RT-DETR改进策略【注意力机制篇】| 2024 PPA 并行补丁感知注意模块，提高小目标关注度
一、本文介绍
本文记录的是
利用
PPA （并行补丁感知注意模块）
改进
RT-DETR
检测精度
，详细说明了优化原因，注意事项等。原论文在红外
小目标检测
任务中，小目标在多次下采样操作中容易丢失关键信息。
PPA模块
通过替代编码器和解码器基本组件中的传统卷积操作，更好地保留小目标的重要信息。
二、PPA 介绍
HCF-Net: Hierarchical Context Fusion Network for Infrared Small Object Detection
2.1 原理
2.1.1 多分支特征提取原理
采用多分支特征提取策略，通过不同分支提取不同尺度和层次的特征。利用局部、全局和串行卷积分支，对输入特征张量进行处理。通过控制 patch size参数实现局部和全局分支的区分，计算非重叠 patch之间的注意力矩阵，实现局部和全局特征提取与交互。在特征提取过程中，还通过一系列操作对特征进行选择和调整权重，最终将三个分支的结果求和得到融合后的特征。
2.1.2 特征融合和注意力原理
在多分支特征提取后，利用注意力机制进行自适应特征增强。注意力模块包括高效的通道注意力和空间注意力组件。首先通过一维通道注意力图和二维空间注意力图对特征进行依次处理，然后经过一系列激活函数、批归一化和 dropout等操作，得到最终输出。
2.2 结构
2.2.1 多分支特征提取结构
-
主要由多分支融合和注意力机制两部分组成。多分支融合部分包括 patch - aware和串联卷积。patch - aware中的参数
p设置为2和4，分别代表局部和全局分支。对于输入特征张量F，先通过点式卷积调整得到F'，然后通过三个分支分别计算F_local、F_global和F_conv，最后将这三个结果求和得到\tilde{F}。
2.2.2 特征融合和注意力结构
-
包括通道注意力和空间注意力组件。
\tilde{F}依次经过一维通道注意力图M_c和二维空间注意力图M_s的处理，通过元素级乘法和后续的激活函数、批归一化等操作，最终得到PPA的输出F''。
-
优势
- 多分支特征提取优势 ：通过多分支策略能够捕获对象的多尺度特征，提高了小目标检测的准确性。不同分支可以关注到不同尺度和层次的信息，避免了单一尺度下可能丢失的小目标特征。
- 特征融合和注意力优势 ：利用注意力机制可以自适应地增强特征，突出小目标的关键信息。通道注意力和空间注意力的结合能够更好地选择和聚焦于与小目标相关的特征，提高网络对小目标的表征能力。
论文：h ttps://arxiv.org/pdf/2403.10778
源码： https://github.com/zhengshuchen/HCFNet
三、PPA 的实现代码
PPA 模块
的实现代码如下：
import math
import torch
import torch.nn as nn
import torch.nn.functional as F
from ultralytics.nn.modules.conv import LightConv
from ultralytics.utils.torch_utils import fuse_conv_and_bn
class SpatialAttentionModule(nn.Module):
def __init__(self):
super(SpatialAttentionModule, self).__init__()
self.conv2d = nn.Conv2d(in_channels=2, out_channels=1, kernel_size=7, stride=1, padding=3)
self.sigmoid = nn.Sigmoid()
def forward(self, x):
avgout = torch.mean(x, dim=1, keepdim=True)
maxout, _ = torch.max(x, dim=1, keepdim=True)
out = torch.cat([avgout, maxout], dim=1)
out = self.sigmoid(self.conv2d(out))
return out * x
class PPA(nn.Module):
def __init__(self, in_features, filters) -> None:
super().__init__()
self.skip = conv_block(in_features=in_features,
out_features=filters,
kernel_size=(1, 1),
padding=(0, 0),
norm_type='bn',
activation=False)
self.c1 = conv_block(in_features=in_features,
out_features=filters,
kernel_size=(3, 3),
padding=(1, 1),
norm_type='bn',
activation=True)
self.c2 = conv_block(in_features=filters,
out_features=filters,
kernel_size=(3, 3),
padding=(1, 1),
norm_type='bn',
activation=True)
self.c3 = conv_block(in_features=filters,
out_features=filters,
kernel_size=(3, 3),
padding=(1, 1),
norm_type='bn',
activation=True)
self.sa = SpatialAttentionModule()
self.cn = ECA(filters)
self.lga2 = LocalGlobalAttention(filters, 2)
self.lga4 = LocalGlobalAttention(filters, 4)
self.bn1 = nn.BatchNorm2d(filters)
self.drop = nn.Dropout2d(0.1)
self.relu = nn.ReLU()
self.gelu = nn.GELU()
def forward(self, x):
x_skip = self.skip(x)
x_lga2 = self.lga2(x_skip)
x_lga4 = self.lga4(x_skip)
x1 = self.c1(x)
x2 = self.c2(x1)
x3 = self.c3(x2)
x = x1 + x2 + x3 + x_skip + x_lga2 + x_lga4
x = self.cn(x)
x = self.sa(x)
x = self.drop(x)
x = self.bn1(x)
x = self.relu(x)
return x
class LocalGlobalAttention(nn.Module):
def __init__(self, output_dim, patch_size):
super().__init__()
