module):
    """
    vanilla attention
    """

    def __init__(self, dim, num_heads=8, qkv_bias=False, qk_scale=None, attn_drop=0., proj_drop=0.):
        super().__init__()
        self.num_heads = num_heads
        head_dim = dim // num_heads
        # NOTE scale factor was wrong in my original version, can set manually to be compat with prev weights
        self.scale = qk_scale or head_dim ** -0.5

        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)

    def forward(self, x):
        """
        args:
            x: NCHW tensor
        return:
            NCHW tensor
        """
        _, _, H, W = x.size()
        x = rearrange(x, 'n c h w -> n (h w) c')

        #######################################
        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)

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

        x = (attn @ v).transpose(1, 2).reshape(B, N, C)
        x = self.proj(x)
        x = self.proj_drop(x)
        #######################################

        x = rearrange(x, 'n (h w) c -> n c h w', h=H, w=W)
        return x


class AttentionLePE(nn.Module):
    """
    vanilla attention
    """

    def __init__(self, dim, num_heads=8, qkv_bias=False, qk_scale=None, attn_drop=0., proj_drop=0., side_dwconv=5):
        super().__init__()
        self.num_heads = num_heads
        head_dim = dim // num_heads
        # NOTE scale factor was wrong in my original version, can set manually to be compat with prev weights
        self.scale = qk_scale or head_dim ** -0.5

        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)
        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)

    def forward(self, x):
        """
        args:
            x: NCHW tensor
        return:
            NCHW tensor
        """
        _, _, H, W = x.size()
        x = rearrange(x, 'n c h w -> n (h w) c')

        #######################################
        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)

        lepe = self.lepe(rearrange(x, 'n (h w) c -> n c h w', h=H, w=W))
        lepe = rearrange(lepe, 'n c h w -> n (h w) c')

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

        x = (attn @ v).transpose(1, 2).reshape(B, N, C)
        x = x + lepe

        x = self.proj(x)
        x = self.proj_drop(x)
        #######################################

        x = rearrange(x, 'n (h w) c -> n c h w', h=H, w=W)
        return x

并在common.py中引入

        

#  其中BiLevelRoutingAttention, Attention, AttentionLePE为BiFormer里定义的三种注意力机制

from models.BiFormer import BiLevelRoutingAttention, Attention, AttentionLePE

第一种：在SPPCSPC后面添加注意力机制

在common.py文件中找到SPPCSPC模块

class SPPCSPC(nn.Module):
    # CSP https://github.com/WongKinYiu/CrossStagePartialNetworks
    def __init__(self, c1, c2, n=1, shortcut=False, g=1, e=0.5, k=(5, 9, 13)):
        super(SPPCSPC, self).__init__()
        c_ = int(2 * c2 * e)  # hidden channels
        self.cv1 = Conv(c1, c_, 1, 1)
        self.cv2 = Conv(c1, c_, 1, 1)
        self.cv3 = Conv(c_, c_, 3, 1)
        self.cv4 = Conv(c_, c_, 1, 1)
        self.m = nn.ModuleList([nn.MaxPool2d(kernel_size=x, stride=1, padding=x // 2) for x in k])
        self.cv5 = Conv(4 * c_, c_, 1, 1)
        self.cv6 = Conv(c_, c_, 3, 1)
        self.cv7 = Conv(2 * c_, c2, 1, 1)
        '''新添加的注意力机制'''
        self.att = BiLevelRoutingAttention(c2)  # 通道数为上一层输出的通道数

    def forward(self, x):
        x1 = self.cv4(self.cv3(self.cv1(x)))
        y1 = self.cv6(self.cv5(torch.cat([x1] + [m(x1) for m in self.m], 1)))
        y2 = self.cv2(x)
        return self.att(self.cv7(torch.cat((y1, y2), dim=1)))  # 修改

