RT-DETR改进策略【卷积层】| RCS-OSA 通道混洗的重参数化卷积 二次创新ResNetLayer
一、本文介绍
本文记录的是
利用
RCS-OSA
模块优化
RT-DETR
的目标检测网络模型
。
RCS-OSA
的全称为
Reparameterized Convolution based on channel Shuffle - One - Shot Aggregation
，即基于
通道混洗的重参数化卷积 - 一次性聚合
。
优势在于
RCS模块
的重复堆叠确保了特征的重用，并增强了相邻层特征之间不同通道的信息流，从而可以提取更丰富的特征信息，并降低了内存访问成本
。本文将深入分析
RCS-OSA模块
的特点，结合
RT-DETR
，实现精准涨点。
二、RCS-OSA介绍
RCS-YOLO: A Fast and High-Accuracy Object Detector for Brain Tumor Detection
为克服
DenseNet
中密集连接的低效问题，同时为了在
YOLO架构
中更好地进行特征提取和信息融合，提高计算效率和检测性能，设计了
RCS-OSA模块
。
2.1 原理
2.1.1 OSA模块
One-Shot Aggregation (OSA)模块
通过用多感受野表示多样化特征，并在最后特征图中仅聚合一次所有特征来克服DenseNet的低效。
2.1.2 RCS模块
将
RCS
与
OSA
结合，
RCS模块
的重复堆叠确保了特征的重用，并增强了相邻层特征之间不同通道的信息流。
RCS
的结构。(a)培训阶段的
RepVGG
。(b)模型推理（或部署）期间的
RepConv
。带有黑色外边框的矩形表示张量的特定模操作；渐变颜色的矩形表示张量的特定特征，矩形的宽度表示张量的通道。
2.2 结构
(1). 通道拆分与多分支构建
- 给定输入张量的特征维度为 C × H × W C\times H\times W C × H × W ，经过通道拆分操作（channel split operator）后，被分成两个维度相等（ C × H × W C\times H\times W C × H × W ）的不同通道方向的张量。
- 对于其中一个张量，使用恒等分支（identity branch）、 1 × 1 1\times1 1 × 1 卷积和 3 × 3 3\times3 3 × 3 卷积来构建训练时的RCS。
(2). 结构重参数化
- 在推理阶段，恒等分支、 1 × 1 1\times1 1 × 1 卷积和 3 × 3 3\times3 3 × 3 卷积通过结构重参数化被转换为 3 × 3 3\times3 3 × 3 的RepConv。这种多分支拓扑架构在训练时可以学习丰富的特征信息，而简化的单分支架构在推理时可以节省内存消耗，实现快速推理。
(3). 通道拼接与通道混洗
- 对其中一个张量进行多分支训练后，将其与另一个张量以通道方式拼接（concatenated in a channel - wise manner）。
- 同时应用通道混洗操作（channel shuffle operator）来增强两个张量之间的信息融合，使得能够以较低的计算复杂度实现输入的不同通道特征之间的深度测量。
2.3 优势
- 语义信息提取 ：在骨干网络和颈部网络的不同阶段使用不同数量的堆叠RCS实现语义信息提取。
- 降低内存成本 ：保持相同数量的输入通道和最少的输出通道，从而降低内存访问成本（MAC）。
- 提高计算效率 ：与Efficient Layer Aggregation Networks (ELAN)相比，FLOPs降低近50%，MAC也降低，实现了高精度快速推理。
论文： https://arxiv.org/ftp/arxiv/papers/2307/2307.16412.pdf
源码： https://github.com/mkang315/RCS-YOLO
三、RCSOSA的实现代码
RCSOSA模块
的实现代码如下：
import torch.nn as nn
import torch
import torch.nn.functional as F
import numpy as np
import math
# build RepVGG block
# -----------------------------
def conv_bn(in_channels, out_channels, kernel_size, stride, padding, groups=1):
result = nn.Sequential()
result.add_module('conv', nn.Conv2d(in_channels=in_channels, out_channels=out_channels,
kernel_size=kernel_size, stride=stride, padding=padding, groups=groups,
bias=False))
result.add_module('bn', nn.BatchNorm2d(num_features=out_channels))
return result
class SEBlock(nn.Module):
def __init__(self, input_channels):
super(SEBlock, self).__init__()
internal_neurons = input_channels // 8
self.down = nn.Conv2d(in_channels=input_channels, out_channels=internal_neurons, kernel_size=1, stride=1,
bias=True)
self.up = nn.Conv2d(in_channels=internal_neurons, out_channels=input_channels, kernel_size=1, stride=1,
bias=True)
self.input_channels = input_channels
def forward(self, inputs):
x = F.avg_pool2d(inputs, kernel_size=inputs.size(3))
x = self.down(x)
x = F.relu(x)
x = self.up(x)
x = torch.sigmoid(x)
x = x.view(-1, self.input_channels, 1, 1)
return inputs * x
class RepVGG(nn.Module):
def __init__(self, in_channels, out_channels, kernel_size=3,