self.output_dim = output_dim
self.patch_size = patch_size
self.mlp1 = nn.Linear(patch_size * patch_size, output_dim // 2)
self.norm = nn.LayerNorm(output_dim // 2)
self.mlp2 = nn.Linear(output_dim // 2, output_dim)
self.conv = nn.Conv2d(output_dim, output_dim, kernel_size=1)
self.prompt = torch.nn.parameter.Parameter(torch.randn(output_dim, requires_grad=True))
self.top_down_transform = torch.nn.parameter.Parameter(torch.eye(output_dim), requires_grad=True)
def forward(self, x):
x = x.permute(0, 2, 3, 1)
B, H, W, C = x.shape
P = self.patch_size
# Local branch
local_patches = x.unfold(1, P, P).unfold(2, P, P) # (B, H/P, W/P, P, P, C)
local_patches = local_patches.reshape(B, -1, P * P, C) # (B, H/P*W/P, P*P, C)
local_patches = local_patches.mean(dim=-1) # (B, H/P*W/P, P*P)
local_patches = self.mlp1(local_patches) # (B, H/P*W/P, input_dim // 2)
local_patches = self.norm(local_patches) # (B, H/P*W/P, input_dim // 2)
local_patches = self.mlp2(local_patches) # (B, H/P*W/P, output_dim)
local_attention = F.softmax(local_patches, dim=-1) # (B, H/P*W/P, output_dim)
local_out = local_patches * local_attention # (B, H/P*W/P, output_dim)
cos_sim = F.normalize(local_out, dim=-1) @ F.normalize(self.prompt[None, ..., None], dim=1) # B, N, 1
mask = cos_sim.clamp(0, 1)
local_out = local_out * mask
local_out = local_out @ self.top_down_transform
# Restore shapes
local_out = local_out.reshape(B, H // P, W // P, self.output_dim) # (B, H/P, W/P, output_dim)
local_out = local_out.permute(0, 3, 1, 2)
local_out = F.interpolate(local_out, size=(H, W), mode='bilinear', align_corners=False)
output = self.conv(local_out)
return output
class ECA(nn.Module):
def __init__(self, in_channel, gamma=2, b=1):
super(ECA, self).__init__()
k = int(abs((math.log(in_channel, 2) + b) / gamma))
kernel_size = k if k % 2 else k + 1
padding = kernel_size // 2
self.pool = nn.AdaptiveAvgPool2d(output_size=1)
self.conv = nn.Sequential(
nn.Conv1d(in_channels=1, out_channels=1, kernel_size=kernel_size, padding=padding, bias=False),
nn.Sigmoid()
)
def forward(self, x):
out = self.pool(x)
out = out.view(x.size(0), 1, x.size(1))
out = self.conv(out)
out = out.view(x.size(0), x.size(1), 1, 1)
return out * x
class conv_block(nn.Module):
def __init__(self,
in_features,
out_features,
kernel_size=(3, 3),
stride=(1, 1),
padding=(1, 1),
dilation=(1, 1),
norm_type='bn',
activation=True,
use_bias=True,
groups=1
):
super().__init__()
self.conv = nn.Conv2d(in_channels=in_features,
out_channels=out_features,
kernel_size=kernel_size,
stride=stride,
padding=padding,
dilation=dilation,
bias=use_bias,
groups=groups)
self.norm_type = norm_type
self.act = activation
if self.norm_type == 'gn':
self.norm = nn.GroupNorm(32 if out_features >= 32 else out_features, out_features)
if self.norm_type == 'bn':
self.norm = nn.BatchNorm2d(out_features)
if self.act:
# self.relu = nn.GELU()
self.relu = nn.ReLU(inplace=False)
def forward(self, x):
x = self.conv(x)
if self.norm_type is not None:
x = self.norm(x)
if self.act:
x = self.relu(x)
return x
def autopad(k, p=None, d=1): # kernel, padding, dilation
"""Pad to 'same' shape outputs."""