第二种：对卷积做修改

在common.py中添加

class Conv_BiF(nn.Module):
    # Standard convolution
    def __init__(self, c1, c2, k=1, s=1, p=None, g=1, act=True):  # ch_in, ch_out, kernel, stride, padding, groups
        super(Conv_BiF, self).__init__()
        self.conv = nn.Conv2d(c1, c2, k, s, autopad(k, p), groups=g, bias=False)
        self.bn = nn.BatchNorm2d(c2)
        self.act = nn.SiLU() if act is True else (act if isinstance(act, nn.Module) else nn.Identity())
        self.att = BiLevelRoutingAttention(c2)

    def forward(self, x):
        return self.att(self.act(self.bn(self.conv(x))))

    def fuseforward(self, x):
        return self.att(self.act(self.conv(x)))

然后在yolo.py中if m in [ ]中添加Conv_BiF模块

if m in [nn.Conv2d, Conv, Conv_BiF, RobustConv, RobustConv2, DWConv, GhostConv, RepConv, RepConv_OREPA, DownC,
                 SPP, SPPF, SPPCSPC, GhostSPPCSPC, MixConv2d, Focus, Stem, GhostStem, CrossConv, 
                 Bottleneck, BottleneckCSPA, BottleneckCSPB, BottleneckCSPC, 
                 RepBottleneck, RepBottleneckCSPA, RepBottleneckCSPB, RepBottleneckCSPC,  
                 Res, ResCSPA, ResCSPB, ResCSPC, 
                 RepRes, RepResCSPA, RepResCSPB, RepResCSPC, 
                 ResX, ResXCSPA, ResXCSPB, ResXCSPC, 
                 RepResX, RepResXCSPA, RepResXCSPB, RepResXCSPC, 
                 Ghost, GhostCSPA, GhostCSPB, GhostCSPC,
                 SwinTransformerBlock, STCSPA, STCSPB, STCSPC,
                 SwinTransformer2Block, ST2CSPA, ST2CSPB, ST2CSPC, ACmix]:

最后在cfg里的yaml文件替换

# parameters
nc: 1  # number of classes
depth_multiple: 1.0  # model depth multiple
width_multiple: 1.0  # layer channel multiple

# anchors
anchors:
  - [12,16, 19,36, 40,28]  # P3/8
  - [36,75, 76,55, 72,146]  # P4/16
  - [142,110, 192,243, 459,401]  # P5/32

# yolov7 backbone
backbone:
  # [from, number, module, args]
  [[-1, 1, Conv, [32, 3, 1]],  # 0
  
   [-1, 1, Conv, [64, 3, 2]],  # 1-P1/2      
   [-1, 1, Conv, [64, 3, 1]],
   
   [-1, 1, Conv, [128, 3, 2]],  # 3-P2/4  
   [-1, 1, Conv, [64, 1, 1]],
   [-2, 1, Conv, [64, 1, 1]],
   [-1, 1, Conv, [64, 3, 1]],
   [-1, 1, Conv, [64, 3, 1]],
   [-1, 1, Conv, [64, 3, 1]],
   [-1, 1, Conv, [64, 3, 1]],
   [[-1, -3, -5, -6], 1, Concat, [1]],
   [-1, 1, Conv, [256, 1, 1]],  # 11
         
   [-1, 1, MP, []],
   [-1, 1, Conv, [128, 1, 1]],
   [-3, 1, Conv, [128, 1, 1]],
   [-1, 1, Conv, [128, 3, 2]],
   [[-1, -3], 1, Concat, [1]],  # 16-P3/8  
   [-1, 1, Conv, [128, 1, 1]],
   [-2, 1, Conv, [128, 1, 1]],
   [-1, 1, Conv, [128, 3, 1]],
   [-1, 1, Conv, [128, 3, 1]],
   [-1, 1, Conv, [128, 3, 1]],
   [-1, 1, Conv, [128, 3, 1]],
   [[-1, -3, -5, -6], 1, Concat, [1]],
   [-1, 1, Conv, [512, 1, 1]],  # 24
         