stride=1, padding=1, dilation=1, groups=1, padding_mode='zeros', deploy=False, use_se=False):
super(RepVGG, self).__init__()
self.deploy = deploy
self.groups = groups
self.in_channels = in_channels
padding_11 = padding - kernel_size // 2
self.nonlinearity = nn.SiLU()
# self.nonlinearity = nn.ReLU()
if use_se:
self.se = SEBlock(out_channels, internal_neurons=out_channels // 16)
else:
self.se = nn.Identity()
if deploy:
self.rbr_reparam = nn.Conv2d(in_channels=in_channels, out_channels=out_channels, kernel_size=kernel_size,
stride=stride,
padding=padding, dilation=dilation, groups=groups, bias=True,
padding_mode=padding_mode)
else:
self.rbr_identity = nn.BatchNorm2d(
num_features=in_channels) if out_channels == in_channels and stride == 1 else None
self.rbr_dense = conv_bn(in_channels=in_channels, out_channels=out_channels, kernel_size=kernel_size,
stride=stride, padding=padding, groups=groups)
self.rbr_1x1 = conv_bn(in_channels=in_channels, out_channels=out_channels, kernel_size=1, stride=stride,
padding=padding_11, groups=groups)
# print('RepVGG Block, identity = ', self.rbr_identity)
def get_equivalent_kernel_bias(self):
kernel3x3, bias3x3 = self._fuse_bn_tensor(self.rbr_dense)
kernel1x1, bias1x1 = self._fuse_bn_tensor(self.rbr_1x1)
kernelid, biasid = self._fuse_bn_tensor(self.rbr_identity)
return kernel3x3 + self._pad_1x1_to_3x3_tensor(kernel1x1) + kernelid, bias3x3 + bias1x1 + biasid
def _pad_1x1_to_3x3_tensor(self, kernel1x1):
if kernel1x1 is None:
return 0
else:
return torch.nn.functional.pad(kernel1x1, [1, 1, 1, 1])
def _fuse_bn_tensor(self, branch):
if branch is None:
return 0, 0
if isinstance(branch, nn.Sequential):
kernel = branch.conv.weight
running_mean = branch.bn.running_mean
running_var = branch.bn.running_var
gamma = branch.bn.weight
beta = branch.bn.bias
eps = branch.bn.eps
else:
assert isinstance(branch, nn.BatchNorm2d)
if not hasattr(self, 'id_tensor'):
input_dim = self.in_channels // self.groups
kernel_value = np.zeros((self.in_channels, input_dim, 3, 3), dtype=np.float32)
for i in range(self.in_channels):
kernel_value[i, i % input_dim, 1, 1] = 1
self.id_tensor = torch.from_numpy(kernel_value).to(branch.weight.device)
kernel = self.id_tensor
running_mean = branch.running_mean
running_var = branch.running_var
gamma = branch.weight
beta = branch.bias
eps = branch.eps
std = (running_var + eps).sqrt()
t = (gamma / std).reshape(-1, 1, 1, 1)
return kernel * t, beta - running_mean * gamma / std
def forward(self, inputs):
if hasattr(self, 'rbr_reparam'):
return self.nonlinearity(self.se(self.rbr_reparam(inputs)))
if self.rbr_identity is None:
id_out = 0
else:
id_out = self.rbr_identity(inputs)
return self.nonlinearity(self.se(self.rbr_dense(inputs) + self.rbr_1x1(inputs) + id_out))
def fusevggforward(self, x):
return self.nonlinearity(self.rbr_dense(x))
# RepVGG block end
# -----------------------------
class SR(nn.Module):
# Shuffle RepVGG
def __init__(self, c1, c2):