if d > 1:
k = d * (k - 1) + 1 if isinstance(k, int) else [d * (x - 1) + 1 for x in k] # actual kernel-size
if p is None:
p = k // 2 if isinstance(k, int) else [x // 2 for x in k] # auto-pad
return p
class Conv(nn.Module):
"""Standard convolution with args(ch_in, ch_out, kernel, stride, padding, groups, dilation, activation)."""
default_act = nn.SiLU() # default activation
def __init__(self, c1, c2, k=1, s=1, p=None, g=1, d=1, act=True):
"""Initialize Conv layer with given arguments including activation."""
super().__init__()
self.conv = nn.Conv2d(c1, c2, k, s, autopad(k, p, d), groups=g, dilation=d, bias=False)
self.bn = nn.BatchNorm2d(c2)
self.act = self.default_act if act is True else act if isinstance(act, nn.Module) else nn.Identity()
def forward(self, x):
"""Apply convolution, batch normalization and activation to input tensor."""
return self.act(self.bn(self.conv(x)))
def forward_fuse(self, x):
"""Perform transposed convolution of 2D data."""
return self.act(self.conv(x))
class HGBlock_PPA(nn.Module):
"""
HG_Block of PPHGNetV2 with 2 convolutions and LightConv.
https://github.com/PaddlePaddle/PaddleDetection/blob/develop/ppdet/modeling/backbones/hgnet_v2.py
"""
def __init__(self, c1, cm, c2, k=3, n=6, lightconv=False, shortcut=False, act=nn.ReLU()):
"""Initializes a CSP Bottleneck with 1 convolution using specified input and output channels."""
super().__init__()
block = LightConv if lightconv else Conv
self.m = nn.ModuleList(block(c1 if i == 0 else cm, cm, k=k, act=act) for i in range(n))
self.sc = Conv(c1 + n * cm, c2 // 2, 1, 1, act=act) # squeeze conv
self.ec = Conv(c2 // 2, c2, 1, 1, act=act) # excitation conv
self.add = shortcut and c1 == c2
self.cv = PPA(c2, c2)
def forward(self, x):
"""Forward pass of a PPHGNetV2 backbone layer."""
y = [x]
y.extend(m(y[-1]) for m in self.m)
y = self.cv(self.ec(self.sc(torch.cat(y, 1))))
return y + x if self.add else y
四、创新模块
4.1 改进点⭐
模块改进方法
：直接加入
PPA
（
第五节讲解添加步骤
）。
PPA
模块加入如下：
4.2 改进点⭐
模块改进方法
：基于
PPA模块
的
HGBlock
（
第五节讲解添加步骤
）。
第二种改进方法是对
RT-DETR
中的
HGBlock模块
进行改进，并将
PPA
在加入到
HGBlock
模块中。
改进代码如下：
对
HGBlock
模块进行改进，加入
PPA模块
，并重命名为
HGBlock_PPA
。
class HGBlock_PPA(nn.Module):
"""
HG_Block of PPHGNetV2 with 2 convolutions and LightConv.