   [-1, 1, MP, []],
   [-1, 1, Conv, [256, 1, 1]],
   [-3, 1, Conv, [256, 1, 1]],
   [-1, 1, Conv, [256, 3, 2]],
   [[-1, -3], 1, Concat, [1]],  # 29-P4/16  
   [-1, 1, Conv, [256, 1, 1]],
   [-2, 1, Conv, [256, 1, 1]],
   [-1, 1, Conv, [256, 3, 1]],
   [-1, 1, Conv, [256, 3, 1]],
   [-1, 1, Conv, [256, 3, 1]],
   [-1, 1, Conv, [256, 3, 1]],
   [[-1, -3, -5, -6], 1, Concat, [1]],
   [-1, 1, Conv, [1024, 1, 1]],  # 37
         
   [-1, 1, MP, []],
   [-1, 1, Conv, [512, 1, 1]],
   [-3, 1, Conv, [512, 1, 1]],
   [-1, 1, Conv, [512, 3, 2]],
   [[-1, -3], 1, Concat, [1]],  # 42-P5/32  
   [-1, 1, Conv, [256, 1, 1]],
   [-2, 1, Conv, [256, 1, 1]],
   [-1, 1, Conv, [256, 3, 1]],
   [-1, 1, Conv, [256, 3, 1]],
   [-1, 1, Conv, [256, 3, 1]],
   [-1, 1, Conv, [256, 3, 1]],
   [[-1, -3, -5, -6], 1, Concat, [1]],
   [-1, 1, Conv, [1024, 1, 1]],  # 50
  ]

# yolov7 head
head:
  [[-1, 1, SPPCSPC, [512]], # 51
  
   [-1, 1, Conv, [256, 1, 1]],
   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
   [37, 1, Conv, [256, 1, 1]], # route backbone P4
   [[-1, -2], 1, Concat, [1]],
   
   [-1, 1, Conv, [256, 1, 1]],
   [-2, 1, Conv, [256, 1, 1]],
   [-1, 1, Conv, [128, 3, 1]],
   [-1, 1, Conv, [128, 3, 1]],
   [-1, 1, Conv, [128, 3, 1]],
   [-1, 1, Conv, [128, 3, 1]],
   [[-1, -2, -3, -4, -5, -6], 1, Concat, [1]],
   [-1, 1, Conv, [256, 1, 1]], # 63
   
   [-1, 1, Conv, [128, 1, 1]],
   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
   [24, 1, Conv, [128, 1, 1]], # route backbone P3
   [[-1, -2], 1, Concat, [1]],
   
   [-1, 1, Conv, [128, 1, 1]],
   [-2, 1, Conv, [128, 1, 1]],
   [-1, 1, Conv, [64, 3, 1]],
   [-1, 1, Conv, [64, 3, 1]],
   [-1, 1, Conv, [64, 3, 1]],
   [-1, 1, Conv, [64, 3, 1]],
   [[-1, -2, -3, -4, -5, -6], 1, Concat, [1]],
   [-1, 1, Conv, [128, 1, 1]], # 75
      
   [-1, 1, MP, []],
   [-1, 1, Conv, [128, 1, 1]],
   [-3, 1, Conv, [128, 1, 1]],
   [-1, 1, Conv, [128, 3, 2]],
   [[-1, -3, 63], 1, Concat, [1]],
   
   [-1, 1, Conv, [256, 1, 1]],
   [-2, 1, Conv, [256, 1, 1]],
   [-1, 1, Conv, [128, 3, 1]],
   [-1, 1, Conv, [128, 3, 1]],
   [-1, 1, Conv, [128, 3, 1]],
   [-1, 1, Conv, [128, 3, 1]],
   [[-1, -2, -3, -4, -5, -6], 1, Concat, [1]],
   [-1, 1, Conv, [256, 1, 1]], # 88
      
   [-1, 1, MP, []],
   [-1, 1, Conv, [256, 1, 1]],
   [-3, 1, Conv, [256, 1, 1]],
   [-1, 1, Conv, [256, 3, 2]],
   [[-1, -3, 51], 1, Concat, [1]],
   
   [-1, 1, Conv, [512, 1, 1]],
   [-2, 1, Conv, [512, 1, 1]],
   [-1, 1, Conv, [256, 3, 1]],
   [-1, 1, Conv, [256, 3, 1]],
   [-1, 1, Conv, [256, 3, 1]],
   [-1, 1, Conv_BiF, [256, 3, 1]],
   [[-1, -2, -3, -4, -5, -6], 1, Concat, [1]],
   [-1, 1, Conv, [512, 1, 1]], # 101
   