super().__init__()
c1_ = int(c1 // 2)
c2_ = int(c2 // 2)
self.repconv = RepVGG(c1_, c2_)
def forward(self, x):
x1, x2 = x.chunk(2, dim=1)
out = torch.cat((x1, self.repconv(x2)), dim=1)
out = self.channel_shuffle(out, 2)
return out
def channel_shuffle(self, x, groups):
batchsize, num_channels, height, width = x.data.size()
channels_per_group = num_channels // groups
x = x.view(batchsize, groups, channels_per_group, height, width)
x = torch.transpose(x, 1, 2).contiguous()
x = x.view(batchsize, -1, height, width)
return x
def make_divisible(x, divisor):
# Returns nearest x divisible by divisor
if isinstance(divisor, torch.Tensor):
divisor = int(divisor.max()) # to int
return math.ceil(x / divisor) * divisor
class RCSOSA(nn.Module):
# VoVNet with Res Shuffle RepVGG
def __init__(self, c1, c2, n=1, se=False, e=0.5, stackrep=True):
super().__init__()
n_ = n // 2
c_ = make_divisible(int(c1 * e), 8)
# self.conv1 = Conv(c1, c_)
self.conv1 = RepVGG(c1, c_)
self.conv3 = RepVGG(int(c_ * 3), c2)
self.sr1 = nn.Sequential(*[SR(c_, c_) for _ in range(n_)])
self.sr2 = nn.Sequential(*[SR(c_, c_) for _ in range(n_)])
self.se = None
if se:
self.se = SEBlock(c2)
def forward(self, x):
x1 = self.conv1(x)
x2 = self.sr1(x1)
x3 = self.sr2(x2)
x = torch.cat((x1, x2, x3), 1)
return self.conv3(x) if self.se is None else self.se(self.conv3(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 ResNetBlock(nn.Module):
"""ResNet block with standard convolution layers."""
def __init__(self, c1, c2, s=1, e=4):
"""Initialize convolution with given parameters."""
super().__init__()
c3 = e * c2
self.cv1 = Conv(c1, c2, k=1, s=1, act=True)
self.cv2 = Conv(c2, c2, k=3, s=s, p=1, act=True)
self.cv3 = RCSOSA(c2, c3)
self.shortcut = nn.Sequential(Conv(c1, c3, k=1, s=s, act=False)) if s != 1 or c1 != c3 else nn.Identity()
def forward(self, x):
"""Forward pass through the ResNet block."""
return F.relu(self.cv3(self.cv2(self.cv1(x))) + self.shortcut(x))
class ResNetLayer_RCSOSA(nn.Module):
"""ResNet layer with multiple ResNet blocks."""
def __init__(self, c1, c2, s=1, is_first=False, n=1, e=4):
"""Initializes the ResNetLayer given arguments."""
super().__init__()
self.is_first = is_first
if self.is_first:
self.layer = nn.Sequential(
Conv(c1, c2, k=7, s=2, p=3, act=True), nn.MaxPool2d(kernel_size=3, stride=2, padding=1)
)
else:
blocks = [ResNetBlock(c1, c2, s, e=e)]
blocks.extend([ResNetBlock(e * c2, c2, 1, e=e) for _ in range(n - 1)])
self.layer = nn.Sequential(*blocks)
def forward(self, x):
"""Forward pass through the ResNet layer."""
return self.layer(x)
四、创新模块
4.1 改进点1⭐
模块改进方法
：直接加入
RCSOSA 模块
（
第五节讲解添加步骤
）。
RCSOSA 模块
添加后如下：
4.2 改进点2⭐
模块改进方法
：基于
RCSOSA 模块
的
ResNetLayer
（
第五节讲解添加步骤
）。
第二种改进方法是对
RT-DETR
中的
ResNetLayer模块
进行改进，并将
RCSOSA
在加入到
ResNetLayer
模块中。
改进代码如下：
将
RCSOSA
加入到
ResNetBlock
模块中，并将
ResNetLayer
重命名为
ResNetLayer_RCSOSA
class ResNetBlock(nn.Module):
"""ResNet block with standard convolution layers."""