https://github.com/PaddlePaddle/PaddleDetection/blob/develop/ppdet/modeling/backbones/hgnet_v2.py
"""
def __init__(self, c1, cm, c2, k=3, n=6, lightconv=False, shortcut=False, act=nn.ReLU()):
"""Initializes a CSP Bottleneck with 1 convolution using specified input and output channels."""
super().__init__()
block = LightConv if lightconv else Conv
self.m = nn.ModuleList(block(c1 if i == 0 else cm, cm, k=k, act=act) for i in range(n))
self.sc = Conv(c1 + n * cm, c2 // 2, 1, 1, act=act) # squeeze conv
self.ec = Conv(c2 // 2, c2, 1, 1, act=act) # excitation conv
self.add = shortcut and c1 == c2
self.cv = PPA(c2, c2)
def forward(self, x):
"""Forward pass of a PPHGNetV2 backbone layer."""
y = [x]
y.extend(m(y[-1]) for m in self.m)
y = self.cv(self.ec(self.sc(torch.cat(y, 1))))
return y + x if self.add else y
注意❗：在
第五小节
中需要声明的模块名称为：
PPA
和
HGBlock_PPA
。
五、添加步骤
5.1 修改一
① 在
ultralytics/nn/
目录下新建
AddModules
文件夹用于存放模块代码
② 在
AddModules
文件夹下新建
PPA.py
，将
第三节
中的代码粘贴到此处
5.2 修改二
在
AddModules
文件夹下新建
__init__.py
（已有则不用新建），在文件内导入模块：
from .PPA import *
5.3 修改三
在
ultralytics/nn/modules/tasks.py
文件中，需要在两处位置添加各模块类名称。
首先：导入模块
其次：在
parse_model函数
中注册
PPA
和
HGBlock_PPA
模块
六、yaml模型文件
6.1 模型改进版本⭐
此处以
ultralytics/cfg/models/rt-detr/rtdetr-l.yaml
为例，在同目录下创建一个用于自己数据集训练的模型文件
rtdetr-l-PPA.yaml
。
将
rtdetr-l.yaml
中的内容复制到
rtdetr-l-PPA.yaml
文件下，修改
nc
数量等于自己数据中目标的数量。
📌 模型的修改方法是将
骨干网络
中的部分
HGBlock模块
替换成
PPA模块
。
# Ultralytics YOLO 🚀, AGPL-3.0 license
# RT-DETR-l object detection model with P3-P5 outputs. For details see https://docs.ultralytics.com/models/rtdetr
# Parameters
nc: 1 # number of classes
scales: # model compound scaling constants, i.e. 'model=yolov8n-cls.yaml' will call yolov8-cls.yaml with scale 'n'
# [depth, width, max_channels]
l: [1.00, 1.00, 1024]
backbone:
# [from, repeats, module, args]
- [-1, 1, HGStem, [32, 48]] # 0-P2/4
- [-1, 6, HGBlock, [48, 128, 3]] # stage 1
- [-1, 1, DWConv, [128, 3, 2, 1, False]] # 2-P3/8
- [-1, 6, HGBlock, [96, 512, 3]] # stage 2
- [-1, 1, DWConv, [512, 3, 2, 1, False]] # 4-P4/16
- [-1, 6, HGBlock, [192, 1024, 5, True, False]] # cm, c2, k, light, shortcut
- [-1, 6, HGBlock, [192, 1024, 5, True, True]]
- [-1, 6, HGBlock, [192, 1024, 5, True, True]] # stage 3
- [-1, 1, DWConv, [1024, 3, 2, 1, False]] # 8-P5/32
- [-1, 6, PPA, [1024]] # stage 4
head:
- [-1, 1, Conv, [256, 1, 1, None, 1, 1, False]] # 10 input_proj.2
- [-1, 1, AIFI, [1024, 8]]
- [-1, 1, Conv, [256, 1, 1]] # 12, Y5, lateral_convs.0
- [-1, 1, nn.Upsample, [None, 2, "nearest"]]