   [75, 1, RepConv, [256, 3, 1]],
   [88, 1, RepConv, [512, 3, 1]],
   [101, 1, RepConv, [1024, 3, 1]],

   [[102,103,104], 1, IDetect, [nc, anchors]],   # Detect(P3, P4, P5)
  ]

第三种，在通道连接（Concat）后面加

在common.py中添加代码

class Concat_BiF(nn.Module):
    def __init__(self, dim, dimension=1):
        super(Concat_BiF, self).__init__()
        self.d = dimension
        self.att = BiLevelRoutingAttention(dim)

    def forward(self, x):
        return self.att(torch.cat(x, self.d))

然后在yolo.py中的if m in [ ]下的对应位置添加

        elif m is Concat:
            c2 = sum([ch[x] for x in f])

        '''新添加的Concat_BiF'''
        elif m is Concat_BiF:
            c2 = sum([ch[x] for x in f])
            args = [c2, *args]

最后在cfg文件下的yaml修改对应位置的concat

管不住嘴的要吃喝
关注
  • 5
    点赞
  • 踩
  • 22
    收藏
    觉得还不错? 一键收藏
  • 1
    评论
YOLOv5改进系列（20）——添加BiFormer注意力机制（CVPR2023|小目标涨点神器）
路人贾的博客
08-11 4433
YOLOv5改进系列之添加BiFormer注意力机制，通过双向路由注意力构建高效金字塔网络架构，CVPR2023，小目标实测涨点神器
YOLOv7改进：在不同位置添加biformer
m0_51530640的博客
04-15 2219
为了缓解多头自注意力()的可扩展性问题，先前的一些方法提出了不同的稀疏注意力机制，其中每个查询只关注少量的键值对，而非全部。为此，作者探索了一种动态的、查询感知的稀疏注意力机制，其关键思想是在粗糙区域级别过滤掉大部分不相关的键值对，以便只保留一小部分路由区域（这不就把冗余的信息干掉了吗老铁们）。其次，作者在这些路由区域的联合中应用细粒度的注意力。本文以yolov7-tiny.yaml为基础网络结构进行修改，尝试将注意力机制添加到不同的位置。CBAM的原理不在赘述，直接开始代码修改。
基于yolov5的PCB缺陷检测，引入CVPR 2023 BiFormer：Vision Transformer with Bi-Level Routing Attention提升检测精度
03-23 4167
基于yolov5的PCB缺陷检测，通过不同优化，如CVPR 2023 BiFormer：Vision Transformer with Bi-Level Routing Attention，提升检测精度
YOLOv8最新改进系列：YOLOv8+BiFormer（CVPR 2023最新提出），基于动态稀疏注意力构建高效金字塔网络架构，用动态、查询感知的方式实现计算的有效分配，嘎嘎提升目标检测效果！
weixin_51692073的博客
09-13 7913
YOLOv8最新改进系列：YOLOv8+BiFormer（CVPR 2023最新提出），基于动态稀疏注意力构建高效金字塔网络架构，用动态、查询感知的方式实现计算的有效分配，嘎嘎提升目标检测效果！
Yolov5/Yolov7 引入CVPR 2023 BiFormer: 基于动态稀疏注意力构建高效金字塔网络架构，对小目标涨点明显
热门推荐
03-23 1万+
Yolov5/Yolov7 引入CVPR 2023 BiFormer: 基于动态稀疏注意力构建高效金字塔网络架构，对小目标涨点明显
改进YOLO系列 | CVPR2023最新注意力 | BiFormer：视觉变换器与双层路由注意力
YOLOv8项目贡献者
04-24 4830
🍀🍀🍀CVPR2023最新注意力 | BiFormer：视觉变换器与双层路由注意力
