1，本文介绍
Transformer 模型具备许多适合构建强大数据驱动模型的特性，比如能够捕获数据中的远程依赖关系。与卷积操作的局部特性不同，注意力机制的全局接收场使得视觉 Transformer 能够处理远程依赖。引入稀疏注意力可以减少计算负担。由于不同语义区域的查询会关注不同的键值对，强制所有查询处理相同的令牌组可能不够理想。一种改进的方法是通过每个查询的本地上下文预测注意力偏移量，从而减少计算复杂性。为了更高效地定位有价值的键值，可以使用区域到区域路由策略，这在粗粒度的区域级别过滤掉不相关的键值，而不是在细粒度的令牌级别。使用 BRA（Bidirectional Region Attention）作为核心组件，我们提出了 BiFormer，这是一种通用的视觉 Transformer 骨干。BRA 使 BiFormer 能够以内容感知的方式处理每个查询最相关的键/值令牌，从而在计算性能和效率之间实现更好的平衡。
关于BiFormer的详细介绍可以看论文：https://arxiv.org/pdf/2303.08810.pdf
本文将讲解如何将BiFormer融合进yolov8
话不多说，上代码！
2， 将BiFormer融合进yolov8
2.1 步骤一
找到如下的目录'ultralytics/nn/modules'，然后在这个目录下创建一个BiFormer.py文件，文件名字可以根据你自己的习惯起，然后将BiFormer的核心代码复制进去
###################### BiLevelRoutingAttention #### AI&CV start ###############################
from einops import rearrange
import torch.nn.functional as F
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) -> 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 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 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 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, num_heads=8, n_win=7, qk_dim=None, qk_scale=None,
kv_per_win=4, kv_downsample_ratio=4, kv_downsample_kernel='ada_avgpool', kv_downsample_mode='identity',
topk=4, param_attention="qkv", param_routing=False, diff_routing=False, soft_routing=False,
side_dwconv=5,
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
"""
# 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()
#print(N)
# print(H)
# print(W)
# print(self.n_win)
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 out
class BiFormerBlock(nn.Module):
def __init__(self, dim, drop_path=0.,
num_heads=8, n_win=7, qk_dim=None, qk_scale=None,
kv_per_win=4, kv_downsample_ratio=4, kv_downsample_kernel=None, kv_downsample_mode='ada_avgpool',
topk=4, param_attention="qkvo", param_routing=False, diff_routing=False, soft_routing=False,
mlp_ratio=2, mlp_dwconv=False,
side_dwconv=3, before_attn_dwconv=3, pre_norm=True, auto_pad=True):
super().__init__()
qk_dim = qk_dim or dim
self.attn = BiLevelRoutingAttention(dim=dim, num_heads=num_heads, n_win=n_win, qk_dim=qk_dim,
qk_scale=qk_scale, kv_per_win=kv_per_win,
kv_downsample_ratio=kv_downsample_ratio,
kv_downsample_kernel=kv_downsample_kernel,
kv_downsample_mode=kv_downsample_mode,
topk=topk, param_attention=param_attention, param_routing=param_routing,
diff_routing=diff_routing, soft_routing=soft_routing,
side_dwconv=side_dwconv,
auto_pad=auto_pad)
def forward(self, x):
"""
x: NCHW tensor
"""
# permute to NHWC tensor for attention & mlp
x = x.permute(0, 2, 3, 1) # (N, C, H, W) -> (N, H, W, C)
x = self.attn(x)# (N, H, W, C)
# permute back
x = x.permute(0, 3, 1, 2) # (N, H, W, C) -> (N, C, H, W)
return x
class C2f_BiLevelRoutingAttention(nn.Module):
def __init__(self, c1, c2, n=1, shortcut=False, g=1, e=0.5): # ch_in, ch_out, number, shortcut, groups, expansion
super().__init__()
self.c = int(c2 * e) # hidden channels
self.cv1 = Conv(c1, 2 * self.c, 1, 1)
self.cv2 = Conv((2 + n) * self.c, c2, 1) # optional act=FReLU(c2)
self.m = nn.ModuleList(BiFormerBlock(self.c) for _ in range(n))
def forward(self, x):
y = list(self.cv1(x).chunk(2, 1))
y.extend(m(y[-1]) for m in self.m)
return self.cv2(torch.cat(y, 1))