- [7, 1, Conv, [256, 1, 1, None, 1, 1, False]] # 14 input_proj.1
- [[-2, -1], 1, Concat, [1]]
- [-1, 3, RepC3, [256]] # 16, fpn_blocks.0
- [-1, 1, Conv, [256, 1, 1]] # 17, Y4, lateral_convs.1
- [-1, 1, nn.Upsample, [None, 2, "nearest"]]
- [3, 1, Conv, [256, 1, 1, None, 1, 1, False]] # 19 input_proj.0
- [[-2, -1], 1, Concat, [1]] # cat backbone P4
- [-1, 3, RepC3, [256]] # X3 (21), fpn_blocks.1
- [-1, 1, Conv, [256, 3, 2]] # 22, downsample_convs.0
- [[-1, 17], 1, Concat, [1]] # cat Y4
- [-1, 3, RepC3, [256]] # F4 (24), pan_blocks.0
- [-1, 1, Conv, [256, 3, 2]] # 25, downsample_convs.1
- [[-1, 12], 1, Concat, [1]] # cat Y5
- [-1, 3, RepC3, [256]] # F5 (27), pan_blocks.1
- [[21, 24, 27], 1, RTDETRDecoder, [nc]] # Detect(P3, P4, P5)
6.2 模型改进版本⭐
此处以
ultralytics/cfg/models/rt-detr/rtdetr-l.yaml
为例，在同目录下创建一个用于自己数据集训练的模型文件
rtdetr-l-HGBlock_PPA.yaml
。
将
rtdetr-l.yaml
中的内容复制到
rtdetr-l-HGBlock_PPA.yaml
文件下，修改
nc
数量等于自己数据中目标的数量。
📌 模型的修改方法是将
骨干网络
中的
HGBlock模块
替换成
HGBlock_PPA模块
。
# Ultralytics YOLO 🚀, AGPL-3.0 license
# RT-DETR-l object detection model with P3-P5 outputs. For details see https://docs.ultralytics.com/models/rtdetr
# Parameters
nc: 1 # number of classes
scales: # model compound scaling constants, i.e. 'model=yolov8n-cls.yaml' will call yolov8-cls.yaml with scale 'n'
# [depth, width, max_channels]
l: [1.00, 1.00, 1024]
backbone:
# [from, repeats, module, args]
- [-1, 1, HGStem, [32, 48]] # 0-P2/4
- [-1, 6, HGBlock, [48, 128, 3]] # stage 1
- [-1, 1, DWConv, [128, 3, 2, 1, False]] # 2-P3/8
- [-1, 6, HGBlock, [96, 512, 3]] # stage 2
- [-1, 1, DWConv, [512, 3, 2, 1, False]] # 4-P4/16
- [-1, 6, HGBlock, [192, 1024, 5, True, False]] # cm, c2, k, light, shortcut
- [-1, 6, HGBlock, [192, 1024, 5, True, True]]
- [-1, 6, HGBlock, [192, 1024, 5, True, True]] # stage 3
- [-1, 1, DWConv, [1024, 3, 2, 1, False]] # 8-P5/32
- [-1, 6, HGBlock_PPA, [384, 2048, 5, True, False]] # stage 4
head:
- [-1, 1, Conv, [256, 1, 1, None, 1, 1, False]] # 10 input_proj.2
- [-1, 1, AIFI, [1024, 8]]
- [-1, 1, Conv, [256, 1, 1]] # 12, Y5, lateral_convs.0
- [-1, 1, nn.Upsample, [None, 2, "nearest"]]
- [7, 1, Conv, [256, 1, 1, None, 1, 1, False]] # 14 input_proj.1
- [[-2, -1], 1, Concat, [1]]
- [-1, 3, RepC3, [256]] # 16, fpn_blocks.0
- [-1, 1, Conv, [256, 1, 1]] # 17, Y4, lateral_convs.1
- [-1, 1, nn.Upsample, [None, 2, "nearest"]]
- [3, 1, Conv, [256, 1, 1, None, 1, 1, False]] # 19 input_proj.0
- [[-2, -1], 1, Concat, [1]] # cat backbone P4
- [-1, 3, RepC3, [256]] # X3 (21), fpn_blocks.1