def __init__(self, c1, c2, s=1, e=4):
"""Initialize convolution with given parameters."""
super().__init__()
c3 = e * c2
self.cv1 = Conv(c1, c2, k=1, s=1, act=True)
self.cv2 = Conv(c2, c2, k=3, s=s, p=1, act=True)
self.cv3 = RCSOSA(c2, c3)
self.shortcut = nn.Sequential(Conv(c1, c3, k=1, s=s, act=False)) if s != 1 or c1 != c3 else nn.Identity()
def forward(self, x):
"""Forward pass through the ResNet block."""
return F.relu(self.cv3(self.cv2(self.cv1(x))) + self.shortcut(x))
class ResNetLayer_RCSOSA(nn.Module):
"""ResNet layer with multiple ResNet blocks."""
def __init__(self, c1, c2, s=1, is_first=False, n=1, e=4):
"""Initializes the ResNetLayer given arguments."""
super().__init__()
self.is_first = is_first
if self.is_first:
self.layer = nn.Sequential(
Conv(c1, c2, k=7, s=2, p=3, act=True), nn.MaxPool2d(kernel_size=3, stride=2, padding=1)
)
else:
blocks = [ResNetBlock(c1, c2, s, e=e)]
blocks.extend([ResNetBlock(e * c2, c2, 1, e=e) for _ in range(n - 1)])
self.layer = nn.Sequential(*blocks)
def forward(self, x):
"""Forward pass through the ResNet layer."""
return self.layer(x)
注意❗：在
第五小节
中需要声明的模块名称为：
RCSOSA
和
ResNetLayer_RCSOSA
。
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
RCSOSA .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 .RCSOSA 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
RCSOSA
和
ResNetLayer_RCSOSA
模块
六、yaml模型文件
6.1 模型改进版本1
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-RCSOSA .yaml
。
将
rtdetr-l.yaml
中的内容复制到
rtdetr-l-RCSOSA .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
中添加
RCSOSA 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, RCSOSA, [128]] # 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, [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)
6.2 模型改进版本2⭐
此处以
ultralytics/cfg/models/rt-detr/rtdetr-resnet50.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-ResNetLayer_AKConv.yaml
。
将
rtdetr-resnet50.yaml
中的内容复制到
rtdetr-ResNetLayer_RCSOSA.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
中的所有
ResNetLayer模块
替换成
ResNetLayer_RCSOSA模块
。
# Ultralytics YOLO 🚀, AGPL-3.0 license
# RT-DETR-ResNet50 object detection model with P3-P5 outputs.
# 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, ResNetLayer_RCSOSA, [3, 64, 1, True, 1]] # 0
- [-1, 1, ResNetLayer_RCSOSA, [64, 64, 1, False, 3]] # 1
- [-1, 1, ResNetLayer_RCSOSA, [256, 128, 2, False, 4]] # 2
- [-1, 1, ResNetLayer_RCSOSA, [512, 256, 2, False, 6]] # 3
- [-1, 1, ResNetLayer_RCSOSA, [1024, 512, 2, False, 3]] # 4
head:
- [-1, 1, Conv, [256, 1, 1, None, 1, 1, False]] # 5
- [-1, 1, AIFI, [1024, 8]]
- [-1, 1, Conv, [256, 1, 1]] # 7
- [-1, 1, nn.Upsample, [None, 2, "nearest"]]
- [3, 1, Conv, [256, 1, 1, None, 1, 1, False]] # 9
- [[-2, -1], 1, Concat, [1]]
- [-1, 3, RepC3, [256]] # 11
- [-1, 1, Conv, [256, 1, 1]] # 12
- [-1, 1, nn.Upsample, [None, 2, "nearest"]]
- [2, 1, Conv, [256, 1, 1, None, 1, 1, False]] # 14
- [[-2, -1], 1, Concat, [1]] # cat backbone P4