class C3_BiLevelRoutingAttention(nn.Module):
# CSP Bottleneck with 3 convolutions
def __init__(self, c1, c2, n=1, shortcut=True, g=1, e=0.5): # ch_in, ch_out, number, shortcut, groups, expansion
super().__init__()
c_ = int(c2 * e) # hidden channels
self.cv1 = Conv(c1, c_, 1, 1)
self.cv2 = Conv(c1, c_, 1, 1)
self.cv3 = Conv(2 * c_, c2, 1) # optional act=FReLU(c2)
self.m = nn.Sequential(*(BiFormerBlock(c_) for _ in range(n)))
def forward(self, x):
return self.cv3(torch.cat((self.m(self.cv1(x)), self.cv2(x)), 1))
###################### BiLevelRoutingAttention #### end ###############################2.2 步骤二
在task.py导入我们的模块
2.3 步骤三
在task.py的parse_model方法里面注册我们的模块
注意，共需要在二个位置进行添加
到此注册成功,复制后面的yaml文件直接运行即可
此处我有三种添加方式，大家可以参考，具体关于每个数据集位置不同，效果不同，大家可以自行调试
yaml文件一 BiFormerBlock
# Ultralytics YOLO 🚀, GPL-3.0 license
# YOLOv8 object detection model with P3-P5 outputs. For Usage examples see https://docs.ultralytics.com/tasks/detect
# Parameters
nc: 1 # number of classes
scales: # model compound scaling constants, i.e. 'model=yolov8n.yaml' will call yolov8.yaml with scale 'n'
# [depth, width, max_channels]
n: [0.33, 0.25, 1024] # YOLOv8n summary: 225 layers, 3157200 parameters, 3157184 gradients, 8.9 GFLOPs
s: [0.33, 0.50, 1024] # YOLOv8s summary: 225 layers, 11166560 parameters, 11166544 gradients, 28.8 GFLOPs
m: [0.67, 0.75, 768] # YOLOv8m summary: 295 layers, 25902640 parameters, 25902624 gradients, 79.3 GFLOPs
l: [1.00, 1.00, 512] # YOLOv8l summary: 365 layers, 43691520 parameters, 43691504 gradients, 165.7 GFLOPs
x: [1.00, 1.25, 512] # YOLOv8x summary: 365 layers, 68229648 parameters, 68229632 gradients, 258.5 GFLOPs
# YOLOv8.0n 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, 3, C2f, [128, True]]
- [-1, 1, Conv, [256, 3, 2]] # 3-P3/8
- [-1, 6, C2f, [256, True]]
- [-1, 1, Conv, [512, 3, 2]] # 5-P4/16
- [-1, 6, C2f, [512, True]]
- [-1, 1, Conv, [1024, 3, 2]] # 7-P5/32
- [-1, 3, C2f, [1024, True]]
- [-1, 1, SPPF, [1024, 5]] # 9
# YOLOv8.0n head
head:
- [-1, 1, nn.Upsample, [None, 2, 'nearest']]
- [[-1, 6], 1, Concat, [1]] # cat backbone P4
- [-1, 3, C2f, [512]] # 12
- [-1, 1, BiFormerBlock, [512]] # 13
- [-1, 1, nn.Upsample, [None, 2, 'nearest']]
- [[-1, 4], 1, Concat, [1]] # cat backbone P3
- [-1, 3, C2f, [256]] # 16 (P3/8-small)
- [-1, 1, BiFormerBlock, [256]] # 17
- [-1, 1, Conv, [256, 3, 2]]
- [[-1, 12], 1, Concat, [1]] # cat head P4
- [-1, 3, C2f, [512]] # 20 (P4/16-medium)
- [-1, 1, BiFormerBlock, [512]] # 21
- [-1, 1, Conv, [512, 3, 2]]
- [[-1, 9], 1, Concat, [1]] # cat head P5
- [-1, 3, C2f, [1024]] # 24 (P5/32-large)
- [-1, 1, BiFormerBlock, [1024]] # 25
- [[17, 21, 25], 1, Detect, [nc]] # Detect(P3, P4, P5)yaml文件二 C2f_BiLevelRoutingAttention
# Ultralytics YOLO 🚀, GPL-3.0 license
# YOLOv8 object detection model with P3-P5 outputs. For Usage examples see https://docs.ultralytics.com/tasks/detect
# Parameters
nc: 1 # number of classes
scales: # model compound scaling constants, i.e. 'model=yolov8n.yaml' will call yolov8.yaml with scale 'n'
# [depth, width, max_channels]
n: [0.33, 0.25, 1024] # YOLOv8n summary: 225 layers, 3157200 parameters, 3157184 gradients, 8.9 GFLOPs
s: [0.33, 0.50, 1024] # YOLOv8s summary: 225 layers, 11166560 parameters, 11166544 gradients, 28.8 GFLOPs