- [-1, 1, Conv, [256, 3, 2]] # 22, downsample_convs.0
- [[-1, 17], 1, Concat, [1]] # cat Y4
- [-1, 3, RepC3, [256]] # F4 (24), pan_blocks.0
- [-1, 1, Conv, [256, 3, 2]] # 25, downsample_convs.1
- [[-1, 12], 1, Concat, [1]] # cat Y5
- [-1, 3, RepC3, [256]] # F5 (27), pan_blocks.1
- [[21, 24, 27], 1, RTDETRDecoder, [nc]] # Detect(P3, P4, P5)
七、成功运行结果
打印网络模型可以看到
PPA
和
HGBlock_PPA
已经加入到模型中，并可以进行训练了。
rtdetr-l-PPA ：
rtdetr-l-PPA summary: 854 layers, 233,658,931 parameters, 233,658,931 gradients, 254.3 GFLOPs
from n params module arguments
0 -1 1 25248 ultralytics.nn.modules.block.HGStem [3, 32, 48]
1 -1 6 155072 ultralytics.nn.modules.block.HGBlock [48, 48, 128, 3, 6]
2 -1 1 1408 ultralytics.nn.modules.conv.DWConv [128, 128, 3, 2, 1, False]
3 -1 6 839296 ultralytics.nn.modules.block.HGBlock [128, 96, 512, 3, 6]
4 -1 1 5632 ultralytics.nn.modules.conv.DWConv [512, 512, 3, 2, 1, False]
5 -1 6 1695360 ultralytics.nn.modules.block.HGBlock [512, 192, 1024, 5, 6, True, False]
6 -1 6 2055808 ultralytics.nn.modules.block.HGBlock [1024, 192, 1024, 5, 6, True, True]
7 -1 6 2055808 ultralytics.nn.modules.block.HGBlock [1024, 192, 1024, 5, 6, True, True]
8 -1 1 11264 ultralytics.nn.modules.conv.DWConv [1024, 1024, 3, 2, 1, False]
9 -1 6 207821424 ultralytics.nn.AddModules.PPA.PPA [1024, 1024]
10 -1 1 262656 ultralytics.nn.modules.conv.Conv [1024, 256, 1, 1, None, 1, 1, False]
11 -1 1 789760 ultralytics.nn.modules.transformer.AIFI [256, 1024, 8]
12 -1 1 66048 ultralytics.nn.modules.conv.Conv [256, 256, 1, 1]
13 -1 1 0 torch.nn.modules.upsampling.Upsample [None, 2, 'nearest']
14 7 1 262656 ultralytics.nn.modules.conv.Conv [1024, 256, 1, 1, None, 1, 1, False]
15 [-2, -1] 1 0 ultralytics.nn.modules.conv.Concat [1]
16 -1 3 2232320 ultralytics.nn.modules.block.RepC3 [512, 256, 3]
17 -1 1 66048 ultralytics.nn.modules.conv.Conv [256, 256, 1, 1]
18 -1 1 0 torch.nn.modules.upsampling.Upsample [None, 2, 'nearest']
19 3 1 131584 ultralytics.nn.modules.conv.Conv [512, 256, 1, 1, None, 1, 1, False]
20 [-2, -1] 1 0 ultralytics.nn.modules.conv.Concat [1]
21 -1 3 2232320 ultralytics.nn.modules.block.RepC3 [512, 256, 3]
22 -1 1 590336 ultralytics.nn.modules.conv.Conv [256, 256, 3, 2]
23 [-1, 17] 1 0 ultralytics.nn.modules.conv.Concat [1]
24 -1 3 2232320 ultralytics.nn.modules.block.RepC3 [512, 256, 3]
25 -1 1 590336 ultralytics.nn.modules.conv.Conv [256, 256, 3, 2]
26 [-1, 12] 1 0 ultralytics.nn.modules.conv.Concat [1]
27 -1 3 2232320 ultralytics.nn.modules.block.RepC3 [512, 256, 3]