- [-1, 3, RepC3, [256]] # X3 (16), fpn_blocks.1
- [-1, 1, Conv, [256, 3, 2]] # 17, downsample_convs.0
- [[-1, 12], 1, Concat, [1]] # cat Y4
- [-1, 3, RepC3, [256]] # F4 (19), pan_blocks.0
- [-1, 1, Conv, [256, 3, 2]] # 20, downsample_convs.1
- [[-1, 7], 1, Concat, [1]] # cat Y5
- [-1, 3, RepC3, [256]] # F5 (22), pan_blocks.1
- [[16, 19, 22], 1, RTDETRDecoder, [nc]] # Detect(P3, P4, P5)
七、成功运行结果
打印网络模型可以看到
RCSOSA
和
ResNetLayer_RCSOSA
已经加入到模型中，并可以进行训练了。
**rtdetr-l-RCSOSA **：
rtdetr-l-RCSOSA summary: 782 layers, 33,841,219 parameters, 33,841,219 gradients, 121.2 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 1970688 ultralytics.nn.AddModules.RCSOSA.RCSOSA [128, 128]
4 -1 1 5632 ultralytics.nn.modules.conv.DWConv [128, 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 6708480 ultralytics.nn.modules.block.HGBlock [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 33280 ultralytics.nn.modules.conv.Conv [128, 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-RCSOSA summary: 782 layers, 33,841,219 parameters, 33,841,219 gradients, 121.2 GFLOPs
**rtdetr-ResNetLayer_RCSOSA **：
rtdetr-ResNetLayer_RCSOSA summary: 865 layers, 119,506,339 parameters, 119,506,339 gradients, 335.6 GFLOPs
from n params module arguments
0 -1 1 9536 ultralytics.nn.AddModules.RCSOSA.ResNetLayer_RCSOSA[3, 64, 1, True, 1]
1 -1 1 967296 ultralytics.nn.AddModules.RCSOSA.ResNetLayer_RCSOSA[64, 64, 1, False, 3]
2 -1 1 5222400 ultralytics.nn.AddModules.RCSOSA.ResNetLayer_RCSOSA[256, 128, 2, False, 4]
3 -1 1 31099904 ultralytics.nn.AddModules.RCSOSA.ResNetLayer_RCSOSA[512, 256, 2, False, 6]
4 -1 1 62952448 ultralytics.nn.AddModules.RCSOSA.ResNetLayer_RCSOSA[1024, 512, 2, False, 3]
5 -1 1 524800 ultralytics.nn.modules.conv.Conv [2048, 256, 1, 1, None, 1, 1, False]
6 -1 1 789760 ultralytics.nn.modules.transformer.AIFI [256, 1024, 8]
7 -1 1 66048 ultralytics.nn.modules.conv.Conv [256, 256, 1, 1]
8 -1 1 0 torch.nn.modules.upsampling.Upsample [None, 2, 'nearest']
9 3 1 262656 ultralytics.nn.modules.conv.Conv [1024, 256, 1, 1, None, 1, 1, False]
10 [-2, -1] 1 0 ultralytics.nn.modules.conv.Concat [1]
11 -1 3 2232320 ultralytics.nn.modules.block.RepC3 [512, 256, 3]
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 2 1 131584 ultralytics.nn.modules.conv.Conv [512, 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 590336 ultralytics.nn.modules.conv.Conv [256, 256, 3, 2]
18 [-1, 12] 1 0 ultralytics.nn.modules.conv.Concat [1]
19 -1 3 2232320 ultralytics.nn.modules.block.RepC3 [512, 256, 3]
20 -1 1 590336 ultralytics.nn.modules.conv.Conv [256, 256, 3, 2]
21 [-1, 7] 1 0 ultralytics.nn.modules.conv.Concat [1]
22 -1 3 2232320 ultralytics.nn.modules.block.RepC3 [512, 256, 3]
23 [16, 19, 22] 1 7303907 ultralytics.nn.modules.head.RTDETRDecoder [1, [256, 256, 256]]
rtdetr-ResNetLayer_RCSOSA summary: 865 layers, 119,506,339 parameters, 119,506,339 gradients, 335.6 GFLOPs