m: [0.67, 0.75, 768] # YOLOv8m summary: 295 layers, 25902640 parameters, 25902624 gradients, 79.3 GFLOPs
l: [1.00, 1.00, 512] # YOLOv8l summary: 365 layers, 43691520 parameters, 43691504 gradients, 165.7 GFLOPs
x: [1.00, 1.25, 512] # YOLOv8x summary: 365 layers, 68229648 parameters, 68229632 gradients, 258.5 GFLOPs
# YOLOv8.0n 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, 3, C2f, [128, True]]
- [-1, 1, Conv, [256, 3, 2]] # 3-P3/8
- [-1, 6, C2f, [256, True]]
- [-1, 1, Conv, [512, 3, 2]] # 5-P4/16
- [-1, 6, C2f, [512, True]]
- [-1, 1, Conv, [1024, 3, 2]] # 7-P5/32
- [-1, 3, C2f, [1024, True]]
- [-1, 1, SPPF, [1024, 5]] # 9
# YOLOv8.0n head
head:
- [-1, 1, nn.Upsample, [None, 2, 'nearest']]
- [[-1, 6], 1, Concat, [1]] # cat backbone P4
- [-1, 3, C2f_BiLevelRoutingAttention, [512]] # 12
- [-1, 1, nn.Upsample, [None, 2, 'nearest']]
- [[-1, 4], 1, Concat, [1]] # cat backbone P3
- [-1, 3, C2f_BiLevelRoutingAttention, [256]] # 15 (P3/8-small)
- [-1, 1, Conv, [256, 3, 2]]
- [[-1, 12], 1, Concat, [1]] # cat head P4
- [-1, 3, C2f_BiLevelRoutingAttention, [512]] # 18 (P4/16-medium)
- [-1, 1, Conv, [512, 3, 2]]
- [[-1, 9], 1, Concat, [1]] # cat head P5
- [-1, 3, C2f_BiLevelRoutingAttention, [1024]] # 21 (P5/32-large)
- [[15, 18, 21], 1, Detect, [nc]] # Detect(P3, P4, P5)yaml文件三 C3_BiLevelRoutingAttention
# Ultralytics YOLO 🚀, GPL-3.0 license
# YOLOv8 object detection model with P3-P5 outputs. For Usage examples see https://docs.ultralytics.com/tasks/detect
# Parameters
nc: 1 # number of classes
scales: # model compound scaling constants, i.e. 'model=yolov8n.yaml' will call yolov8.yaml with scale 'n'
# [depth, width, max_channels]
n: [0.33, 0.25, 1024] # YOLOv8n summary: 225 layers, 3157200 parameters, 3157184 gradients, 8.9 GFLOPs
s: [0.33, 0.50, 1024] # YOLOv8s summary: 225 layers, 11166560 parameters, 11166544 gradients, 28.8 GFLOPs
m: [0.67, 0.75, 768] # YOLOv8m summary: 295 layers, 25902640 parameters, 25902624 gradients, 79.3 GFLOPs
l: [1.00, 1.00, 512] # YOLOv8l summary: 365 layers, 43691520 parameters, 43691504 gradients, 165.7 GFLOPs
x: [1.00, 1.25, 512] # YOLOv8x summary: 365 layers, 68229648 parameters, 68229632 gradients, 258.5 GFLOPs
# YOLOv8.0n 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, 3, C2f, [128, True]]
- [-1, 1, Conv, [256, 3, 2]] # 3-P3/8
- [-1, 6, C2f, [256, True]]
- [-1, 1, Conv, [512, 3, 2]] # 5-P4/16
- [-1, 6, C2f, [512, True]]
- [-1, 1, Conv, [1024, 3, 2]] # 7-P5/32
- [-1, 3, C2f, [1024, True]]
- [-1, 1, SPPF, [1024, 5]] # 9
# YOLOv8.0n head
head:
- [-1, 1, nn.Upsample, [None, 2, 'nearest']]
- [[-1, 6], 1, Concat, [1]] # cat backbone P4
- [-1, 3, C3_BiLevelRoutingAttention, [512]] # 12
- [-1, 1, nn.Upsample, [None, 2, 'nearest']]
- [[-1, 4], 1, Concat, [1]] # cat backbone P3
- [-1, 3, C3_BiLevelRoutingAttention, [256]] # 15 (P3/8-small)
- [-1, 1, Conv, [256, 3, 2]]
- [[-1, 12], 1, Concat, [1]] # cat head P4
- [-1, 3, C3_BiLevelRoutingAttention, [512]] # 18 (P4/16-medium)
- [-1, 1, Conv, [512, 3, 2]]
- [[-1, 9], 1, Concat, [1]] # cat head P5
- [-1, 3, C3_BiLevelRoutingAttention, [1024]] # 21 (P5/32-large)
- [[15, 18, 21], 1, Detect, [nc]] # Detect(P3, P4, P5)不知不觉已经看完了哦，动动小手留个点赞吧--_--
2万+
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