04 一套终生受用的说服模型.pdf
05-17
04 一套终生受用的说服模型.pdf
2020届高考语文人生哲理篇写作素材《一道受用终身的测试题》.doc
10-13
标题中的“2020届高考语文人生哲理篇写作素材《一道受用终身的测试题》”指的是一份用于高考语文复习的人生哲理类写作素材，它以一道假设性的问题来引发思考，旨在帮助学生理解并运用人生哲理进行论述。这道测试题是...
很受用的Web创业的10条戒律
09-30
很受用的Web创业的10条戒律
Zookeeper学习中的疑难问题总结，很受用！
10-25
ZooKeeper是一个分布式的，开放源码的分布式应用程序协调服务，是Google的Chubby一个开源的实现，它是集群的管理者，监视着集群中各个节点的状态根据节点提交的反馈进行下一步合理操作。最终，将简单易用的接口和...
YOLOV7改进-对小目标有效的BiFormer注意力机制
毕竟是Shy哥
09-08 1561
如果要在sppcspc后面加一个注意力模块。
突破小目标检测瓶颈：Yolov8引入CVPR 2023 BiFormer，基于动态稀疏注意力构建高效金字塔网络架构
一直在水些技术小文
11-10 1258
CVPR 2023中Yolov8引入BiFormer的创新性设计为小目标检测任务带来了重大突破。动态稀疏注意力和高效金字塔网络的结合使得BiFormer在目标检测领域成为了一颗耀眼的新星。通过本文的介绍和案例演示，我们希望读者能更深入地了解这一引人注目的技术，并期待它在未来的深度学习研究中发挥更大的作用。（注：本文中的示例代码仅为演示用途，实际应用中可能需要根据具体情况进行调整和优化。
BartModel 源码解析
说文科技，做有态度的研究。
10-17 3480
BartModel的代码真的有太多的坑了
芒果YOLOv8改进20：主干Backbone篇BiFormer：顶会CVPR2023即插即用，小目标检测涨点必备，首发原创改进，基于动态查询感知的稀疏注意力机制、构建高效金字塔网络架构
包括YOLOv5、YOLOv7、YOLOv8等模型改进
05-18 4685
YOLOv8代码改进实践｜最新CVPR2023主干BiFormer：即插即用
【YOLOv10改进[注意力]】使用iRMB倒置残差块注意力(2023.8)改进C2f+ 含全部代码和详细修改方式 + 手撕结构图
静谧、淡雅
07-12 1411
【YOLOv10改进[注意力]】使用iRMB倒置残差块注意力(2023.8)改进C2f+ 含全部代码和详细修改方式 + 手撕结构图
YOLOV3翻译
最新发布
smilejfy的博客
07-15 515
我们对 YOLO 进行了一些更新！我们在设计上做了一些小改动，使它变得更好。我们还训练了一个新的网络，它非常强大。在模型上，它比上次的大了一点，但更准确了，不过速度还是很快，不用担心。在 320×320 时，YOLOv3 以 28.2 mAP 在 22 毫秒内运行，与 SSD 一样精确，但速度快三倍。当我们使用旧的 0.5 IOU mAP 检测指标时，YOLOv3 的表现相当不错。
图片标注yolo
JYFZXX的博客
07-12 157
Pycharm软件、待标注的图片。
Mybatis 中受用#{} 与 ${}的区别
04-23
Mybatis 在什么方面受用呢？如果是使用 Mybatis 进行数据库操作的话，它具有以下优点： 1. 灵活的 SQL 映射，可以通过 XML 或注解的方式编写 SQL 语句，并实现动态 SQL。 2. 提供多种查询方式，如分页查询、动态查询等。 3. 采用二级缓存技术，提高数据库访问性能。 4. 与 Spring 等框架无缝集成，方便开发和维护。 5. 易于学习和使用，适合各种规模的项目。

“相关推荐”对你有帮助么？

  • 非常没帮助
  • 没帮助
  • 一般
  • 有帮助
  • 非常有帮助
提交
评论 1
添加红包

请填写红包祝福语或标题

个

红包个数最小为10个

元

红包金额最低5元

当前余额3.43元 前往充值 >
需支付：10.00元
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付元
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明：

1.余额是钱包充值的虚拟货币，按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载，可以购买VIP、付费专栏及课程。

余额充值