28 [21, 24, 27] 1 7303907 ultralytics.nn.modules.head.RTDETRDecoder [1, [256, 256, 256]]
rtdetr-l-PPA summary: 854 layers, 233,658,931 parameters, 233,658,931 gradients, 254.3 GFLOPs
rtdetr-l-HGBlock_PPA ：
rtdetr-l-HGBlock_PPA summary: 720 layers, 171,287,853 parameters, 171,287,853 gradients, 209.2 GFLOPs
from n params module arguments
0 -1 1 25248 ultralytics.nn.modules.block.HGStem [3, 32, 48]
1 -1 6 155072 ultralytics.nn.modules.block.HGBlock [48, 48, 128, 3, 6]
2 -1 1 1408 ultralytics.nn.modules.conv.DWConv [128, 128, 3, 2, 1, False]
3 -1 6 839296 ultralytics.nn.modules.block.HGBlock [128, 96, 512, 3, 6]
4 -1 1 5632 ultralytics.nn.modules.conv.DWConv [512, 512, 3, 2, 1, False]
5 -1 6 1695360 ultralytics.nn.modules.block.HGBlock [512, 192, 1024, 5, 6, True, False]
6 -1 6 2055808 ultralytics.nn.modules.block.HGBlock [1024, 192, 1024, 5, 6, True, True]
7 -1 6 2055808 ultralytics.nn.modules.block.HGBlock [1024, 192, 1024, 5, 6, True, True]
8 -1 1 11264 ultralytics.nn.modules.conv.DWConv [1024, 1024, 3, 2, 1, False]
9 -1 6 145188202 ultralytics.nn.AddModules.PPA.HGBlock_PPA [1024, 384, 2048, 5, 6, True, False]
10 -1 1 524800 ultralytics.nn.modules.conv.Conv [2048, 256, 1, 1, None, 1, 1, False]
11 -1 1 789760 ultralytics.nn.modules.transformer.AIFI [256, 1024, 8]
12 -1 1 66048 ultralytics.nn.modules.conv.Conv [256, 256, 1, 1]
13 -1 1 0 torch.nn.modules.upsampling.Upsample [None, 2, 'nearest']
14 7 1 262656 ultralytics.nn.modules.conv.Conv [1024, 256, 1, 1, None, 1, 1, False]
15 [-2, -1] 1 0 ultralytics.nn.modules.conv.Concat [1]
16 -1 3 2232320 ultralytics.nn.modules.block.RepC3 [512, 256, 3]
17 -1 1 66048 ultralytics.nn.modules.conv.Conv [256, 256, 1, 1]
18 -1 1 0 torch.nn.modules.upsampling.Upsample [None, 2, 'nearest']
19 3 1 131584 ultralytics.nn.modules.conv.Conv [512, 256, 1, 1, None, 1, 1, False]
20 [-2, -1] 1 0 ultralytics.nn.modules.conv.Concat [1]
21 -1 3 2232320 ultralytics.nn.modules.block.RepC3 [512, 256, 3]
22 -1 1 590336 ultralytics.nn.modules.conv.Conv [256, 256, 3, 2]
23 [-1, 17] 1 0 ultralytics.nn.modules.conv.Concat [1]
24 -1 3 2232320 ultralytics.nn.modules.block.RepC3 [512, 256, 3]
25 -1 1 590336 ultralytics.nn.modules.conv.Conv [256, 256, 3, 2]
26 [-1, 12] 1 0 ultralytics.nn.modules.conv.Concat [1]
27 -1 3 2232320 ultralytics.nn.modules.block.RepC3 [512, 256, 3]
28 [21, 24, 27] 1 7303907 ultralytics.nn.modules.head.RTDETRDecoder [1, [256, 256, 256]]
rtdetr-l-HGBlock_PPA summary: 720 layers, 171,287,853 parameters, 171,287,853 gradients, 209.2 GFLOPs